Diagnostics

16 pages, 1870 KiB

Open AccessArticle

Artificial Intelligence as a Potential Tool for Predicting Surgical Margin Status in Early Breast Cancer Using Mammographic Specimen Images

by David Andras, Radu Alexandru Ilies, Victor Esanu, Stefan Agoston, Tudor Florin Marginean Jumate and George Calin Dindelegan

Diagnostics 2025, 15(10), 1276; https://doi.org/10.3390/diagnostics15101276 (registering DOI) - 17 May 2025

Abstract

Background/Objectives: Breast cancer is the most common malignancy among women globally, with an increasing incidence, particularly in younger populations. Achieving complete surgical excision is essential to reduce recurrence. Artificial intelligence (AI), including large language models like ChatGPT, has potential for supporting diagnostic [...] Read more.

Background/Objectives: Breast cancer is the most common malignancy among women globally, with an increasing incidence, particularly in younger populations. Achieving complete surgical excision is essential to reduce recurrence. Artificial intelligence (AI), including large language models like ChatGPT, has potential for supporting diagnostic tasks, though its role in surgical oncology remains limited. Methods: This retrospective study evaluated ChatGPT’s performance (ChatGPT-4, OpenAI, March 2025) in predicting surgical margin status (R0 or R1) based on intraoperative mammograms of lumpectomy specimens. AI-generated responses were compared with histopathological findings. Performance was evaluated using sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), F1 score, and Cohen’s kappa coefficient. Results: Out of a total of 100 patients, ChatGPT achieved an accuracy of 84.0% in predicting surgical margin status. Sensitivity for identifying R1 cases (incomplete excision) was 60.0%, while specificity for R0 (complete excision) was 86.7%. The positive predictive value (PPV) was 33.3%, and the negative predictive value (NPV) was 95.1%. The F1 score for R1 classification was 0.43, and Cohen’s kappa coefficient was 0.34, indicating moderate agreement with histopathological findings. Conclusions: ChatGPT demonstrated moderate accuracy in confirming complete excision but showed limited reliability in identifying incomplete margins. While promising, these findings emphasize the need for domain-specific training and further validation before such models can be implemented in clinical breast cancer workflows. Full article

(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

10 pages, 471 KiB

Open AccessArticle

Outcomes and Prognostic Markers in Extracorporeal Cardiopulmonary Resuscitation: 10-Year Experience from a Rural Tertiary Care Center

by Kamran Namjouyan, Aastha Mittal, Evan Gajkowski, Amanda Young, Sudheer Penupolu and Brendan Carry

Diagnostics 2025, 15(10), 1275; https://doi.org/10.3390/diagnostics15101275 (registering DOI) - 17 May 2025

Abstract

Background: Extracorporeal cardiopulmonary resuscitation (eCPR) is a method for initiation of cardiopulmonary bypass during resuscitation of a patient with refractory cardiac arrest to support end-organ perfusion. This retrospective study evaluates which prognostic markers are seen in patients with poor outcomes who underwent eCPR [...] Read more.

Background: Extracorporeal cardiopulmonary resuscitation (eCPR) is a method for initiation of cardiopulmonary bypass during resuscitation of a patient with refractory cardiac arrest to support end-organ perfusion. This retrospective study evaluates which prognostic markers are seen in patients with poor outcomes who underwent eCPR in our rural tertiary care center. Study Design/Methods: All patients who underwent eCPR at our center from May 2013 to January 2023 were analyzed in a retrospective manner. We then compared outcomes in patients who survived to discharge (survivors) versus those who did not survive to discharge (non-survivors). Demographic factors, body mass index, peak serum lactate in 24 h, initial rhythm, lowest mean arterial pressure within the first six hours, a requirement of renal replacement therapy, and the number of blood transfusions required during the hospitalization were analyzed. Results: 37 patients (24 males and 13 females) with a median age of 58 years (IQR: 48–65) were included. The overall mortality rate was 75.7%, and all survivors had good neurological outcomes, which were defined as Cerebral Performance Category (CPC) scores of 1 or 2. The most significant factors seen in non-survivors were obesity as measured by BMI more than 30 (odds ratio = 7.33; 95% CI 1.40–38.33; p = 0.02), and lowest MAP <65 within the first 6 h despite being on extracorporeal membrane oxygenation (0% vs. 74.1%; p = <0.01). Conclusions: This retrospective study demonstrates that initial presentations of patients who underwent eCPR with obesity and MAPS < 65 within the first 6 h despite ECMO support were seen in patients with higher mortality. Full article

(This article belongs to the Special Issue Advances in the Diagnosis and Management of Cardiovascular Disease)

► Show Figures

Figure 1

13 pages, 1713 KiB

Open AccessArticle

Risk Factors Influencing Right and Left Ventricular Variables Assessed with Gated Cadmium–Zinc–Telluride Equilibrium Radionuclide Angiocardiography in Oncology Patients

by Olav Monsson, Marc Nielsen, Thomas Kümler, Christian Haarmark and Bo Zerahn

Diagnostics 2025, 15(10), 1274; https://doi.org/10.3390/diagnostics15101274 (registering DOI) - 17 May 2025

Abstract

Background: Left ventricular ejection fraction remains the primary focus in cardiac monitoring for oncology patients undergoing potentially cardiotoxic chemotherapy, while right ventricular function is seldom examined. This study evaluates how established risk factors for left ventricular dysfunction affect right ventricular function. Methods [...] Read more.

Background: Left ventricular ejection fraction remains the primary focus in cardiac monitoring for oncology patients undergoing potentially cardiotoxic chemotherapy, while right ventricular function is seldom examined. This study evaluates how established risk factors for left ventricular dysfunction affect right ventricular function. Methods: This retrospective cohort study included 1770 patients undergoing cadmium–zinc–telluride equilibrium radionuclide angiocardiography before chemotherapy. Patients were categorized based on risk factors for left ventricular dysfunction—diabetes (DM), atrial fibrillation (AF), coronary heart disease (CHD), and previous oncological therapy—and compared to controls using independent t-tests. Results: Patients with previous oncological therapy exhibited a significantly lower right ventricular end-diastolic volume (RVEDV) (mean difference: −4.4 mL/m², 95% CI: −6.1 to −2.7, p < 0.001), lower right ventricular end-systolic volume (RVESV) (−2.3 mL/m², 95% CI: −3.4 to −1.2, p < 0.001), and lower right ventricular stroke volume (RVSV) (−2.1 mL/m², 95% CI: −3 to −1.2, p < 0.001). In patients with CHD, there was a higher right ventricular ejection fraction (RVEF) (3.0 mL/m², 95% CI: 0.8 to 5.2, p < 0.01), whereas patients with DM had lower RVEDV (−5.1 mL/m², 95% CI: −9.2 to −1, p < 0.05) and RVESV (−3.0 mL/m², 95% CI: −5.5 to −0.4, p < 0.05). No ventricular variables differed from the control group among patients with AF. Conclusions: Risk factors known to affect the left ventricle also impacted the right ventricle, with the exception of AF. Full article

(This article belongs to the Section Medical Imaging and Theranostics)

► Show Figures

Figure 1

13 pages, 5630 KiB

Open AccessCase Report

Carotid Stump Syndrome: A Case That Highlights the Necessity of Digital Subtraction Angiography for the Prompt Management of the Syndrome

by Christos Stenos, Aikaterini Anastasiou, Georgia Nikolopoulou, Panagiotis Papanagiotou, Georgios Papagiannis, Aikaterini Koutroumpi, Danai Drakopoulou, Periklis Anastasiou and Konstantina Yiannopoulou

Diagnostics 2025, 15(10), 1273; https://doi.org/10.3390/diagnostics15101273 (registering DOI) - 17 May 2025

Abstract

Background and Clinical Significance: Carotid stump syndrome (CSS) is a rare and unexpected cause of recurrent ischemic ipsilateral events in the carotid vascular territory despite the demonstrated occlusion of the internal carotid artery (ICA). It is believed to be caused by microemboli due [...] Read more.

