Next Issue
Volume 15, May-1
Previous Issue
Volume 15, April-1
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
3.0
Journals
Diagnostics
Volume 15
Issue 8
share announcement

Diagnostics, Volume 15, Issue 8 (April-2 2025) – 108 articles

Cover Story (view full-size image): Breast cancer remains one of the leading causes of cancer-related mortality among women. Early detection through mammography is essential but often limited by variability in radiologist interpretation. This study compares machine learning (ML)-based radiomics and deep learning (DL) approaches for classifying breast lesions. Radiomic features were extracted from 1219 mammograms in the CBIS-DDSM dataset using matRadiomics, while an EfficientNetB6-based DL model was also evaluated. The ML radiomic model achieved area-under-the-curve values of 68.3% for microcalcifications and 61.5% for masses. In contrast, the DL model reached 81.5% and 76.2%, respectively, demonstrating its superior performance and greater potential for accurate breast cancer diagnosis. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
6 pages, 623 KiB  
Editorial
Machine Learning and Deep Learning for Healthcare Data Processing and Analyzing: Towards Data-Driven Decision-Making and Precise Medicine
by Haipeng Liu and Rajesh Kumar Tripathy
Diagnostics 2025, 15(8), 1051; https://doi.org/10.3390/diagnostics15081051 - 21 Apr 2025
Abstract
Artificial intelligence (AI) is reshaping the landscape of healthcare data [...] Full article
(This article belongs to the Special Issue Machine Learning and Deep Learning for Healthcare Data Processing and Analyzing)
►▼ Show Figures

Figure 1

10 pages, 19987 KiB  
Article
First Report of Ethylenediaminetetraacetic Acid-Dependent Pseudo-Thrombocytopenia in Chile: Prevalence and Laboratory Insights
by Mario Balcázar-Villarroel, Florencia Carmine, Francisco Torrens, Katherine Birditt and Cristian Sandoval
Diagnostics 2025, 15(8), 1050; https://doi.org/10.3390/diagnostics15081050 - 21 Apr 2025
Abstract
Background: Ethylenediaminetetraacetic acid-dependent pseudo thrombocytopenia (EDTA-PCTP) is defined as a false in vitro decrease in the platelet count performed in the EDTA tube due to the spontaneous formation of platelet aggregates that prevent a correct count in hematological auto analyzers. The frequency of [...] Read more.
Background: Ethylenediaminetetraacetic acid-dependent pseudo thrombocytopenia (EDTA-PCTP) is defined as a false in vitro decrease in the platelet count performed in the EDTA tube due to the spontaneous formation of platelet aggregates that prevent a correct count in hematological auto analyzers. The frequency of EDTA-PCTP varies depending on the population studied, ranging from 0.01% to 30.0%. In Chile, although the diagnosis of this condition is performed in clinical laboratories, only a few isolated reports have been described. Objectives: To determine the prevalence of EDTA-PCTP in a cohort of patients who attended an outpatient clinical laboratory in southern Chile over a period of almost 4 years. Methods: A retrospective analysis was conducted using the Laboratory Information System from January 2021 to November 2024 to identify patients with suspected and confirmed cases of EDTA-PCTP. Results: The prevalence rate observed was 0.044% (12 out of 27,480). Additionally, we established that platelet count measurement from the citrate tube at 2–5 h post-sampling was comparable to the platelet count from the EDTA/K2 tube at time 0 (p > 0.05) in these patients. Conclusions: We conclude that a relatively low prevalence of EDTA-PTCP was identified in a population of patients attending an outpatient laboratory in Chile, marking the first report of its kind in our country. Future studies may validate our findings to enhance understanding of EDTA-PTCP, thereby preventing incorrect diagnoses and treatments. Full article
(This article belongs to the Section Clinical Laboratory Medicine)
►▼ Show Figures

Figure 1

16 pages, 5107 KiB  
Article
Quantitative MRI Assessment of Supraspinatus Tendon Remodeling Following a Single Platelet-Rich Plasma Injection Using T2 Mapping and Relaxation Time Profiling
by Karlo Pintarić, Andrej Vovk, Vladka Salapura, Žiga Snoj and Jernej Vidmar
Diagnostics 2025, 15(8), 1049; https://doi.org/10.3390/diagnostics15081049 - 21 Apr 2025
Abstract
Background: Quantitative magnetic resonance imaging (MRI) techniques such as T2 mapping may detect early tendon changes following biologic therapies. This study aimed to assess the structural remodeling of the supraspinatus tendon using mean T2 values and T2 distribution profiles after [...] Read more.
Background: Quantitative magnetic resonance imaging (MRI) techniques such as T2 mapping may detect early tendon changes following biologic therapies. This study aimed to assess the structural remodeling of the supraspinatus tendon using mean T2 values and T2 distribution profiles after an ultrasound (US)-guided single platelet-rich plasma (PRP) injection. Methods: Twenty-six patients with symptomatic supraspinatus tendinopathy were divided into tendinosis (n = 9) and partial tear (n = 13) groups. T2 mapping and clinical evaluations (shoulder pain and disability index questionnaire (SPADI), Constant-Murley score) were conducted at baseline and 6 months post-PRP. Mean T2 values were measured in three tendon segments (lateral, middle, and medial), and T2 profiles were compared to asymptomatic controls. Results: Clinical outcomes showed significant improvement in both the tendinosis and partial tear groups at the 6-month follow-up. Although no significant changes were observed in the mean T2 relaxation times across tendon segments following PRP treatment, T2 distribution profiling revealed statistically significant alterations in both groups. In the tendinosis group, post-treatment T2 profiles approached those of the asymptomatic controls, suggesting structural remodeling consistent with tendon healing. Conclusions: T2 mapping is an effective tool for detecting tendon remodeling following PRP therapy. Structural improvements indicative of tissue healing were observed in cases of tendinosis, but not in partial tendon tears. These findings support the use of T2 mapping—particularly the T2 distribution profiling—as a quantitative biomarker for assessing treatment response to PRP. Full article
(This article belongs to the Special Issue Diagnostic Imaging in Musculoskeletal Diseases)
►▼ Show Figures