Background and Clinical Significance: Carotid stump syndrome (CSS) is a rare and unexpected cause of recurrent ischemic ipsilateral events in the carotid vascular territory despite the demonstrated occlusion of the internal carotid artery (ICA). It is believed to be caused by microemboli due to turbulent blood flow in the patent stump of the occluded ICA that passes through anastomotic channels and retrograde flow into the middle cerebral artery circulation. Case Presentation: We describe the case of a 65-year-old male patient who suffered multiple concurrent transient ischemic attacks (TIAs) with a totally occluded ipsilateral ICA revealed by computed tomography angiography (CTA). He was diagnosed with CSS, which required the safest therapeutic approach. A further investigation with digital subtraction angiography (DSA) was performed, and a trickle of blood flow was observed in the reportedly occluded ICA. The diagnosis of a true ICA occlusion was withdrawn, and a diagnosis of pseudo-occlusion was established, affecting the final treatment strategy. Therefore, the patient underwent an ipsilateral carotid endarterectomy (CEA), and he has remained asymptomatic since then. Conclusions: The differentiation between a pseudo-occlusion and a true ICA occlusion is essential in promptly managing acute recurrent ipsilateral ischemic strokes in the carotid vascular territory. A further investigation with DSA in cases with a totally occluded ICA using CTA is essential for excluding pseudo-occlusions in ipsilaterally symptomatic patients. Full article

(This article belongs to the Special Issue Digital Imaging in Acute Ischemic Stroke)

► Show Figures

Figure 1

18 pages, 638 KiB

Open AccessReview

Utility and Challenges of Imaging in Peripheral Vestibular Disorder Diagnosis: A Narrative Review

by Gabriela Cornelia Musat, Codrut Sarafoleanu, Mihai Alexandru Preda, Calin Petru Tataru, George G. Mitroi, Andreea Alexandra Mihaela Musat, Mihnea Radu and Ovidiu Musat

Diagnostics 2025, 15(10), 1272; https://doi.org/10.3390/diagnostics15101272 (registering DOI) - 16 May 2025

Abstract

This review focuses on the contribution of medical imaging in the diagnosis of peripheral vestibular disorders. This is a narrative review based on a focused literature search conducted using PubMed and the Cochrane Library. Imaging is not usually recommended in initial consultations for [...] Read more.

This review focuses on the contribution of medical imaging in the diagnosis of peripheral vestibular disorders. This is a narrative review based on a focused literature search conducted using PubMed and the Cochrane Library. Imaging is not usually recommended in initial consultations for vestibular disorders because only 5–10% of MRI scans reveal findings directly related to the disease. The study is a review of the literature that highlights the utility and limitations of imaging such as computed tomography (CT) and magnetic resonance imaging (MRI). It follows the diagnostic approach from history and physical examination to laboratory tests and imaging. Some conditions like vestibular neuritis and benign paroxysmal positional vertigo (BPPV) have limited imaging utility due to the fine details required. Conversely, high-resolution CT and MRI are important for diagnosing Meniere’s disease, acoustic neuroma, and superior canal dehiscence. The role of imaging varies a lot among specific conditions. Advances in imaging technology, particularly high-resolution MRI, promise enhanced diagnostic capabilities. Full article

(This article belongs to the Section Medical Imaging and Theranostics)

23 pages, 2423 KiB

Open AccessArticle

Comparative Study of Cell Nuclei Segmentation Based on Computational and Handcrafted Features Using Machine Learning Algorithms

by Rashadul Islam Sumon, Md Ariful Islam Mozumdar, Salma Akter, Shah Muhammad Imtiyaj Uddin, Mohammad Hassan Ali Al-Onaizan, Reem Ibrahim Alkanhel and Mohammed Saleh Ali Muthanna

Diagnostics 2025, 15(10), 1271; https://doi.org/10.3390/diagnostics15101271 - 16 May 2025

Abstract

Background: Nuclei segmentation is the first stage of automated microscopic image analysis. The cell nucleus is a crucial aspect in segmenting to gain more insight into cell characteristics and functions that enable computer-aided pathology for early disease detection, such as prostate cancer, breast [...] Read more.

Background: Nuclei segmentation is the first stage of automated microscopic image analysis. The cell nucleus is a crucial aspect in segmenting to gain more insight into cell characteristics and functions that enable computer-aided pathology for early disease detection, such as prostate cancer, breast cancer, brain tumors, and other diagnoses. Nucleus segmentation remains a challenging task despite significant advancements in automated methods. Traditional techniques, such as Otsu thresholding and watershed approaches, are ineffective in challenging scenarios. However, deep learning-based methods exhibit remarkable results across various biological imaging modalities, including computational pathology. Methods: This work explores machine learning approaches for nuclei segmentation by evaluating the quality of nuclei image segmentation. We employed several methods, including K-means clustering, Random Forest (RF), Support Vector Machine (SVM) with handcrafted features, and Logistic Regression (LR) using features derived from Convolutional Neural Networks (CNNs). Handcrafted features extract attributes like the shape, texture, and intensity of nuclei and are meticulously developed based on specialized knowledge. Conversely, CNN-based features are automatically acquired representations that identify complex patterns in nuclei images. To assess how effectively these techniques segment cell nuclei, their performance is evaluated. Results: Experimental results show that Logistic Regression based on CNN-derived features outperforms the other techniques, achieving an accuracy of 96.90%, a Dice coefficient of 74.24, and a Jaccard coefficient of 55.61. In contrast, the Random Forest, Support Vector Machine, and K-means algorithms yielded lower segmentation performance metrics. Conclusions: The conclusions suggest that leveraging CNN-based features in conjunction with Logistic Regression significantly enhances the accuracy of cell nuclei segmentation in pathological images. This approach holds promise for refining computer-aided pathology workflows, potentially leading to more reliable and earlier disease diagnoses. Full article

(This article belongs to the Special Issue Diagnostic Imaging of Prostate Cancer)

17 pages, 1748 KiB

Open AccessReview

Vulvar Hemangioma: A Review

by Wing-Yu Sharon Siu, Yen-Chang Chen and Dah-Ching Ding

Diagnostics 2025, 15(10), 1270; https://doi.org/10.3390/diagnostics15101270 - 16 May 2025

Abstract

Objectives: To review the clinical presentation, diagnostic approach, treatment strategies, and outcomes of vulvar hemangiomas, and to evaluate the consistency of management practices in the absence of standardized guidelines. Eligibility criteria: We included case reports, case series, and observational studies describing [...] Read more.

Objectives: To review the clinical presentation, diagnostic approach, treatment strategies, and outcomes of vulvar hemangiomas, and to evaluate the consistency of management practices in the absence of standardized guidelines. Eligibility criteria: We included case reports, case series, and observational studies describing vulvar hemangiomas with clinical, histological, and management data in human subjects. Reviews, editorials, and studies unrelated to vulvar hemangiomas were excluded. Information sources: Systematic searches were conducted in PubMed, Embase, Scopus, and Web of Science up to 20 February 2025, with additional citation tracking. Results: 85 studies were included. Data were synthesized narratively due to heterogeneity in the study design and outcome reporting. Most studies described symptomatic lesions presenting as swelling, bleeding, or pain, often misdiagnosed as Bartholin cysts or varicosities. Treatment varied widely, including observation, surgical excision, embolization, and medical therapies. No evidence-based guidelines were identified. Conclusions: Vulvar hemangiomas are rare and frequently misdiagnosed. While asymptomatic lesions may be observed, symptomatic cases require individualized treatment. This review highlights the need for diagnostic vigilance and the development of standardized management protocols. Further research is needed to optimize clinical outcomes. Full article

(This article belongs to the Section Clinical Diagnosis and Prognosis)

► Show Figures

Figure 1

12 pages, 1793 KiB

Open AccessArticle

Unsupervised Clustering of Patients Undergoing Thoracoscopic Ablation Identifies Relevant Phenotypes for Advanced Atrial Fibrillation

by Ilse Meijer, Marc M. Terpstra, Oscar Camara, Henk A. Marquering, Nerea Arrarte Terreros and Joris R. de Groot

Diagnostics 2025, 15(10), 1269; https://doi.org/10.3390/diagnostics15101269 - 16 May 2025

Abstract

Background/Objectives: The rate of recurrence after ablation for atrial fibrillation (AF) is considerable. Risk stratification for AF recurrence after ablation remains incompletely developed. Unsupervised clustering is a machine learning technique which might provide valuable insights in AF recurrence by identifying patient clusters [...] Read more.

Background/Objectives: The rate of recurrence after ablation for atrial fibrillation (AF) is considerable. Risk stratification for AF recurrence after ablation remains incompletely developed. Unsupervised clustering is a machine learning technique which might provide valuable insights in AF recurrence by identifying patient clusters using numerous clinical characteristics. We hypothesize that unsupervised clustering identifies patient clusters with different clinical phenotypes, including AF type and cardiovascular morbidities, and ablation outcomes. Methods: Baseline and procedural characteristics of 658 patients undergoing thoracoscopic ablation for advanced AF (persistent, with enlarged left atria, or with previous failed catheter ablation) between 2008 and 2021 were collected. Principal component analysis (PCA) was used as an unsupervised dimensionality reduction technique, followed by K-Means clustering for unsupervised data clustering. The silhouette score was used to determine the optimal number of clusters, resulting in the formation of three clusters. CHA₂DS₂-VASc score and AF recurrence were not included in the clustering, but were compared between clusters. Moreover, we compared the patients with and without previously established risk factors for AF recurrence for each cluster. Results: Unsupervised clustering resulted in three distinct clusters. Cluster I had a significantly lower rate of AF recurrence than Cluster II, which contained significantly more persistent AF patients than the other clusters. The CHA₂DS₂-VASc score in Cluster III was significantly higher than in the other clusters. In all clusters, but particularly in Cluster III, the recurrence risk was higher for persistent AF patients and female patients. In Cluster II, the recurrence risk was not influenced by an increased left atrial volume index, unlike other clusters. Conclusions: Using unsupervised clustering of clinical and procedural data, we identified three distinct advanced AF patient clusters with differences in AF type, CHA₂DS₂-VASc score, and AF recurrence. We found that established risk factors like BMI, AF type, and LAVI vary in importance across clusters. Full article

(This article belongs to the Special Issue Diagnosis and Management of Arrhythmias)

► Show Figures

Figure 1

20 pages, 1428 KiB

Open AccessArticle

Quantifying Body Motion Synchrony in Autism Spectrum Disorder Using a Phase Difference Detection Algorithm: Toward a Novel Behavioral Biomarker

by Jinhwan Kwon and Hiromi Kotani

Diagnostics 2025, 15(10), 1268; https://doi.org/10.3390/diagnostics15101268 - 16 May 2025

Abstract

Background/Objectives: Nonverbal synchrony—the temporal coordination of physical behaviors such as head movement and gesture—is a critical component of effective social communication. Individuals with autism spectrum disorder (ASD) are often described as having impairments in such synchrony, but objective and scalable tools to [...] Read more.

Background/Objectives: Nonverbal synchrony—the temporal coordination of physical behaviors such as head movement and gesture—is a critical component of effective social communication. Individuals with autism spectrum disorder (ASD) are often described as having impairments in such synchrony, but objective and scalable tools to measure these disruptions remain limited. This study aims to assess body motion synchrony in ASD using phase-based features as potential markers of social timing impairments. Methods: We applied a phase difference detection algorithm to high-resolution triaxial accelerometer data obtained during structured, unidirectional verbal communication. A total of 72 participants (36 typically developing TD–TD and 36 TD–ASD) were divided into dyads. ASD participants always assumed the listener role, enabling the isolation of receptive synchrony. Four distribution-based features—synchrony activity, directionality, variability, and coherence—were extracted from the phase difference data to assess synchrony dynamics. Results: Compared to the TD group, the ASD group exhibited significantly lower synchrony activity (ASD: 5.96 vs. TD: 9.63 times/min, p = 0.0008, Cohen’s d = 1.23), greater temporal variability (ASD: 384.4 ms vs. TD: 311.1 ms, p = 0.0036, d = 1.04), and reduced coherence (ASD: 0.13 vs. TD: 0.81, p = 0.036, d = 0.73). Although the mean phase difference did not differ significantly between groups, the ASD group displayed weaker and more irregular synchrony patterns, indicating impaired temporal stability. Conclusions: Our findings highlight robust impairments in nonverbal head motion synchrony in ASD, not only in frequency but also in terms of temporal stability and convergence. The use of phase-based synchrony features provides a continuous, high-resolution, language-independent metric for social timing. These metrics offer substantial potential as behavioral biomarkers for diagnostic support and intervention monitoring in ASD. Full article

(This article belongs to the Section Clinical Diagnosis and Prognosis)

► Show Figures

Figure 1

15 pages, 1396 KiB

Open AccessCase Report

Fibrotic Hypersensitivity Pneumonitis: A Diagnostic Challenge Leading to Lung Transplantation

by Maria-Daniela Mot, Dana Cristina Olar, Paula Alexandra Vulciu, Paula-Irina Barata, Ana-Liana Bouros-Tataru, Denis Bogdan Butari, Florin Mihai Șandor and Laura Ioana Bondar

Diagnostics 2025, 15(10), 1267; https://doi.org/10.3390/diagnostics15101267 - 16 May 2025

Abstract

Background/Objectives: Hypersensitivity pneumonitis (HP), a subtype of interstitial lung disease (ILD), is often misdiagnosed as idiopathic pulmonary fibrosis (IPF), particularly when the causative antigen cannot be identified. Typically resulting from chronic exposure to inhaled organic particles smaller than 5 microns, HP presents [...] Read more.

Background/Objectives: Hypersensitivity pneumonitis (HP), a subtype of interstitial lung disease (ILD), is often misdiagnosed as idiopathic pulmonary fibrosis (IPF), particularly when the causative antigen cannot be identified. Typically resulting from chronic exposure to inhaled organic particles smaller than 5 microns, HP presents a diagnostic challenge. This report outlines a case of fibrotic HP initially misclassified as asthma. No triggering antigen was identified despite extensive investigation. The disease progressed despite corticosteroid, immunosuppressive, and antifibrotic therapy, ultimately leading to an advanced fibrotic stage and requiring lung transplantation. This clinical course is rare and infrequently reported, particularly in cases requiring lung transplantation without an identifiable causative antigen. Such progression is uncommon and underreported, especially in patients initially misclassified as having asthma. Methods: Medical records of 24 patients diagnosed with HP were reviewed. Only one case demonstrated progression to fibrotic HP; this case was selected for detailed analysis. Results: Clinical and functional deterioration occurred despite standard therapy. Given the advanced stage of fibrosis and treatment resistance, lung transplantation was deemed the next appropriate therapeutic option. Conclusions: HP remains underdiagnosed due to difficulties in identifying the causative antigen and overlapping features with other ILDs. Early and accurate differentiation from IPF is essential, particularly in progressive fibrotic forms unresponsive to conventional therapies. Full article

(This article belongs to the Special Issue Diagnosis of Cardio-Thoracic Diseases)

► Show Figures

Figure 1

11 pages, 906 KiB

Open AccessArticle

Single Angio-Seal™ Device as a Simplified and Technically Feasible Alternative for Tract Closure in Percutaneous Portal Vein Access: A Retrospective Study

by Ismail Karluka and Mustafa Mazıcan

Diagnostics 2025, 15(10), 1266; https://doi.org/10.3390/diagnostics15101266 - 16 May 2025

Abstract

Purpose: This study aimed to evaluate the efficacy and safety of the Angio-Seal™ VIP vascular closure device (VCD) in achieving hemostasis following percutaneous transhepatic portal venous interventions. Methods: This retrospective study evaluated 20 patients (mean age: 52.85 ± 16.18 years; 80% male) who [...] Read more.

Purpose: This study aimed to evaluate the efficacy and safety of the Angio-Seal™ VIP vascular closure device (VCD) in achieving hemostasis following percutaneous transhepatic portal venous interventions. Methods: This retrospective study evaluated 20 patients (mean age: 52.85 ± 16.18 years; 80% male) who underwent percutaneous transhepatic portal vein interventions followed by tract closure with the Angio-Seal™ device between January 2016 and September 2024. Procedural data, pre- and post-procedural hemoglobin and hematocrit levels, and complications were analyzed. Technical success was defined as the successful deployment of the device with immediate hemostasis and no evidence of bleeding on post-procedural imaging. Results: Technical success, as defined in this study, was achieved in all 20 procedures (100%). The mean hemoglobin level declined from 11.91 ± 2.01 g/dL to 11.09 ± 2.19 g/dL (p < 0.001), and the mean hematocrit level decreased from 36.18 ± 6.03% to 32.98 ± 5.80% (p = 0.001). A hemoglobin drop ≥2 g/dL occurred in two patients (10%) and a hematocrit drop ≥4% in six patients (30%); none were associated with imaging or clinical evidence of hemorrhage. No major complications were observed. Minor complications, including localized pain managed with analgesics, occurred in five patients (25%). Follow-up imaging confirmed the absence of hemoperitoneum or device-related failure. Conclusions: Angio-Seal™ is a technically feasible, safe, and effective option for tract closure following percutaneous transhepatic portal vein access. This single-device approach may offer a cost-effective alternative to traditional embolization techniques. However, more extensive prospective studies are required to validate these findings. Full article

(This article belongs to the Special Issue Advancements in Interventional Radiology Techniques in Vascular and Extravascular Diseases)

► Show Figures

Figure 1

10 pages, 1243 KiB

Open AccessCase Report

A Case of Rheumatoid Arthritis Complicated by Compression of the Popliteal Artery and Tibial Nerve Due to an Organized Hematoma in the Popliteal Fossa: A Case Report and Literature Review

by Gi Beom Kim, Min Cheol Chang and Hyun-Je Kim

Diagnostics 2025, 15(10), 1265; https://doi.org/10.3390/diagnostics15101265 (registering DOI) - 16 May 2025

Abstract

Background/Objectives: Among the various types of masses that can cause compression, hematomas are a relatively common but often overlooked cause. Rheumatoid arthritis (RA) is associated with bleeding problems due to vascular inflammation, platelet dysfunction, impaired production of clotting factors, and medication use. Case [...] Read more.