Figure 1

13 pages, 1382 KiB  
Article
The Prognostic and Predictive Roles of Ataxia–Telangiectasia Mutated (ATM) Expression in Patients with Metastatic Non-Small-Cell Lung Cancer Receiving Pembrolizumab Monotherapy Alone or in Combination with Chemotherapy
by Jamshid Hamdard, Harun Muğlu, Ahmet Bilici, Elif Kuzucular, Özgür Açıkgöz, Ömer Fatih Ölmez, Oktay Olmuşçelik and Özcan Yıldız
Diagnostics 2025, 15(8), 1048; https://doi.org/10.3390/diagnostics15081048 - 21 Apr 2025
Abstract
Background/Objectives: This study investigated the prognostic and predictive significance of Ataxia–Telangiectasia Mutated (ATM) expression in patients with metastatic non-small-cell lung cancer (NSCLC) who were treated with pembrolizumab. Methods: A retrospective analysis was conducted on 49 patients with metastatic NSCLC who received first-line pembrolizumab, [...] Read more.
Background/Objectives: This study investigated the prognostic and predictive significance of Ataxia–Telangiectasia Mutated (ATM) expression in patients with metastatic non-small-cell lung cancer (NSCLC) who were treated with pembrolizumab. Methods: A retrospective analysis was conducted on 49 patients with metastatic NSCLC who received first-line pembrolizumab, either as a single agent or in combination with chemotherapy. ATM expression in archival pathology specimens was assessed using immunohistochemistry, where nuclear staining was considered to be positive. ATM expression was categorized into low- and high-expression groups based on staining intensity and the percentage of positive cells. Subsequently, the prognostic and predictive value of ATM expression was evaluated. Results: In terms of demographics, the mean age was 62.7 ± 9.5, most patients (91.8%) were male, and the majority (75.5%) had adenocarcinoma. The objective response rate (ORR) was 69.4%, and ATM expression was high in 75.5% of patients. Patients with low ATM expression had significantly longer progression-free survival (PFS) compared to those with high expression (51 vs. 5.7 months, p = 0.004). In multivariate analysis, ATM expression was the only independent prognostic factor for PFS, showing that patients with high ATM expression had a shorter overall survival (OS) compared to those with low expression (51 vs. 8.9 months, p = 0.013), which was statistically significant (HR 2.41, p = 0.034). Logistic regression analysis showed that ATM expression, as well as the presence of bone metastasis and the absence of liver metastasis, was significantly associated with a response to treatment (p = 0.006; OR: 0.06; 95% CI: 0.008–0.45). Conclusions: The findings of this study concerning ATM expression as a biomarker should be interpreted cautiously due to inherent limitations, including its retrospective design, the semi-quantitative nature of immunohistochemistry for ATM assessment, the small sample size with uneven clinical characteristics, and the relatively short follow-up period, which collectively impact generalizability. Despite these limitations, lower ATM expression was associated with better prognosis and pembrolizumab treatment response, suggesting that it may be a valuable biomarker for predicting these factors. Full article
(This article belongs to the Special Issue Diagnosis and Management of Lung Cancer)
►▼ Show Figures

Figure 1

11 pages, 667 KiB  
Article
Performance of the 2021 Estimated Glomerular Filtration Rate CKD-EPI Refit and the European Kidney Function Consortium (EKFC) Formulas
by Evelyn O. Ilori, Casey R. Cai, Fatou Sahor, Brianna Wilson, Tanooha Veeramachaneni, Samir M. Parikh and Ibrahim A. Hashim
Diagnostics 2025, 15(8), 1047; https://doi.org/10.3390/diagnostics15081047 - 21 Apr 2025
Abstract
Background: The glomerular filtration rate (GFR) is a universal clinical measure central to assessing kidney function and to the management of kidney disorders. Several formulas for the estimation of GFR are in use. The European Kidney Function Consortium (EKFC) formula has been [...] Read more.
Background: The glomerular filtration rate (GFR) is a universal clinical measure central to assessing kidney function and to the management of kidney disorders. Several formulas for the estimation of GFR are in use. The European Kidney Function Consortium (EKFC) formula has been reported to more accurately estimate the GFR as compared to the Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) formula and its recent version (REFIT equation) in European and African populations. However, validation of the EKFC equation in diverse U.S. populations, especially the Black subpopulation, is needed. Methods: Data from the electronic medical records of 75,442 individuals presenting to a large safety net county hospital with measurements of serum creatinine and/or iohexol clearance studies were used to calculate the estimated GFR (eGFR) and to determine CKD stage using the various reported eGFR formulas. The correlation between eGFR and measured GFR was determined for each equation. Results: The median eGFR for Black participants using the CKD-EPI, REFIT, and EKFC formulas was 130.6 mL/min/1.73 m2, 82.0 mL/min/1.73 m2, and 80.6 mL/min/1.73 m2 (p < 0.001), respectively. For White participants, the median eGFR using the CKD-EPI, REFIT, and EKFC formulas was 145.3 mL/min/1.73 m2, 105.6 mL/min/1.73 m2, and 99.2 mL/min/1.73 m2, respectively (p < 0.001). The REFIT equation underestimates the mGFR in Black individuals at eGFR < 80 mL/min per 1.73 m2 and in White individuals at eGFR > 20 mL/min per 1.73 m2. In comparison, the EKFC equation underestimates the mGFR at eGFR > 20 mL/min per 1.73 m2 in both Black and White individuals. The REFIT equation had the least absolute median bias as compared to EKFC and CKD-EPI in both Black and White participants (p < 0.0001). The P30 of the REFIT and EKFC equations was not statistically different for either Black or White participants (p = 0.16, p = 0.37). Conclusions: Although the accuracies (P30) of the EKFC and REFIT equations are not statistically significant (p = 0.16 and 0.37, Black and White individuals, respectively), adopting the EKFC formula in Americans requires the evaluation of each subpopulation. Both the EKFC and REFIT formulas underestimate the mGFR at a lower eGFR, which may have a direct impact on CKD classification for Black and White patients, with potentially significant implications for clinical management. Full article
(This article belongs to the Section Clinical Diagnosis and Prognosis)
►▼ Show Figures

Figure 1

10 pages, 2471 KiB  
Article
Early-Branched Short Renal Arteries Are False Multiple Renal Arteries
by Adelina Maria Jianu, Nawwaf Sebastian Damen, Monica Adriana Vaida, Laura Octavia Grigoriță, Marius Ioan Rusu and Mugurel Constantin Rusu
Diagnostics 2025, 15(8), 1046; https://doi.org/10.3390/diagnostics15081046 - 20 Apr 2025
Abstract
Background/Objectives: During retroperitoneal surgery, awareness of the anatomic variants of renal arteries (RAs) is essential. We aimed to determine the prevalence of early-branched (short) Ras, the bilateral morphologies of RAs in such cases, and to check for significant correlations regarding gender or [...] Read more.
Background/Objectives: During retroperitoneal surgery, awareness of the anatomic variants of renal arteries (RAs) is essential. We aimed to determine the prevalence of early-branched (short) Ras, the bilateral morphologies of RAs in such cases, and to check for significant correlations regarding gender or side. Short RAs may be regarded as false multiple RAs and should be distinguished from true RAs. Methods: For the study, 185 archived angioCT files were randomly selected and evaluated for <1.5 cm RAs (106 male and 79 female cases). Simple regression and multiple regression tests, alongside ANOVA, were used for the statistical analysis. Results: Short RAs were found in 15/185 cases, 12 males and 3 females (8.1%), with short RAs found on the right side (2.7%), left side (4.86), and bilaterally (one case, 0.54%). The mean length was 9.46 mm. Short RAs were bifurcated in most cases and trifurcated in one case. In four other cases, peculiar RA anatomical patterns were found. They included a right RA origin of the right inferior phrenic artery, variable polar RAs, malrotated and ptotic kidneys, anteriorly dehiscent renal sinuses, and multiple RAs, including five right RAs, with the three inferior ones having precaval courses. Short RAs were not significantly related to gender (p > 0.05). There was a significant correlation between gender and right short RAs (p < 0.05). Conclusions: During renal transplant surgery, distinguishing between true and false multiple RAs is essential. While true multiple RAs may cause surgical discomfort, short RAs may be used as single RAs, but they should be carefully documented before donor nephrectomies. Full article
(This article belongs to the Special Issue Clinical Impacts and Value of Anatomy)
►▼ Show Figures

Figure 1

3 pages, 140 KiB  
Editorial
Advances in Cerebrovascular Imaging and Interventions
by Seyedmehdi Payabvash
Diagnostics 2025, 15(8), 1045; https://doi.org/10.3390/diagnostics15081045 - 20 Apr 2025
Viewed by 38
Abstract
Since the 1990s, the global burden of cerebrovascular disease – particularly stroke – has significantly increased [...] Full article
(This article belongs to the Special Issue Advances in Cerebrovascular Imaging and Interventions)
13 pages, 255 KiB  
Review
Impact of Multiplex PCR on Diagnosis of Bacterial and Fungal Infections and Choice of Appropriate Antimicrobial Therapy
by Francesca Serapide, Rita Pallone, Angela Quirino, Nadia Marascio, Giorgio Settimo Barreca, Chiara Davoli, Rosaria Lionello, Giovanni Matera and Alessandro Russo
Diagnostics 2025, 15(8), 1044; https://doi.org/10.3390/diagnostics15081044 - 20 Apr 2025
Viewed by 72
Abstract
Multiplex Polymerase Chain Reaction (PCR) has significantly impacted the field of infectious disease diagnostics, offering rapid and precise identification of bacterial and fungal pathogens. Unlike traditional culture methods, which may take days to yield results, multiplex PCR provides diagnostic insights within hours, enabling [...] Read more.
Multiplex Polymerase Chain Reaction (PCR) has significantly impacted the field of infectious disease diagnostics, offering rapid and precise identification of bacterial and fungal pathogens. Unlike traditional culture methods, which may take days to yield results, multiplex PCR provides diagnostic insights within hours, enabling faster, targeted antimicrobial therapy and reducing the delay in treating critical infections like sepsis. The technique’s high sensitivity and broad pathogen coverage make it ideal for both single and polymicrobial infections, improving outcomes across respiratory, bloodstream, and bacterial/fungal infections. However, multiplex PCR is not without challenges; initial high costs and the need for specialized training can limit its adoption, especially in low-resource settings. This review discusses the clinical advantages and limitations of multiplex PCR, highlighting its influence on diagnostic accuracy, antimicrobial stewardship, and the global fight against antimicrobial resistance (AMR). Furthermore, recent innovations in multiplex PCR, such as digital PCR and portable devices, are explored as potential tools for expanding access to rapid diagnostics worldwide. Full article
(This article belongs to the Special Issue Editorial Board Members' Collection Series: Molecular Diagnostics of Infectious Diseases)
15 pages, 3017 KiB  
Article
Assessment of Spectral Computed Tomography Image Quality and Detection of Lesions in the Liver Based on Image Reconstruction Algorithms and Virtual Tube Voltage
by Areej Hamami, Mohammad Aljamal, Nora Almuqbil, Mohammad Al-Harbi and Zuhal Y. Hamd
Diagnostics 2025, 15(8), 1043; https://doi.org/10.3390/diagnostics15081043 - 19 Apr 2025
Viewed by 107
Abstract
Background: Spectral detector computed tomography (SDCT) has demonstrated superior diagnostic performance and image quality in liver disease assessment compared with traditional CT. Selecting the right reconstruction algorithm and tube voltage is essential to avoid increased noise and diagnostic errors. Objectives: This [...] Read more.
Background: Spectral detector computed tomography (SDCT) has demonstrated superior diagnostic performance and image quality in liver disease assessment compared with traditional CT. Selecting the right reconstruction algorithm and tube voltage is essential to avoid increased noise and diagnostic errors. Objectives: This study evaluated improvements in image quality achieved using various virtual tube voltages and reconstruction algorithms for diagnosing common liver diseases with spectral CT. Methods: This retrospective study involved forty-seven patients who underwent spectral CT scans for liver conditions, including fatty liver, hemangiomas, and metastatic lesions. The assessment utilized signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), with images reconstructed using various algorithms (IMR, iDose) at different levels and virtual tube voltages. Three experienced radiologists analyzed the reconstructed images to identify the best reconstruction methods and tube voltage combinations for diagnosing these liver pathologies. Results: The signal-to-noise ratio (SNR) was highest for spectral CT images using the IMR3 algorithm in metastatic, hemangioma, and fatty liver cases. A strong positive correlation was found between IMR3 at 120 keV and 70 keV (p-value = 0.000). In contrast, iDOSE2 at 120 keV and 70 keV showed a low correlation of 0.291 (p-value = 0.045). Evaluators noted that IMR1 at 70 keV provided the best visibility for liver lesions (mean = 3.58), while IMR3 at 120 keV had the lowest image quality (mean = 2.65). Conclusions: Improvements in image quality were noted with SDCT, especially in SNR values for liver tissues at low radiation doses and a specific IMR level. The IMR1 algorithm reduced noise, enhancing the visibility of liver lesions for better diagnosis. Full article
(This article belongs to the Special Issue Computed Tomography Imaging in Medical Diagnosis, 2nd Edition)
►▼ Show Figures

Figure 1

12 pages, 3393 KiB  
Article
Immunoexpressions of PD-L1 and EZH2 in Endometrial Carcinoma: Associations with Clinicopathological Parameters
by Badrul Iskandar Abdul Wahab, Shamsul Azhar Shah, Roslina Mohd Arshad, Nurwardah Alfian, Geok Chin Tan and Yin Ping Wong
Diagnostics 2025, 15(8), 1042; https://doi.org/10.3390/diagnostics15081042 - 19 Apr 2025
Viewed by 108
Abstract
Background: This study investigated PD-L1 and EZH2 immunoexpressions in endometrial carcinomas (ECs) and correlated their associations with clinicopathological parameters and five-year survival outcomes. Methods: A cross-sectional, retrospective study was conducted on all ECs diagnosed between January 2014 and December 2018. Immunohistochemical staining for [...] Read more.
Background: This study investigated PD-L1 and EZH2 immunoexpressions in endometrial carcinomas (ECs) and correlated their associations with clinicopathological parameters and five-year survival outcomes. Methods: A cross-sectional, retrospective study was conducted on all ECs diagnosed between January 2014 and December 2018. Immunohistochemical staining for PD-L1 (clone 22C3) and EZH2 was performed on tumour samples, and their expression levels were assessed. Results: Among the 104 EC cases included, 19.2% (n = 20) overexpressed PD-L1, while 8.7% (n = 9) overexpressed EZH2. Most (n = 19/20, 95.0%) PD-L1-expressing tumour cells showed EZH2 immunonegativity. Likewise, most (n = 8/9, 88.9%) EZH2-expressing ECs were PD-L1-negative. Increased PD-L1 and EZH2 expressions in ECs were seen more frequently in women more than 60 years of age (p = 0.013 and p = 0.039). EZH2 overexpression was associated with higher tumour grade (p = 0.009) and more aggressive histological subtypes (p = 0.013), while PD-L1 expression was not significantly associated with tumour grade, tumour stage, histological subtypes, and lymph node status (p > 0.05). Kaplan–Meier survival analysis revealed that PD-L1-positive ECs had a significantly better five-year overall survival (OS) rate compared to PD-L1-negative ECs (p = 0.034). Conversely, EZH2 overexpression did not correlate with survival outcomes (p > 0.05). Notably, the combination of PD-L1 and EZH2 expression patterns on ECs (PD-L1-/EZH2+) portends the worst OS compared to other combined PD-L1/EZH2 expression patterns (p = 0.05). Conclusions: PD-L1 immunoexpression was associated with better survival outcomes in ECs, while overexpression of EZH2 was associated with higher tumour grade and aggressive histological subtypes, suggesting their potential utility as prognostic biomarkers in ECs. Full article
(This article belongs to the Section Pathology and Molecular Diagnostics)
►▼ Show Figures