Background/Objectives: Among the various types of masses that can cause compression, hematomas are a relatively common but often overlooked cause. Rheumatoid arthritis (RA) is associated with bleeding problems due to vascular inflammation, platelet dysfunction, impaired production of clotting factors, and medication use. Case Presentation: We report a case of a 76-year-old woman with RA who developed vascular and neurological symptoms in her right lower leg due to compression of the popliteal artery and tibial nerve by an organized hematoma in the popliteal fossa. She experienced swelling, pain, and plantar flexor weakness in the affected leg with no history of trauma. Magnetic resonance imaging revealed a mass measuring 1.2 × 1.0 × 3.0 cm in size in the right popliteal fossa that was in contact with the popliteal artery and tibial nerve on its posterolateral aspect. Electrodiagnostic examination revealed that the right tibial neuropathy developed most probably around the knee level. Surgical excision of the hematoma resulted in almost complete resolution of symptoms, and excisional biopsy disclosed findings of an organized hematoma. We confirmed that the patient’s symptoms were induced by compression of the popliteal artery and tibial nerve due to the organized hematoma in the right popliteal fossa. Conclusions: This case report emphasizes the importance of considering space-occupying lesions, such as organized hematomas, in patients with RA who develop neurological and vascular symptoms. Full article

(This article belongs to the Special Issue Diagnosis and Management of Musculoskeletal Disorders)

► Show Figures

Figure 1

19 pages, 9021 KiB

Open AccessSystematic Review

The Association of Placental Grading with Perinatal Outcomes: A Systematic Review and Meta-Analysis

by Antonios Siargkas, Christina Pachi, Meletios P. Nigdelis, Sofoklis Stavros, Ekaterini Domali, Apostolos Mamopoulos, Ioannis Tsakiridis and Themistoklis Dagklis

Diagnostics 2025, 15(10), 1264; https://doi.org/10.3390/diagnostics15101264 - 15 May 2025

Abstract

Objective: Premature placental calcification (PPC) has been implicated in adverse perinatal outcomes, yet its clinical significance remains controversial. This meta-analysis aimed to quantitatively synthesize current data on the association between PPC, defined as grade 3 placental calcification before 36⁺⁶ weeks of [...] Read more.

Objective: Premature placental calcification (PPC) has been implicated in adverse perinatal outcomes, yet its clinical significance remains controversial. This meta-analysis aimed to quantitatively synthesize current data on the association between PPC, defined as grade 3 placental calcification before 36⁺⁶ weeks of gestation and adverse perinatal outcomes. Data Sources: A systematic search was conducted in MEDLINE, Scopus and The Cochrane Library from inception until 11 March 2025, to identify eligible studies. Study Eligibility Criteria: Observational studies including singleton pregnancies with PPC diagnosed via ultrasonography between 28⁺⁰ and 36⁺⁶ weeks of gestation and comparing them with pregnancies with Grannum grade 0, 1, or 2 placentas were considered eligible. Methods: Study quality was assessed using the Newcastle−Ottawa Scale, and the risk of bias was evaluated with the Quality In Prognosis Studies tool. The primary outcomes were small-for-gestational-age (SGA) neonates and preeclampsia. Heterogeneity was assessed using Cochran’s Q test and the I² statistic. Meta-analyses were conducted using a random-effects model, with outcomes reported as relative risk (RR) or mean difference (MD) with 95% confidence intervals (CIs). Results: In total, nine cohort studies were included. PPC was associated with an increased risk of SGA (RR, 1.99; 95% CI, 1.46−2.70), preeclampsia (RR, 5.27; 95% CI, 2.24−12.40), fetal growth restriction (RR, 2.31; 95% CI, 1.30−4.09), preterm delivery (RR, 2.11; 95% CI, 1.00−4.45), suspected fetal hypoxia (RR, 1.71; 95% CI, 1.13–2.56), low 5 min Apgar score (RR, 2.28; 95% CI, 1.50−3.44) and neonatal intensive care unit admission (RR, 1.80; 95% CI, 1.02−3.18). No significant associations were found with fetal or neonatal death (RR, 2.75; 95% CI, 0.87−8.71), cesarean delivery (RR, 1.26; 95% CI, 0.90−1.78), gestational diabetes mellitus (RR, 1.17; 95% CI, 0.81−1.70), neonatal resuscitation (RR, 1.04; 95% CI, 0.92−1.16), birthweight (MD, −187.46 g; 95% CI, −413.14 to +38.21), or gestational age at birth (MD, −0.62 weeks; 95% CI, −1.36 to +0.11). A sensitivity analysis excluding high-risk-of-bias studies yielded consistent results. Conclusions: PPC is associated with several adverse perinatal outcomes, including SGA and preeclampsia. While the clinical significance of placental grading has remained limited in recent years, this study has shown that PPC may serve as an early indicator of placental insufficiency, warranting enhanced fetal surveillance and risk assessment in affected pregnancies. Further research is needed to refine its prognostic utility and integration into obstetric practice. Full article

(This article belongs to the Special Issue Diagnosis and Management of Contemporary Issues in Maternal-Fetal Medicine)

► Show Figures

Figure 1

14 pages, 2076 KiB

Open AccessArticle

Incidental Calcifications of Carotid and Vertebral Arteries: Frequency and Associations in Pediatric Population

by Turkhun Cetin, Gokce Cinar, Berna Ucan, Fulya Memis, Baris Irgul and Sonay Aydin

Diagnostics 2025, 15(10), 1263; https://doi.org/10.3390/diagnostics15101263 - 15 May 2025

Abstract

Background: Calcifications in the carotid and vertebral arteries may be present on cranial and temporal bone CT imaging of pediatric patients. Few studies have investigated the frequency, location, and patterns of carotid artery calcifications in this age group. However, these studies are outdated [...] Read more.

Background: Calcifications in the carotid and vertebral arteries may be present on cranial and temporal bone CT imaging of pediatric patients. Few studies have investigated the frequency, location, and patterns of carotid artery calcifications in this age group. However, these studies are outdated and do not include data on the vertebral artery. The aim of this study was to determine the frequency, location, and pattern of incidental carotid and vertebral artery calcifications on cranial CT and temporal bone CT images in children under 15 years of age. We also aimed to investigate possible associations between these calcifications and various diseases. Methods: A total of 300 CT images of the cranial and temporal bone of 300 pediatric patients were retrospectively evaluated for the presence of calcification in the carotid and vertebral arteries. The evaluation included determining the presence of calcification in the artery, the pattern of calcification, the degree of calcification, and its anatomical location. Results: In the current study, 300 CT images were analyzed, and calcifications were found in the vertebral artery in 17 patients (5.6%) and the carotid artery in 82 patients (27.3%). The supraclinoid segment and the carotid siphon regions are the most common locations of carotid artery calcifications, with 62 patients (20.7%). The V4 segment is also the most common location for vertebral artery calcifications, with 15 patients (5%). Focal punctate calcification is the most common pattern (65 patients, 21.7%). Incidental carotid and vertebral artery calcifications did not correlate with other diseases. Conclusions: Carotid and vertebral artery calcifications are common incidental findings in pediatric patients. In our study, no association was found between other diseases and incidental carotid and vertebral artery calcifications. Full article

(This article belongs to the Special Issue Advances in the Diagnosis and Management of Pediatric Diseases)

► Show Figures

Figure 1

4 pages, 3733 KiB

Open AccessInteresting Images

Simultaneous Identification of Tc-99m-Sestamibi-Positive Autonomous Thyroid Adenoma and Adjacent F-18-Ethylcholine-Positive Parathyroid Adenoma in Patient with Graves’ Disease Using Real-Time Ultrasound Fusion Imaging

by Theresa Leder, Philipp Seifert, Falk Gühne and Martin Freesmeyer

Diagnostics 2025, 15(10), 1262; https://doi.org/10.3390/diagnostics15101262 - 15 May 2025

Abstract

A 49-year-old female presented for nuclear medicine diagnostics of a sonographically suspected parathyroid adenoma dorsal to the cranial pole of the right thyroid lobe. The patient received Tc-99m-pertechnetate and Tc-99m-sestamibi (including SPECT/CT) scans, revealing no sestamibi uptake by the suspected parathyroid adenoma but [...] Read more.

A 49-year-old female presented for nuclear medicine diagnostics of a sonographically suspected parathyroid adenoma dorsal to the cranial pole of the right thyroid lobe. The patient received Tc-99m-pertechnetate and Tc-99m-sestamibi (including SPECT/CT) scans, revealing no sestamibi uptake by the suspected parathyroid adenoma but a ventrally adjacent autonomous thyroid adenoma. Additional F-18-ethylcholine-PET/CT as well as subsequent Tc-99m-sestamibi-SPECT/US and F-18-ethylcholine-PET/US fusion imaging confirmed the suspected diagnosis of simultaneous autonomous thyroid adenoma and parathyroid adenoma. A blood analysis showed additional Graves’ disease. Full article

(This article belongs to the Section Medical Imaging and Theranostics)

► Show Figures

Figure 1

3 pages, 661 KiB

Open AccessInteresting Images

Greater Omentum Abscess Revealing an Upper Genital Infection

by Romain L’Huillier and Alexandra Braillon

Diagnostics 2025, 15(10), 1261; https://doi.org/10.3390/diagnostics15101261 - 15 May 2025

Abstract

In this clinical case, we report an upper genital infection revealed on Computed Tomography by a greater omentum abscess. The infection was confirmed by endocervical swabs and ultrasound-guided sampling of the epiploic abscess, which found the same bacteria (Parvimonas micra). Omental [...] Read more.