Figure 1

26 pages, 4277 KiB  
Article
Fractal-Based Architectures with Skip Connections and Attention Mechanism for Improved Segmentation of MS Lesions in Cervical Spinal Cord
by Rukiye Polattimur, Mehmet Süleyman Yıldırım and Emre Dandıl
Diagnostics 2025, 15(8), 1041; https://doi.org/10.3390/diagnostics15081041 - 19 Apr 2025
Viewed by 120
Abstract
Background/Objectives: Multiple sclerosis (MS) is an autoimmune disease that damages the myelin sheath of the central nervous system, which includes the brain and spinal cord. Although MS lesions in the brain are more frequently investigated, MS lesions in the cervical spinal cord [...] Read more.
Background/Objectives: Multiple sclerosis (MS) is an autoimmune disease that damages the myelin sheath of the central nervous system, which includes the brain and spinal cord. Although MS lesions in the brain are more frequently investigated, MS lesions in the cervical spinal cord (CSC) can be much more specific for the diagnosis of the disease. Furthermore, as lesion burden in the CSC is directly related to disease progression, the presence of lesions in the CSC may help to differentiate MS from other neurological diseases. Methods: In this study, two novel deep learning models based on fractal architectures are proposed for the automatic detection and segmentation of MS lesions in the CSC by improving the convolutional and connection structures used in the layers of the U-Net architecture. In our previous study, we introduced the FractalSpiNet architecture by incorporating fractal convolutional block structures into the U-Net framework to develop a deeper network for segmenting MS lesions in the CPC. In this study, to improve the detection of smaller structures and finer details in the images, an attention mechanism is integrated into the FractalSpiNet architecture, resulting in the Att-FractalSpiNet model. In addition, in the second hybrid model, a fractal convolutional block is incorporated into the skip connection structure of the U-Net architecture, resulting in the development of the Con-FractalU-Net model. Results: Experimental studies were conducted using U-Net, FractalSpiNet, Con-FractalU-Net, and Att-FractalSpiNet architectures to detect the CSC region and the MS lesions within its boundaries. In segmenting the CSC region, the proposed Con-FractalU-Net architecture achieved the highest Dice Similarity Coefficient (DSC) score of 98.89%. Similarly, in detecting MS lesions within the CSC region, the Con-FractalU-Net model again achieved the best performance with a DSC score of 91.48%. Conclusions: For segmentation of the CSC region and detection of MS lesions, the proposed fractal-based Con-FractalU-Net and Att-FractalSpiNet architectures achieved higher scores than the baseline U-Net architecture, particularly in segmenting small and complex structures. Full article
(This article belongs to the Special Issue Deep Learning Techniques for Medical Image Analysis)
►▼ Show Figures

Figure 1

15 pages, 1313 KiB  
Article
The Effect of Neutrophil-to-Lymphocyte Ratio on Prognosis in Malignant Ovarian Germ Cell Tumors
by Yagmur Arslan, Ipek Betul Ozcivit Erkan, Atacem Mert Aytekin, Cansu Turker Saricoban, Abdullah Serdar Acikgoz, Tugan Bese and Oguzhan Kuru
Diagnostics 2025, 15(8), 1040; https://doi.org/10.3390/diagnostics15081040 - 19 Apr 2025
Viewed by 164
Abstract
Background/Objectives: Ovarian germ cell tumors are rare, and determining prognostic factors is crucial for individualizing management strategies. We aimed to determine an optimal neutrophil-to-lymphocyte ratio (NLR) cut-off value for predicting survival outcomes in malignant ovarian germ cell tumors, and to evaluate the [...] Read more.
Background/Objectives: Ovarian germ cell tumors are rare, and determining prognostic factors is crucial for individualizing management strategies. We aimed to determine an optimal neutrophil-to-lymphocyte ratio (NLR) cut-off value for predicting survival outcomes in malignant ovarian germ cell tumors, and to evaluate the prognostic significance of NLR in these tumors. Methods: This retrospective cohort study included women diagnosed with malignant ovarian germ cell tumors who underwent surgery at Istanbul University-Cerrahpasa between 2000 and 2024. Patients with benign tumors; incomplete follow-up; inaccessible data; history of hematological or rheumatic diseases; inflammatory conditions such as diabetes mellitus, asthma, or renal failure; as well as those with acute/chronic infections or sepsis were excluded. Data collected included demographic characteristics, surgical and pathological findings, chemotherapy details, disease progression, survival outcomes, and laboratory values at preoperative, postoperative, and post-chemotherapy time points. The NLR was calculated and compared for overall survival and disease-free survival. Results: The study included 44 patients with a pathologically confirmed diagnosis of malignant ovarian germ cell tumors. The NLR cut-off value for survival prediction was determined as 3.69 using the ROC curve. The effect of preoperative NLR on overall survival was found to be significant. The median overall survival was significantly lower in the group with NLR ≥ 3.69 (153.2 months) compared to the group with NLR < 3.69 (234 months) (p = 0.010). However, there was no statistically significant difference in median disease-free survival between the NLR ≥ 3.69 group (159.3 months) and the NLR < 3.69 group (215 months). Conclusions: The preoperative NLR was found to have a significant impact on overall survival but not on disease-free survival. A cut-off value of 3.69 can be used to assess short survival time. Full article
(This article belongs to the Section Clinical Diagnosis and Prognosis)
►▼ Show Figures

Figure 1

10 pages, 1948 KiB  
Article
The Use of Positron-Emission Tomography–Magnetic Resonance Imaging to Improve the Local Staging of Disease in Myxofibrosarcoma: A Feasibility Study
by Corey D. Chan, Marcus J. Brookes, Tamir Ali, Elizabeth Howell, Petra Dildey, Michael Firbank, Rachel Pearson, Philip Sloan, Simon Lowes, Raj Sinha, John Tuckett, Maniram Ragbir, Thomas Beckingsale, Geoff Hide, Craig Gerrand, Kenneth S. Rankin and George S. Petrides
Diagnostics 2025, 15(8), 1039; https://doi.org/10.3390/diagnostics15081039 - 19 Apr 2025
Viewed by 151
Abstract
Background/Objectives: Myxofibrosarcomas (MFSs) are aggressive soft-tissue sarcomas (STSs) that often arise in the upper and lower limbs. MFSs are a highly infiltrative sarcoma subtype with a high positive margin rate and poor clinical outcomes. Their management involves multidisciplinary team (MDT) input, with [...] Read more.
Background/Objectives: Myxofibrosarcomas (MFSs) are aggressive soft-tissue sarcomas (STSs) that often arise in the upper and lower limbs. MFSs are a highly infiltrative sarcoma subtype with a high positive margin rate and poor clinical outcomes. Their management involves multidisciplinary team (MDT) input, with the mainstay of treatment being a wide surgical resection to remove the whole tumour, but this can be challenging due to the infiltrative nature of MFSs through fascial planes. Appropriate pre-operative imaging is therefore essential for surgical planning. Currently, MRI imaging is the modality of choice to assess the soft-tissue extent of MFSs; however, it does not always reliably predict tumour extent, especially when an MRI shows high-signal curvilinear projections, known as “tails”, which often represent tumour extension and increase the risk of positive margins and local recurrence. Methods: This feasibility study therefore aimed to investigate whether the addition of an FDG PET-MRI and DWI MRI is superior for the local staging of MFSs compared to a standard MRI, and to assess its practicality for clinical use. Results: Of the eight patients recruited, six completed the required scans, proceeded to surgery, and were included in the data analyses. Five of the six patients had close (<2 mm) or positive margins requiring re-excision. Conclusions: Our results show that combining an FDG-PET and DWI MRI may offer a more accurate local staging of MFSs than a conventional MRI; however, a larger prospective trial is needed to further investigate this pilot data. Nevertheless, this novel feasibly study demonstrates the potential use of PET-MRI and DWI for improving pre-operative planning prior to the surgical resection of MFSs. Full article
(This article belongs to the Special Issue Diagnostic Imaging in Bone and Soft-Tissue Sarcomas: Practice, Education, and Innovation—2nd Edition)
►▼ Show Figures

Figure 1

13 pages, 2177 KiB  
Article
Complete Blood Cell Count Parameters Predict Mortality in Patients with Hypersensitivity Pneumonitis
by Matthaios Katsaras, Vasilina Sotiropoulou, Effrosyni Manali, Evangelia Fouka, Despoina Papakosta, Elisabeth Bendstrup, Lykourgos Kolilekas, Ioannis Tomos, Vasilios Tzilas, Paschalis Ntolios, Paschalis Steiropoulos, Ilias Papanikolaou, Athena Gogali, Konstantinos Kostikas, Panagiota Tsiri, Ourania Papaioannou, Elli Malakounidou, Eva Theohari, Ioannis Christopoulos, Fotios Sampsonas, Spyridon A. Papiris, Nikoletta Rovina, Demosthenes Bouros and Argyrios Tzouvelekisadd Show full author list remove Hide full author list
Diagnostics 2025, 15(8), 1038; https://doi.org/10.3390/diagnostics15081038 - 18 Apr 2025
Viewed by 106
Abstract
Background: Hypersensitivity pneumonitis (HP) represents a chronic lung disease with an unpredictable clinical course. There is a pressing need for clinically applicable prognostic biomarkers in patients with HP. Methods: This was an observational, retrospective study. We investigated the prognostic potential of complete blood [...] Read more.
Background: Hypersensitivity pneumonitis (HP) represents a chronic lung disease with an unpredictable clinical course. There is a pressing need for clinically applicable prognostic biomarkers in patients with HP. Methods: This was an observational, retrospective study. We investigated the prognostic potential of complete blood count parameters in treatment-naïve patients diagnosed with HP between 15 December 2010 and 1 October 2023. Receiver operating characteristic (ROC) curve analysis identified the optimal cut-off thresholds for each parameter in terms of mortality prediction. Results: We included 129 patients diagnosed with HP [median age: 68.0 years (95% CI: 65.0 to 69.0), fibrotic HP: n = 85, 65.9%]. Patients with HP and an eosinophil count > 160 cells/μL [ROC curve, area under curve (AUC): 0.61] exhibited increased mortality risk compared to patients with HP and an eosinophil count ≤ 160 cells/μL [Kaplan–Meier, HR: 2.95 (95% CI: 1.36 to 6.42), p = 0.006]. Patients with HP and a monocyte count > 350 cells/μL (ROC curve, AUC: 0.52) had worse survival compared to patients with HP and a monocyte count lower than this threshold [Kaplan–Meier, HR: 2.48 (95% CI: 1.03 to 5.09), p = 0.04]. Patients with HP and an eosinophil–lymphocyte ratio (ELR) > 0.09 (ROC curve, AUC: 0.64) had a higher risk of mortality compared to patients with HP and ELR ≤ 0.09 [Kaplan–Meier, HR: 2.75 (95% CI: 1.3 to 5.78), p = 0.008]. Conclusions: This study demonstrated that eosinophil count, monocyte count, and ELR could be prognostic biomarkers in patients with HP. Further studies aiming to validate the prognostic potential of complete blood count parameters in patients with HP are greatly anticipated. Full article
(This article belongs to the Special Issue Respiratory Diseases: Diagnosis and Management)
►▼ Show Figures

Figure 1

69 pages, 1033 KiB  
Review
Biosensors, Artificial Intelligence Biosensors, False Results and Novel Future Perspectives
by Georgios Goumas, Efthymia N. Vlachothanasi, Evangelos C. Fradelos and Dimitra S. Mouliou
Diagnostics 2025, 15(8), 1037; https://doi.org/10.3390/diagnostics15081037 - 18 Apr 2025
Viewed by 185
Abstract
Medical biosensors have set the basis of medical diagnostics, and Artificial Intelligence (AI) has boosted diagnostics to a great extent. However, false results are evident in every method, so it is crucial to identify the reasons behind a possible false result in order [...] Read more.
Medical biosensors have set the basis of medical diagnostics, and Artificial Intelligence (AI) has boosted diagnostics to a great extent. However, false results are evident in every method, so it is crucial to identify the reasons behind a possible false result in order to control its occurrence. This is the first critical state-of-the-art review article to discuss all the commonly used biosensor types and the reasons that can give rise to potential false results. Furthermore, AI is discussed in parallel with biosensors and their misdiagnoses, and again some reasons for possible false results are discussed. Finally, an expert opinion with further future perspectives is presented based on general expert insights, in order for some false diagnostic results of biosensors and AI biosensors to be surpassed. Full article
(This article belongs to the Special Issue Wearable Sensors for Health Monitoring and Diagnostics)
►▼ Show Figures