In this clinical case, we report an upper genital infection revealed on Computed Tomography by a greater omentum abscess. The infection was confirmed by endocervical swabs and ultrasound-guided sampling of the epiploic abscess, which found the same bacteria (Parvimonas micra). Omental absecesses are most often secondary to spontaneous or post-operative infarction of the greater omentum, and this observation provides a new cause for epiploic abscesses. Full article

(This article belongs to the Section Medical Imaging and Theranostics)

► Show Figures

Figure 1

20 pages, 8277 KiB

Open AccessArticle

Investigating the Role of Intravoxel Incoherent Motion Diffusion-Weighted Imaging in Evaluating Multiple Sclerosis Lesions

by Othman I. Alomair, Sami A. Alghamdi, Abdullah H. Abujamea, Ahmed Y. AlfIfi, Yazeed I. Alashban and Nyoman D. Kurniawan

Diagnostics 2025, 15(10), 1260; https://doi.org/10.3390/diagnostics15101260 - 15 May 2025

Abstract

Background: Multiple sclerosis (MS) is a chronic and heterogeneous disease characterized by demyelination and axonal loss and damage. Magnetic resonance imaging (MRI) has been employed to distinguish these changes in various types of MS lesions. Objectives: We aimed to evaluate intravoxel incoherent [...] Read more.

Background: Multiple sclerosis (MS) is a chronic and heterogeneous disease characterized by demyelination and axonal loss and damage. Magnetic resonance imaging (MRI) has been employed to distinguish these changes in various types of MS lesions. Objectives: We aimed to evaluate intravoxel incoherent motion (IVIM) diffusion and perfusion MRI metrics across different brain regions in healthy individuals and various types of MS lesions, including enhanced, non-enhanced, and black hole lesions. Methods: A prospective study included 237 patients with MS (65 males and 172 females) and 29 healthy control participants (25 males and 4 females). The field strength was 1.5 Tesla. The imaging sequences included three-dimensional (3D) T₁, 3D fluid-attenuated inversion recovery, two-dimensional (2D) T₁, T₂-weighted imaging, and 2D diffusion-weighted imaging (DWI) sequences. IVIM-derived parameters—apparent diffusion coefficient (ADC), pure molecular diffusion (D), pseudo-diffusion (D*), and perfusion fraction (f)—were quantified for commonly observed lesion types (2506 lesions from 224 patients with MS, excluding 13 patients due to MRI artifacts or not meeting the diagnostic criteria for RR-MS) and for corresponding brain regions in 29 healthy control participants. A one-way analysis of variance, followed by post-hoc analysis (Tukey’s test), was performed to compare mean values between the healthy and MS groups. Receiver operating characteristic curve analyses, including area under the curve, sensitivity, and specificity, were conducted to determine the cutoff values of IVIM parameters for distinguishing between the groups. A p-value of ≤0.05 and 95% confidence intervals were used to report statistical significance and precision, respectively. Results: All IVIM parametric maps in this study discriminated among most MS lesion types. ADC, D, and D* values for MS black hole lesions were significantly higher (p < 0.0001) than those for other MS lesions and healthy controls. ADC, D, and D* maps demonstrated high sensitivity and specificity, whereas f maps exhibited low sensitivity but high specificity. Conclusions: IVIM parameters provide valuable diagnostic and clinical insights by demonstrating high sensitivity and specificity in evaluating different categories of MS lesions. Full article

(This article belongs to the Special Issue Neurological Diseases: Biomarkers, Diagnosis and Prognosis)

► Show Figures

Figure 1

26 pages, 8187 KiB

Open AccessArticle

The Effect of Lesion Length on Doppler Velocities Used Routinely to Determine Carotid Stenosis Cross-Sectional Severity

by Wladyslaw Dabrowski, Lukasz Tekieli, Anna Kablak-Ziembicka, Justyna Stefaniak, Karolina Dzierwa, Adam Mazurek, Piotr Paluszek, Krzysztof Zmudka, Piotr Pieniazek and Piotr Musialek

Diagnostics 2025, 15(10), 1259; https://doi.org/10.3390/diagnostics15101259 - 15 May 2025

Abstract

Background/Objective: Transcutaneous Doppler ultrasound is a fundamental tool in evaluating carotid stenosis cross-sectional severity (CS-CSS) in clinical practice because peak-systolic and end-diastolic velocities (PSV, EDV) increase with angiographic diameter stenosis. We tested the hypothesis that lesion length (LL) may affect PSV and [...] Read more.

Background/Objective: Transcutaneous Doppler ultrasound is a fundamental tool in evaluating carotid stenosis cross-sectional severity (CS-CSS) in clinical practice because peak-systolic and end-diastolic velocities (PSV, EDV) increase with angiographic diameter stenosis. We tested the hypothesis that lesion length (LL) may affect PSV and EDV. Methods: CARUS (Carotid Artery IntravasculaR Ultrasound Study) prospectively enrolled 300 consecutive patients (age 47–83 years, 64.3% men, 63.3% symptomatic) with carotid stenosis ≥50% by Doppler ultrasound considered diagnostic (corelab analyst). We correlated stenosis LL (mm) and minimal lumen area (MLA, mm²) with PSV and EDV. Results: IVUS imaging (20 MHz Volcano/Philips) was uncomplicated. As IVUS probe forward/backward movement with systole/diastole (“jumping”-related artifact superimposed on motorized pullback) restrained LL (but not MLA) determination, LL measurement was angiographic. Final data set included 293 patients/stenoses (applicable to seven angiograms unsuitable for LL measurement). Irrespective of CS-CSS, a significant LL effect on PSV and EDV occurred with LL ≥ 7 mm (n = 224/293, i.e., 76.5% study patients/lesions; r = 0.38 and r = 0.35); for MLA irrespective of CS-CCS the coefficients were r = 0.49 (PSV) and r = 0.42 (EDV); p < 0.001 for all. For LL and MLA considered together, the correlations were stronger: r = 0.61 (PSV) and r = 0.54 (EDV); p < 0.0001 for both. Combined LL and MLA effect was represented by the following formulas: PSV = 0.31 × LL/MLA + 2.02 [m/s]; EDV = 0.12 × LL/MLA + 0.63 [m/s], enabling to correct the PSV (EDV)-based assessment of CS-CSS for the LL effect. Conclusions: This study provides, for the first time, systematic evidence that the length of carotid stenosis significantly affects lesional Doppler velocities. We established formulas incorporating the contribution of both stenosis length and its cross-sectional severity to PSV and EDV. We advocate including stenosis length measurement in duplex ultrasound reports when performing PSV (EDV)-based assessment of carotid cross-sectional stenosis severity. Full article

(This article belongs to the Special Issue Advances in Ultrasound)

► Show Figures

Graphical abstract

13 pages, 915 KiB

Open AccessArticle

Management of Postoperative Pancreatic Fluid Collection and Role of Endoscopy: A Case Series and Review of the Literature

by Chiara Coluccio, Ilaria Tarantino, Maria Chiara Petrone, Edoardo Forti, Stefano Francesco Crinò, Alessandro Fugazza, Roberto Di Mitri, Cecilia Binda, Davide Trama, Arnaldo Amato, Alessandro Redaelli, Germana De Nucci, Fabia Attili, Mario Luciano Brancaccio, Claudio Giovanni De Angelis, Mauro Lovera, Antonio Facciorusso, Andrea Anderloni and Carlo Fabbri

Diagnostics 2025, 15(10), 1258; https://doi.org/10.3390/diagnostics15101258 - 15 May 2025

Abstract

Background: Postoperative fluid collections (POFCs) after abdominal surgeries, particularly pancreatic surgeries, are associated with high morbidity and mortality rates and were historically managed with surgical re-exploration and drainage. In particular, postoperative pancreatic fluid collections (PPFCs) are the most common complications after pancreatic surgery [...] Read more.

Background: Postoperative fluid collections (POFCs) after abdominal surgeries, particularly pancreatic surgeries, are associated with high morbidity and mortality rates and were historically managed with surgical re-exploration and drainage. In particular, postoperative pancreatic fluid collections (PPFCs) are the most common complications after pancreatic surgery resulting from pancreatic leaks. They occur in up to 50% of cases, and approximately 10% of them need to be drained to avoid further sequelae. Endoscopic ultrasonography (EUS)-guided drainage of PPFCs represents the first-line treatment nowadays, but many aspects are still debated. Methods: We describe a retrospective case series of patients from multiple Italian centers who underwent EUS-guided drainage (EUS-D) of POFCs, aiming to provide data on the efficacy and safety of this procedure, supported by a review of the existing literature on this topic. The primary outcomes were technical and clinical success, and the secondary outcomes were the type and rate of adverse events (AEs) and the rate of recurrence. Results: A total of 47 patients were included. The procedure demonstrated a technical success rate of 98% (46/47) and a clinical success rate of 96% (45/47). The rate of AEs was 11% (5/47), represented by bleeding (3/5), stent occlusion (1/5), and buried syndrome (1/5). Conclusions: Management of POFCs has shifted over time towards an endoscopic approach with optimal efficacy and safety. Full article

(This article belongs to the Special Issue Endoscopic Ultrasound (EUS) in Gastrointestinal Diseases)

► Show Figures

Figure 1

20 pages, 3468 KiB

Open AccessArticle

Bayesian Integration of Bronchoalveolar Lavage miRNAs and KL-6 in Progressive Pulmonary Fibrosis Diagnosis

by Piera Soccio, Valerio Longo, Corrado Mencar, Pasquale Tondo, Fabiola Murgolo, Giulia Scioscia and Donato Lacedonia

Diagnostics 2025, 15(10), 1257; https://doi.org/10.3390/diagnostics15101257 - 15 May 2025

Abstract

Background/Objectives: Progressive pulmonary fibrosis (PPF) represents one of the most severe and complex challenges in respiratory medicine, characterized by a rapid decline in lung function and often poor prognosis, making it a priority in research on interstitial lung diseases (ILDs). The aim [...] Read more.