Figure 1

3 pages, 931 KiB  
Interesting Images
V Aortic Arch Remnant
by Corrado Tagliati, Marco Fogante, Stefania Lamja, Cecilia Cerimele, Alessia Quaranta, Alfonso Alberto Matarrese, Davide Battista, Antonio Bernardini, Giulio Argalia, Iacopo Carbone, Ernesto Di Cesare, Nicolò Schicchi and Giuseppe Lanni
Diagnostics 2025, 15(8), 1036; https://doi.org/10.3390/diagnostics15081036 - 18 Apr 2025
Viewed by 79
Abstract
Here, we describe the case of an asymptomatic 70-year-old male patient who performed a contrast-enhanced computed tomography examination for prostate cancer staging, and an exceptional finding was reported. Specifically, a probable and never before reported minimal V aortic arch remnant with a thin [...] Read more.
Here, we describe the case of an asymptomatic 70-year-old male patient who performed a contrast-enhanced computed tomography examination for prostate cancer staging, and an exceptional finding was reported. Specifically, a probable and never before reported minimal V aortic arch remnant with a thin intima–media band that joins together the anterior and posterior aortic walls. Full article
(This article belongs to the Section Medical Imaging and Theranostics)
►▼ Show Figures

Figure 1

15 pages, 285 KiB  
Review
Neurophysiological Examination for the Diagnosis of Orofacial Pain and Temporomandibular Disorders: A Literature Review
by Loredana Raciti, Martina Ferrillo, Antonio Ammendolia, Gianfranco Raciti, Claudio Curci, Dario Calafiore, Maria Pia Onesta, Rocco Salvatore Calabrò, Umile Giuseppe Longo and Alessandro de Sire
Diagnostics 2025, 15(8), 1035; https://doi.org/10.3390/diagnostics15081035 - 18 Apr 2025
Viewed by 153
Abstract
Temporomandibular disorders (TMD) are a cluster of musculoskeletal conditions that involve the overall structures of jaw movements, including the temporomandibular joint, the masticatory muscles, and the surrounding structures. The etiology of TMD-related pain may be either central or peripheral, and differential diagnoses with [...] Read more.
Temporomandibular disorders (TMD) are a cluster of musculoskeletal conditions that involve the overall structures of jaw movements, including the temporomandibular joint, the masticatory muscles, and the surrounding structures. The etiology of TMD-related pain may be either central or peripheral, and differential diagnoses with other orofacial conditions are commonly required. Central pain etiology is associated with altered brain function linked to sensitization of pain-producing centers, whereas peripheral etiology of TMD is considered multifactorial, with some predisposing factors. Differentiating between neurological conditions and TMD requires a comprehensive clinical evaluation, as overlapping symptoms can complicate the diagnostic process. The aim of this review was to summarize the current literature about the role of neurophysiological examination in the management of orofacial pain and temporomandibular disorders to provide clear data that could be useful for clinical practice and for future clinical studies in this field. Full article
(This article belongs to the Special Issue Advancements in the Diagnostics and Management of Musculoskeletal Diseases)
12 pages, 2847 KiB  
Article
Optimal Wavelengths for Multispectral Short Wavelength Infrared Transillumination and Reflectance Imaging for Caries Detection
by Daniel Fried and Yihua Zhu
Diagnostics 2025, 15(8), 1034; https://doi.org/10.3390/diagnostics15081034 - 18 Apr 2025
Viewed by 115
Abstract
Background/Objectives: The aim of this in vitro study was to determine the optimal combinations of wavelengths for short wavelength infrared (SWIR) multispectral transillumination and reflectance imaging of caries lesions on proximal and occlusal surfaces. Methods: The contrasts of (n = 76) caries [...] Read more.
Background/Objectives: The aim of this in vitro study was to determine the optimal combinations of wavelengths for short wavelength infrared (SWIR) multispectral transillumination and reflectance imaging of caries lesions on proximal and occlusal surfaces. Methods: The contrasts of (n = 76) caries lesions on the occlusal and proximal surfaces of extracted teeth were measured at 1050, 1300, and 1550 nm for occlusal transillumination and 1058, 1300, 1450, and 1675 nm for occlusal reflectance. All teeth were also imaged using radiography and microcomputed tomography (μCT) to verify lesion presence. A custom-fabricated handheld imaging probe suitable for clinical use and for the simultaneous acquisition of SWIR occlusal transillumination and reflectance (SWIR-OTR) images was used. Three high-power superluminescent diode lasers were used for transillumination, and a fiber-optic switch was used to switch between the transillumination wavelengths. Optical bandpass filters coupled with a tungsten halogen lamp were used for reflectance. All images were acquired at the same position and with the same field of view for comparison. Results: The highest contrasts in reflection were at 1450 and 1675 nm for occlusal and interproximal lesions, and the highest contrasts for transillumination were at 1050 and 1300 nm. Conclusions: This study suggests that the best wavelengths for SWIR-OTR are between 1000 and 1300 nm for transillumination and greater than 1400 nm for reflectance. Wavelengths beyond 1400 nm are advantageous for reflectance and yield significantly higher contrast. Wavelengths beyond 1300 nm are not promising for occlusal transillumination since internal water absorption leads to contrast inversion. Full article
(This article belongs to the Special Issue Diagnosis and Management of Dental Medicine and Surgery)
►▼ Show Figures

Figure 1

13 pages, 829 KiB  
Article
Endothelial Function and Pro-Inflammatory Cytokines as Prognostic Markers in Acute Coronary Syndromes
by Sotirios Tsalamandris, Leonidas Koliastasis, Antigoni Miliou, Evangelos Oikonomou, Nikos Papageorgiou, Alexis Antonopoulos, George Hatzis, Konstantinos Mourouzis, Georgia Vogiatzi, Gerasimos Siasos, Panagiotis Xaplanteris and Dimitris Tousoulis
Diagnostics 2025, 15(8), 1033; https://doi.org/10.3390/diagnostics15081033 - 18 Apr 2025
Viewed by 72
Abstract
Background: Endothelial dysfunction and inflammation are associated with the progression of coronary artery disease (CAD) and the pathophysiology of acute coronary syndrome (ACS). We examined the prognostic role of endothelial function and pro-inflammatory cytokines in patients admitted with ACS. Methods: The study population [...] Read more.
Background: Endothelial dysfunction and inflammation are associated with the progression of coronary artery disease (CAD) and the pathophysiology of acute coronary syndrome (ACS). We examined the prognostic role of endothelial function and pro-inflammatory cytokines in patients admitted with ACS. Methods: The study population consisted of 864 subjects. From 663 subjects who presented with chest pain, ACS was diagnosed in 460. We additionally recruited 201 consecutive patients with stable CAD. Endothelial function was assessed using flow-mediated dilatation (FMD). Tumor necrosis factor alpha (TNF-α) and interleukin-6 (IL-6) levels were measured via ELISA. Subjects with ACS were followed up for major adverse cardiovascular events (MACE), defined as cardiovascular death, cardiac arrest, myocardial infarction, stroke, nonfatal stroke, other arterial thrombotic events, and hospitalization due to cardiovascular conditions. Results: There was a stepwise impairment in FMD, logTNF-α, and logIL-6 in patients with chest pain of non-epicardial CAD etiology compared to patients with stable CAD and those with ACS (p < 0.001 for all). Moreover, patients who presented with chest pain had increased odds of ACS in accordance with the increasing levels of TNF-α, IL-6, and impaired FMD (p < 0.05 for all). Interestingly, from all these markers, in patients with ACS, we found that only TNF-α levels above 5.19 pg/mL had a 2.5-times-increased risk of MACE compared to patients with TNF-α levels below 5.19 pg/mL, independently of other confounders. Conclusions: In the current study, we found that patients who presented with ACS had impaired endothelial function and increased levels of IL-6 and TNF-α. Full article
(This article belongs to the Section Clinical Laboratory Medicine)
►▼ Show Figures

Figure 1

34 pages, 2247 KiB  
Review
Stain Normalization of Histopathological Images Based on Deep Learning: A Review
by Chuanyun Xu, Yisha Sun, Yang Zhang, Tianqi Liu, Xiao Wang, Die Hu, Shuaiye Huang, Junjie Li, Fanghong Zhang and Gang Li
Diagnostics 2025, 15(8), 1032; https://doi.org/10.3390/diagnostics15081032 - 18 Apr 2025
Viewed by 199
Abstract
Histopathological images stained with hematoxylin and eosin (H&E) are crucial for cancer diagnosis and prognosis. However, color variations caused by differences in tissue preparation and scanning devices can lead to data distribution discrepancies, adversely affecting the performance of downstream algorithms in tasks like [...] Read more.
Histopathological images stained with hematoxylin and eosin (H&E) are crucial for cancer diagnosis and prognosis. However, color variations caused by differences in tissue preparation and scanning devices can lead to data distribution discrepancies, adversely affecting the performance of downstream algorithms in tasks like classification, segmentation, and detection. To address these issues, stain normalization methods have been developed to standardize color distributions across images from various sources. Recent advancements in deep learning-based stain normalization methods have shown significant promise due to their minimal preprocessing requirements, independence from reference templates, and robustness. This review examines 115 publications to explore the latest developments in this field. We first outline the evaluation metrics and publicly available datasets used for assessing stain normalization methods. Next, we systematically review deep learning-based approaches, including supervised, unsupervised, and self-supervised methods, categorizing them by core technologies and analyzing their contributions and limitations. Finally, we discuss current challenges and future directions, aiming to provide researchers with a comprehensive understanding of the field, promote further development, and accelerate the progress of intelligent cancer diagnosis. Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
►▼ Show Figures

Figure 1

11 pages, 2309 KiB  
Article
Performance Evaluation of the New High-Sensitivity Cardiac Troponin I Immunoassay on CL-2600i Mindray Analyzer
by Flaminia Tomassetti, Denise Fiorelli, Edoardo Cappa, Alfredo Giovannelli, Martina Pelagalli, Silvia Velocci, Eleonora Nicolai, Marilena Minieri, Marco Alfonso Perrone, Sergio Bernardini and Massimo Pieri
Diagnostics 2025, 15(8), 1031; https://doi.org/10.3390/diagnostics15081031 - 18 Apr 2025
Viewed by 166
Abstract
Background: International guidelines recommend the use of high-sensitivity cardiac troponin (hs-cTn) I and T methods for the detection of myocardial injury as a pre-requisite for the diagnosis of acute myocardial infarction (AMI) in patients admitted to the emergency department. Recently, Mindray (Mindray [...] Read more.
Background: International guidelines recommend the use of high-sensitivity cardiac troponin (hs-cTn) I and T methods for the detection of myocardial injury as a pre-requisite for the diagnosis of acute myocardial infarction (AMI) in patients admitted to the emergency department. Recently, Mindray (Mindray Bio-Medical Electronics Co., Ltd., Shenzhen, China) has introduced a new chemiluminescence immunoassay (CLIA) for the detection of the cTn complex. The present study aims to verify and validate the hs-cTnI Mindray assay on the new automated CL2600i analyzer compared to the routine Alinity-i series instrument by Abbott (Abbott, Chicago, IL, USA). Methods: This study evaluated linearity, precision through the 5 × 5 protocol, methodological comparison on plasma and serum matrices, hs-cTnI 99th percentile imprecision, and the hs-cTnI detection rate in a healthy population. Results: The results obtained proved that the performance of the Mindray hs-cTnI test on the CL2600i platform was closely comparable to the Abbott Alinity-i system (plasma R2: 0.974; serum R2: 0.995). The CVs were consistently low, and no significant differences were reported. Excellent analytical performance, with high sensitivity, was also observed in the healthy population (overall detection rate: 79%), as well as good linearity within the measuring range (R2: 0.994). Conclusions: The Mindray hs-cTnI test confirms its robustness and utility in routine practice as an advanced assay. The new technology, with more sensitive detection methods, may improve the accuracy and reliability of cardiac biomarker testing, ultimately leading to better outcomes in the management of patients with AMI and other cardiac conditions. Full article
(This article belongs to the Section Clinical Laboratory Medicine)
►▼ Show Figures

Figure 1

19 pages, 679 KiB  
Systematic Review
Nurse-Administered Sedation in Digestive Endoscopy: A Systematic Review
by Miriam Hidalgo-Cabanillas, José Alberto Laredo-Aguilera, Esperanza Barroso-Corroto, Ángel López-González, Joseba Rabanales-Sotos and Juan Manuel Carmona-Torres
Diagnostics 2025, 15(8), 1030; https://doi.org/10.3390/diagnostics15081030 - 17 Apr 2025
Viewed by 198
Abstract
Background/Objectives: Nurses are becoming increasingly common healthcare professionals who perform sedation in digestive endoscopy services. Efficacy, safety and patient satisfaction are indicators of quality and safety in the administration of sedation by nurses in patients undergoing digestive endoscopy. Therefore, the aim of this [...] Read more.
Background/Objectives: Nurses are becoming increasingly common healthcare professionals who perform sedation in digestive endoscopy services. Efficacy, safety and patient satisfaction are indicators of quality and safety in the administration of sedation by nurses in patients undergoing digestive endoscopy. Therefore, the aim of this study was to synthesize the scientific evidence available to date on the efficacy, safety and patient satisfaction of nurse-administered sedation during digestive endoscopies. Methods: A systematic review was conducted according to PRISMA standards. The PubMed, Scopus, SciELO, Web of Science and LILACS databases were consulted. Narrative synthesis and descriptive statistics were used to explore complications arising from the use of sedation by nurses, using the percentage of complications and total events in the included studies. Owing to the methodology and heterogeneity of the included studies, a meta-analysis was not possible. Results: A total of 292 studies were collected, 13 of which were selected. In terms of efficacy, studies indicate that nurse sedation is effective in ensuring patient comfort and optimizing procedure times. On the other hand, studies have evaluated the safety of sedation, measured complications during sedation and reported incident and minor complication rates of less than 2.5%. Finally, studies analyzing patient satisfaction and patient experience have demonstrated high levels of satisfaction. Conclusions: Nurse-administered sedation demonstrates high efficacy in ensuring patient comfort and optimizing procedure times. Nurse-administered propofol sedation is safe for endoscopic procedures, with low rates of significant adverse events. Patients reported high levels of satisfaction with nurse-administered sedation, with reduced discomfort and improved perceptions of the quality of the procedure. Full article
(This article belongs to the Section Medical Imaging and Theranostics)
►▼ Show Figures