Background/Objectives: Progressive pulmonary fibrosis (PPF) represents one of the most severe and complex challenges in respiratory medicine, characterized by a rapid decline in lung function and often poor prognosis, making it a priority in research on interstitial lung diseases (ILDs). The aim of this study is to correlate classical clinical features and three genetic biomarkers with the diagnosis and prognosis of progressive pulmonary fibrosis in ILDs. Methods: This study involved 19 patients with progressive pulmonary fibrosis (PPF) and 20 patients with non-progressive pulmonary fibrosis (nPPF) from the S.C. of Respiratory System Diseases at the Policlinico of Foggia (Italy) between 2015 and 2022. All participants underwent pulmonary function tests (PFTs), a 6 min walk test (6MWT), and bronchoalveolar lavage (BAL) sampling, following the acquisition of written consent for these procedures. Bayesian analysis with generalized linear models has been applied for both diagnostic and prognostic classification. Results: The proposed Bayesian model enables the estimation of the contribution of each considered feature, and the quantification of the uncertainty that is consequential to the small size of the dataset. The analysis of miRNAs such as miR-21 and miR-92a, alongside the protein biomarker KL-6, was identified as a significant indicator for PPF diagnosis, enhancing both the sensitivity and specificity of predictions. Conclusions: The identification of specific genetic markers such as microRNAs and their integration with traditional clinical characteristics can significantly enhance the management of patients with the disease. This multidimensional approach, which integrates clinical data with omics data, could enable more precise identification and monitoring of the disease and potentially optimize future treatments through larger studies and extended follow-ups. Full article

(This article belongs to the Section Pathology and Molecular Diagnostics)

► Show Figures

Figure 1

11 pages, 1787 KiB

Open AccessArticle

Spectralis Optical Coherence Tomography for Evaluating Ocular Hypertensive and Glaucoma Suspect Eyes: Real-World Data from Taiwan

by Man-Sze Wong, Chao-Wei Wu, Yue-Cune Chang and Hsin-Yi Chen

Diagnostics 2025, 15(10), 1256; https://doi.org/10.3390/diagnostics15101256 - 15 May 2025

Abstract

Objectives: The aim of this research was to evaluate the diagnostic performance of Spectralis optical coherence tomography (OCT) parameters for ocular hypertensive (OH) and glaucoma suspect (GS) eyes in an Asian population from Taiwan. Methods: This retrospective cross-sectional study included 258 [...] Read more.

Objectives: The aim of this research was to evaluate the diagnostic performance of Spectralis optical coherence tomography (OCT) parameters for ocular hypertensive (OH) and glaucoma suspect (GS) eyes in an Asian population from Taiwan. Methods: This retrospective cross-sectional study included 258 OH (mean deviation [MD]: −1.10 ± 1.75 dB), 380 GS (MD: −1.24 ± 2.63 dB), and 742 normal (MD: −1.47 ± 3.29 dB) eyes. The diagnostic performance of Spectralis OCT parameters, including optic nerve head (ONH) and macular parameters, was compared among groups. The area under the receiver operating characteristic curve (AUC) of each parameter signified its power to differentiate between normal and OH or GS eyes. Results: In various scanning protocols, circumpapillary retinal nerve fiber layer (NFL)-temporal (AUC = 0.538), macular NFL-outer temporal (AUC = 0.611), and retinal average thickness (RAT)_1.8 (AUC = 0.578) were the best parameters in distinguishing OH eyes from normal eyes. Moreover, minimum rim width (MRW)-mean global (AUC = 0.737), macular NFL-outer temporal (AUC = 0.558), and RAT_2.8 (AUC = 0.543) were the best parameters in distinguishing GS eyes from normal eyes. After adjusting for age and refraction effects, we determined that the AUCs for OH and GS were 0.694 and 0.646, respectively. Conclusions: Our real-world data indicate that Spectralis OCT parameters show some potential for early glaucoma detection and monitoring, but their current diagnostic effectiveness remains limited. When managing OH eyes, caution is required in evaluating macular retinal NFL thickness in addition to the ONH. Bruch’s membrane opening–MRW is a potential objective indicator of ONH changes in GS eyes. Full article

(This article belongs to the Special Issue Diagnosis and Management of Ophthalmic Disorders)

► Show Figures

Figure 1

20 pages, 1989 KiB

Open AccessArticle

Deep Reinforcement Learning for CT-Based Non-Invasive Prediction of SOX9 Expression in Hepatocellular Carcinoma

by Minghui Liu, Yi Wei, Tianshu Xie, Meiyi Yang, Xuan Cheng, Lifeng Xu, Qian Li, Feng Che, Qing Xu, Bin Song and Ming Liu

Diagnostics 2025, 15(10), 1255; https://doi.org/10.3390/diagnostics15101255 - 15 May 2025

Abstract

Background: The transcription factor SOX9 plays a critical role in various diseases, including hepatocellular carcinoma (HCC), and has been implicated in resistance to sorafenib treatment. Accurate assessment of SOX9 expression is important for guiding personalized therapy in HCC patients; however, a reliable non-invasive [...] Read more.

Background: The transcription factor SOX9 plays a critical role in various diseases, including hepatocellular carcinoma (HCC), and has been implicated in resistance to sorafenib treatment. Accurate assessment of SOX9 expression is important for guiding personalized therapy in HCC patients; however, a reliable non-invasive method for evaluating SOX9 status remains lacking. This study aims to develop a deep learning (DL) model capable of preoperatively and non-invasively predicting SOX9 expression from CT images in HCC patients. Methods: We retrospectively analyzed a dataset comprising 4011 CT images from 101 HCC patients who underwent surgical resection followed by sorafenib therapy at West China Hospital, Sichuan University. A deep reinforcement learning (DRL) approach was proposed to enhance prediction accuracy by identifying and focusing on image regions highly correlated with SOX9 expression, thereby reducing the impact of background noise. Results: Our DRL-based model achieved an area under the curve (AUC) of 91.00% (95% confidence interval: 88.64–93.15%), outperforming conventional DL methods by over 10%. Furthermore, survival analysis revealed that patients with SOX9-positive tumors had significantly shorter recurrence-free survival (RFS) and overall survival (OS) compared to SOX9-negative patients, highlighting the prognostic value of SOX9 status. Conclusions: This study demonstrates that a DRL-enhanced DL model can accurately and non-invasively predict SOX9 expression in HCC patients using preoperative CT images. These findings support the clinical utility of imaging-based SOX9 assessment in informing treatment strategies and prognostic evaluation for patients with advanced HCC. Full article

(This article belongs to the Special Issue 3rd Edition: AI/ML-Based Medical Image Processing and Analysis)

► Show Figures

Figure 1

14 pages, 3518 KiB

Open AccessArticle

Object Detection in Laparoscopic Surgery: A Comparative Study of Deep Learning Models on a Custom Endometriosis Dataset

by Andrey Bondarenko, Vilen Jumutc, Antoine Netter, Fanny Duchateau, Henrique Mendonca Abrão, Saman Noorzadeh, Giuseppe Giacomello, Filippo Ferrari, Nicolas Bourdel, Ulrik Bak Kirk and Dmitrijs Bļizņuks

Diagnostics 2025, 15(10), 1254; https://doi.org/10.3390/diagnostics15101254 - 15 May 2025

Abstract

Background: Laparoscopic surgery for endometriosis presents unique challenges due to the complexity of and variability in lesion appearances within the abdominal cavity. This study investigates the application of deep learning models for object detection in laparoscopic videos, aiming to assist surgeons in accurately [...] Read more.

Background: Laparoscopic surgery for endometriosis presents unique challenges due to the complexity of and variability in lesion appearances within the abdominal cavity. This study investigates the application of deep learning models for object detection in laparoscopic videos, aiming to assist surgeons in accurately identifying and localizing endometriosis lesions and related anatomical structures. A custom dataset was curated, comprising of 199 video sequences and 205,725 frames. Of these, 17,560 frames were meticulously annotated by medical professionals. The dataset includes object detection annotations for 10 object classes relevant to endometriosis, alongside segmentation masks for some classes. Methods: To address the object detection task, we evaluated the performance of two deep learning models—FasterRCNN and YOLOv9—under both stratified and non-stratified training scenarios. Results: The experimental results demonstrated that stratified training significantly reduced the risk of data leakage and improved model generalization. The best-performing FasterRCNN object detection model achieved a high average test precision of 0.9811 ± 0.0084, recall of 0.7083 ± 0.0807, and mAP50 (mean average precision at 50% overlap) of 0.8185 ± 0.0562 across all presented classes. Despite these successes, the study also highlights the challenges posed by the weak annotations and class imbalances in the dataset, which impacted overall model performances. Conclusions: In conclusion, this study provides valuable insights into the application of deep learning for enhancing laparoscopic surgical precision in endometriosis treatment. The findings underscore the importance of robust dataset curation and advanced training strategies in developing reliable AI-assisted tools for surgical interventions. The latter could potentially improve the guidance of surgical interventions and prevent blind spots occurring in difficult to reach abdominal regions. Future work will focus on refining the dataset and exploring more sophisticated model architectures to further improve detection accuracy. Full article

(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

16 pages, 2299 KiB

Open AccessArticle

Three Neglected STARD Criteria Reduce the Uncertainty of the Liver Fibrosis Biomarker FibroTest-T2D in Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD)

by Thierry Poynard, Olivier Deckmyn, Raluca Pais, Judith Aron-Wisnewsky, Valentina Peta, Pierre Bedossa, Frederic Charlotte, Maharajah Ponnaiah, Jean-Michel Siksik, Laurent Genser, Karine Clement, Gilles Leanour and Dominique Valla

Diagnostics 2025, 15(10), 1253; https://doi.org/10.3390/diagnostics15101253 - 15 May 2025

Abstract

Background/Objectives: Bariatric surgery (BS), drugs approved for type-2-diabetes (T2D), obesity, and liver fibrosis (resmetirom) announce the widespread use of fibrosis tests in patients with metabolic liver disease (MASLD). An unmet need is to reduce the uncertainty of biomarkers for the diagnosis of the [...] Read more.

Background/Objectives: Bariatric surgery (BS), drugs approved for type-2-diabetes (T2D), obesity, and liver fibrosis (resmetirom) announce the widespread use of fibrosis tests in patients with metabolic liver disease (MASLD). An unmet need is to reduce the uncertainty of biomarkers for the diagnosis of the early stage of clinically significant fibrosis (eF). This can be achieved if three essential but neglected STARD methods (3M) are used, which have a more sensitive histological score than the standard comparator (five-tiers), the weighted area under the characteristic curve (wAUROC) instead of the binary AUROC, and biopsy length. We applied 3M to FibroTest-T2D to demonstrate this reduction of uncertainty and constructed proxies predicting eF in large populations. Methods: For uncertainty, seven subsets were analyzed, four included biopsies (n = 1903), and to assess eF incidence, three MASLD-populations (n = 299,098). FibroTest-T2D classification rates after BS and in outpatients-T2D (n = 402) were compared with and without 3M. In MASLD, trajectories of proxies and incidence against confounding factors used hazard ratios. Results: After BS (110 biopsies), reversal of eF was observed in 16/29 patients (84%) using seven-tier scores vs. 3/20 patients (47%) using five-tier scores (p = 0.005). When the biopsy length was above the median, FibroTest-T2D wAUROC was 0.90 (SD = 0.01), and the wAUROC was 0.88 (SD = 0.1) when the length was below the median (p < 0.001). For the first time, obesity was associated with eF before T2D (p < 0.001), and perimenopausal age with apoA1 and haptoglobin increases (p < 0.0001). Conclusions: Validations of circulating biomarkers need to assess their uncertainty. FibroTest-T2D predicts fibrosis regression after BS. Applying 3M and adjustments could avoid misinterpretations in MASLD surveillance. Full article

(This article belongs to the Special Issue Signatures Underlying Inflammation in the Pathogenesis and Evolution of Chronic Diseases)

► Show Figures

Figure 1

16 pages, 1744 KiB

Open AccessArticle

A Cone-Beam Computed Tomography-Based Assessment of Safe Zones for Orthodontic Mini-Implant Placement in the Lateral Maxilla: A Retrospective Morphometric Study

by Iva Jakovljevic, Pavle Milanovic, Milica Vasiljevic, Jovana Milanovic, Momir Z. Stevanovic, Nemanja Jovicic, Milos Stepovic, Vladimir Ristic, Dragica Selakovic, Gvozden Rosic and Aleksandra Arnaut

Diagnostics 2025, 15(10), 1252; https://doi.org/10.3390/diagnostics15101252 - 15 May 2025

Abstract

Background/Objectives: Orthodontic temporary anchorage devices (TADs) in the lateral maxillary region are useful tools for successful orthodontic treatment. Radiological anatomical knowledge is crucial for the successful placement of TADs. The use of cone-beam computed tomography (CBCT) is essential for evaluating the relationship between [...] Read more.

Background/Objectives: Orthodontic temporary anchorage devices (TADs) in the lateral maxillary region are useful tools for successful orthodontic treatment. Radiological anatomical knowledge is crucial for the successful placement of TADs. The use of cone-beam computed tomography (CBCT) is essential for evaluating the relationship between the ideal placement point (IPP) and dental structures, particularly in cases with anatomical limitations. Accordingly, this study aims to assess the anatomical conditions for orthodontic mini-implant (MI) insertion in the posterior maxilla using CBCT as the gold standard. Methods: This retrospective study included 62 patients (37.1% male, 62.9% female) aged 11 to 50 years. CBCT scans (sagittal and axial cross-sections) were used to evaluate interdental bone characteristics in different regions. The evaluated regions were defined as follows: Region 1 (canine and first premolar), Region 2 (first and second premolars), Region 3 (second premolar and first molar), and Region 4 (first and second molars). All parameters were assessed at three predefined levels: A, B, and C, located 4, 3, and 2 mm, respectively, from the alveolar crest. At the aforementioned levels, we performed measurements, such as the interdental width (IDW) in the mesiodistal direction and buccopalatal depth (BPD). The last observation was the relationship between the ideal TAD placement point (IPP) and dental structures, such as contact points (CPs) and cusp tips (C1-cusp of mesial tooth, C2-cusp of distal tooth, in each region). Results: A statistically significant positive correlation was found between the IDW and BPD at Levels A, B, and C in Region 1, while a negative correlation was observed between the IDW and BPD at Level C in Region 2′. The highest percentages of IDW exceeding 3 mm were found in Region 4 at Level A (67.7%), followed by Region 1′ and 2′, both at Level A. The mean interdental width measured at each level on the right and left sides was highest at Level A, exceeding 3 mm, and the width decreased with each successive level. The mean BPD measured at each level on the right and left sides was also highest at Level A. Conclusions: This methodological approach could assist in ensuring precise and efficient implant insertion. Furthermore, it can be concluded that the safe zone for buccal and interdental mini-implant placement is located 4 mm from the alveolar crest at Level A. Also, the CBCT analysis algorithm may serve as a valuable tool for clinicians in determining optimal TAD placement in different dental regions. Full article

(This article belongs to the Special Issue Diagnostic Approach and Innovations in the Different Dentistry Fields)

► Show Figures

Figure 1

12 pages, 3055 KiB

Open AccessArticle

Diagnostic Performance of Magnetic Resonance Sequences in Staging Lymph Node Involvement and Extranodal Extension in Head and Neck Squamous Cell Carcinoma

by Giovanni Lorusso, Nicola Maggialetti, Francesca Laugello, Annalisa Garofalo, Ilaria Villanova, Sara Greco, Chiara Morelli, Pasquale Pignataro, Nicola Maria Lucarelli and Amato Antonio Stabile Ianora

Diagnostics 2025, 15(10), 1251; https://doi.org/10.3390/diagnostics15101251 - 15 May 2025

Abstract

Objectives: This study aimed to evaluate the diagnostic performance of various MRI sequences in detecting nodal metastasis (N+) and extranodal extension (ENE+) in patients with head and neck squamous cell carcinoma (HNSCC). Methods: A retrospective analysis was conducted on 42 patients with [...] Read more.

Objectives: This study aimed to evaluate the diagnostic performance of various MRI sequences in detecting nodal metastasis (N+) and extranodal extension (ENE+) in patients with head and neck squamous cell carcinoma (HNSCC). Methods: A retrospective analysis was conducted on 42 patients with HNSCC who underwent preoperative MRI and subsequent surgical lymph node dissection between June 2021 and December 2023. Lymph node MRI features were evaluated on five different MRI sequences. For each rN+ case, the presence of radiological extranodal extension (rENE+) was assessed independently in every MRI sequence by analyzing three characteristics. ENE was deemed positive if at least one of three criteria considered was present. Results: All of the MRI sequences demonstrated slightly high accuracy (~76%) for detecting N+, with T1WI, STIR, and CE THRIVE showing comparable sensitivities (60–65%). The STIR sequence exhibited the highest sensitivity (75%) and nearly the highest accuracy (91%) for detecting ENE+. Capsular irregularity and necrosis showed high specificity across sequences, while the loss of fatty hilum and nodal size had lower performance. Conclusions: Tailoring MRI protocols to leverage the strengths of specific sequences can significantly improve the diagnostic accuracy, aiding in better patient management and treatment outcomes. Full article

(This article belongs to the Special Issue Advances in the Diagnosis and Management of Head and Neck Disease)

► Show Figures

Figure 1

25 pages, 2339 KiB

Open AccessArticle

Early Detection of Fetal Health Conditions Using Machine Learning for Classifying Imbalanced Cardiotocographic Data

by Irem Nazli, Ertugrul Korbeko, Seyma Dogru, Emin Kugu and Ozgur Koray Sahingoz

Diagnostics 2025, 15(10), 1250; https://doi.org/10.3390/diagnostics15101250 - 15 May 2025

Abstract

Background: Cardiotocography (CTG) is widely used in obstetrics to monitor fetal heart rate and uterine contractions. It helps detect early signs of fetal distress. However, manual interpretation of CTG can be time-consuming and may vary between clinicians. Recent advances in machine learning provide [...] Read more.