Figure 1

27 pages, 2238 KiB  
Review
How to Assess Pulmonary Circulation and Right Heart Chambers in Systemic Sclerosis Patients?
by Michele Correale, Ester Maria Lucia Bevere, Lucia Tricarico, Deborah Villani, Mattia Granato, Erminia Guerriero, Raffaele Capasso, Luciano Rossi, Cinzia Rotondo, Francesco Paolo Cantatore, Addolorata Corrado, Massimo Iacoviello and Natale Daniele Brunetti
Diagnostics 2025, 15(8), 1029; https://doi.org/10.3390/diagnostics15081029 - 17 Apr 2025
Viewed by 332
Abstract
Systemic sclerosis (SSc) is a rare autoimmune connective tissue disease characterized by a widespread accumulation of extracellular matrix components leading to fibrosis of the skin and internal organs. Vascular changes occur in all involved tissues and are responsible for several distinctive clinical manifestations [...] Read more.
Systemic sclerosis (SSc) is a rare autoimmune connective tissue disease characterized by a widespread accumulation of extracellular matrix components leading to fibrosis of the skin and internal organs. Vascular changes occur in all involved tissues and are responsible for several distinctive clinical manifestations of the disease. This review focuses on the usefulness of various diagnostic tools in clinical practice for the early identification of clinical, functional, and/or structural RV impairment in SSc patients at risk of PH. It aims to identify specific causes of RV dysfunction, describe potential differences in outcome measures, and, ultimately, determine different cut-off values compared to subjects with PH not related to SSc. Full article
(This article belongs to the Section Clinical Diagnosis and Prognosis)
►▼ Show Figures

Figure 1

24 pages, 4943 KiB  
Article
From Cell Lines to Patients: Dissecting the Proteomic Landscape of Exosomes in Breast Cancer
by Aleksei Shefer, Lyudmila Yanshole, Ksenia Proskura, Oleg Tutanov, Natalia Yunusova, Alina Grigor’eva, Yuri Tsentalovich and Svetlana Tamkovich
Diagnostics 2025, 15(8), 1028; https://doi.org/10.3390/diagnostics15081028 - 17 Apr 2025
Viewed by 178
Abstract
Background: Breast cancer (BC) is the most common cancer among women worldwide; therefore, the efforts of many scientists are aimed at finding effective biomarkers for this disease. It is known that exosomes are nanosized extracellular vesicles (EVs) that are released from various cell [...] Read more.
Background: Breast cancer (BC) is the most common cancer among women worldwide; therefore, the efforts of many scientists are aimed at finding effective biomarkers for this disease. It is known that exosomes are nanosized extracellular vesicles (EVs) that are released from various cell types, including cancer cells. Exosomes are directly involved in governing the physiological and pathological processes of an organism through the horizontal transfer of functional molecules (proteins, microRNA, etc.) from producing to receiving cells. Since the diagnosis and treatment of BC have been improved substantially with exosomes, in this study, we isolated breast carcinoma cell-derived exosomes, primary endotheliocyte-derived exosomes, and blood exosomes from BC patients (BCPs) in the first stage of disease and investigated their proteomic profiles. Methods: Exosomes were isolated from the samples by ultrafiltration and ultracentrifugation, followed by mass spectrometric and bioinformatics analyses of the data. The exosomal nature of vesicles was verified using transmission electron microscopy and flow cytometry. Results: Exosome proteins secreted by MCF-7 and BT-474 cells were found to form two clusters, one of which enhanced the malignant potential of cancer cells, while the other coincided with a cluster of HUVEC-derived exosome proteins. Despite the different ensembles of proteins in exosomes from the MCF-7 and BT-474 lines, the relevant portions of these proteins are involved in similar biological pathways. Comparison analysis revealed that more BC-associated proteins were found in the exosomal fraction of blood from BCPs than in the exosomal fraction of conditioned medium from cells mimicking the corresponding cancer subtype (89% and 81% for luminal A BC and MCF-7 cells and 86% and 80% for triple-positive BC and BT-474 cells, respectively). Conclusions: Tumor-associated proteins should be sought not in exosomes secreted by cell lines but in the composition of blood exosomes from cancer patients, while the contribution of endotheliocyte exosomes to the total pool of blood exosomes can be neglected. Full article
(This article belongs to the Special Issue Liquid Biopsy: Cancer Diagnostic Biomarkers of the Future)
►▼ Show Figures

Figure 1

18 pages, 7347 KiB  
Article
Clear Cell Sarcoma of Soft Tissues: Radiological Analysis of 14 Patients—MRI Findings Related to Metastatic Disease
by Paola Di Masi, Marco Colangeli, Mario Simonetti, Giuseppe Bianchi, Alberto Righi, Gabriele Bilancia, Emanuela Palmerini, Amandine Crombé and Paolo Spinnato
Diagnostics 2025, 15(8), 1027; https://doi.org/10.3390/diagnostics15081027 - 17 Apr 2025
Viewed by 108
Abstract
Background/Objectives: Clear cell sarcoma (CCS) is a very uncommon, aggressive soft-tissue sarcoma (STS) with a dismal prognosis. In the current literature, there are very limited data focused on the radiological features of CCS. Our study’s objective was to describe CCS pre-treatment’s peculiar imaging [...] Read more.
Background/Objectives: Clear cell sarcoma (CCS) is a very uncommon, aggressive soft-tissue sarcoma (STS) with a dismal prognosis. In the current literature, there are very limited data focused on the radiological features of CCS. Our study’s objective was to describe CCS pre-treatment’s peculiar imaging characteristics (MRI above all) and to assess if some radiologic features may predict patients’ outcomes with regard to the occurrence of distant metastases. Methods: Our single-center experience includes all the patients with a histological diagnosis of CCS and available radiological and clinical data: 14 patients (8M, 6F, mean age 39.4 years old) were included. The available pre-treatment MRI or contrast-enhanced computed tomography (CECT) studies were examined using an analytical grid that incorporated characteristics from the most recent STS research. The occurrence of metastatic disease was matched with radiological features from baseline imaging studies. Results: MRI was available in 13 patients and CECT in 1 patient. The mean longest diameter (LD) was 50.5 mm ± 29.2. In 10 cases (71.4%), the tumor was deeply seated. MRI revealed a slightly high signal intensity (SI) on T1-WI and a high SI on T2-WI in every subject. At baseline, metastases were already