Background: Cardiotocography (CTG) is widely used in obstetrics to monitor fetal heart rate and uterine contractions. It helps detect early signs of fetal distress. However, manual interpretation of CTG can be time-consuming and may vary between clinicians. Recent advances in machine learning provide more efficient and consistent alternatives for analyzing CTG data. Objectives: This study aims to investigate the classification of fetal health using various machine learning models to facilitate early detection of fetal health conditions. Methods: This study utilized a tabular dataset comprising 2126 patient records and 21 features. To classify fetal health outcomes, various machine learning algorithms were employed, including CatBoost, Decision Tree, ExtraTrees, Gradient Boosting, KNN, LightGBM, Random Forest, SVM, ANN and DNN. To address class imbalance and enhance model performance, the Synthetic Minority Oversampling Technique (SMOTE) was employed. Results: Among the tested models, the LightGBM algorithm achieved the highest performance, boasting a classification accuracy of 90.73% and, more notably, a balanced accuracy of 91.34%. This superior balanced accuracy highlights LightGBM’s effectiveness in handling imbalanced datasets, outperforming other models in ensuring fair classification across all classes. Conclusions: This study highlights the potential of machine learning models as reliable tools for fetal health classification. The findings emphasize the transformative impact of such technologies on medical diagnostics. Additionally, the use of SMOTE effectively addressed dataset imbalance, further enhancing the reliability and applicability of the proposed approach. Full article

(This article belongs to the Special Issue AI-Driven Diagnostics: Transforming Healthcare from Data to Clinical Decisions)

► Show Figures

Figure 1

9 pages, 1029 KiB

Open AccessCase Report

Morphological and Immunohistochemical Support for the Origin of the Carcinoid Component in Strumal Carcinoids: A Case Report and Literature Review

by Yu Liu, Asra Feroze, Liz Yang and Ridin Balakrishnan

Diagnostics 2025, 15(10), 1249; https://doi.org/10.3390/diagnostics15101249 - 14 May 2025

Viewed by 117

Abstract

: Strumal carcinoid tumors of the ovary are rare neoplasms composed of an intimate mixture of thyroid and carcinoid tissues. Although various theories regarding their histogenesis have been proposed, evidence confirming the origin of the carcinoid component has been lacking. We report a [...] Read more.

: Strumal carcinoid tumors of the ovary are rare neoplasms composed of an intimate mixture of thyroid and carcinoid tissues. Although various theories regarding their histogenesis have been proposed, evidence confirming the origin of the carcinoid component has been lacking. We report a case of a 40-year-old female with an ovarian strumal carcinoid arising in the background of a mature cystic teratoma. Morphological and immunohistochemical findings support the hypothesis that the carcinoid component originates from the thyroid follicular epithelium, undergoing neuroendocrine differentiation. A single-cell growth pattern was also identified, expanding the known histological spectrum of strumal carcinoids. Our case provides additional immunohistochemical support for the histogenetic origin of strumal carcinoids, offering new insights into their pathogenesis. Recognizing these distinct patterns of staining and unusual morphology is critical for accurate diagnosis and differentiation from metastatic disease. Full article

(This article belongs to the Section Pathology and Molecular Diagnostics)

12 pages, 802 KiB

Open AccessArticle

Effect of Thyroxine Replacement Therapy on Serum Maresin 1 and NF-kB Levels in Patients with Hashimoto Thyroiditis

by Meltem Yardim, Levent Deniz, Mehmet Akif Saltabas and Nilufer Celik

Diagnostics 2025, 15(10), 1248; https://doi.org/10.3390/diagnostics15101248 - 14 May 2025

Viewed by 139

Abstract

Background/Objectives: This study aimed to investigate the effects of thyroxine replacement therapy (TRT) on serum Maresin 1 and nuclear factor kappa beta (NF-kB) levels in patients with Hashimoto’s thyroiditis (HT). Methods: A total of 90 patients were included in this study, 60 with [...] Read more.

Background/Objectives: This study aimed to investigate the effects of thyroxine replacement therapy (TRT) on serum Maresin 1 and nuclear factor kappa beta (NF-kB) levels in patients with Hashimoto’s thyroiditis (HT). Methods: A total of 90 patients were included in this study, 60 with HT and 30 without. Patients in the HT group were divided into two groups according to whether they received TRT. Group 1 included 30 patients who underwent TRT, and Group 2 comprised 30 patients who were newly diagnosed with HT, either euthyroid or hypothyroid. The analysis included serum levels of thyroid-stimulating hormone (TSH), free thyroxine (FT4), free triiodothyronine (FT3), thyroid peroxidase antibody (TPOAb), Maresin 1, and NF-kB. Results: The serum NF-kB level in the TRT group was significantly higher than that in the control and non-TRT groups. In the subgroup analysis of patients who did not receive TRT, the serum NF-kB level in euthyroid patients was significantly lower than that in hypothyroid patients. Maresin 1 levels in the control group were significantly higher than those in patients who did and did not receive TRT. The serum Maresin 1 level in the TRT group was significantly lower than that in the untreated group. Maresin 1 levels were higher in the euthyroid group than in the hypothyroid group. TPOAb levels were positively correlated with NF-kB and negatively correlated with Maresin 1. Conclusions: TRT maintains the euthyroid state in patients with HT, but may not contribute positively to the pro-anti-inflammatory balance in these patients. Full article

(This article belongs to the Section Clinical Laboratory Medicine)

► Show Figures

Figure 1

14 pages, 3925 KiB

Open AccessArticle

In Vitro Evaluation of Accuracy of CBCT-Derived Volumes in Maxillary Defects: Effects of kVp, Device, and Software

by Sema Murat, Kıvanç Kamburoğlu, Diego Vazquez, Leonardo Jorge Nart, Victoria Azcona, Lorena Elizabeth Benitez, Mohammed Awawdeh and Wael Aboelmaaty

Diagnostics 2025, 15(10), 1247; https://doi.org/10.3390/diagnostics15101247 - 14 May 2025

Viewed by 64

Abstract

Objectives: This study aimed to evaluate the accuracy of CBCT-based volumetric measurements of maxillary defects and to investigate the effects of different CBCT devices, kVp settings, and segmentation software on measurement accuracy. Methods: CBCT images from eight patients with maxillary defects were used [...] Read more.

Objectives: This study aimed to evaluate the accuracy of CBCT-based volumetric measurements of maxillary defects and to investigate the effects of different CBCT devices, kVp settings, and segmentation software on measurement accuracy. Methods: CBCT images from eight patients with maxillary defects were used to generate 3D-printed models for volumetric assessment. Two CBCT systems (Largev Smart and Planmeca Promax) were evaluated at three different kVp settings. Volume calculations were conducted using ITK-SNAP version 4.2.2 and 3D Doctor version 4.0 software, while micro-CT served as the gold standard (GS) for comparison. Statistical analysis included a three-way ANOVA to assess the effect of CBCT parameters and software on volumetric accuracy. Additionally, post-hoc Tukey HSD analysis was performed to identify specific differences between kVp groups, and Pearson correlation analysis was used to evaluate consistency with the GS. Significance level was set at p < 0.05. Results: Higher kVp settings significantly improved volumetric accuracy, with 100 kVp yielding the smallest deviations (−3.77%) from the GS. Tukey HSD analysis revealed significant differences between 60–80 kVp (p = 0.008), 60–100 kVp (p < 0.001), and 80–100 kVp (p = 0.041), confirming the influence of kVp on accuracy. No significant differences were observed between CBCT devices or software programs (p > 0.05). A strong positive correlation (r = 0.96) between CBCT-derived and micro-CT volumes confirmed CBCT’s reliability for volumetric assessments (p < 0.001). Conclusions: CBCT provides accurate volumetric measurements of maxillary defects, particularly at higher kVp settings. These findings support its clinical application for preoperative planning and postoperative evaluation, offering a cost-effective alternative to micro-CT. Full article

(This article belongs to the Section Medical Imaging and Theranostics)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Diagnostics, Volume 15, Issue 10 (May-2 2025) – 94 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI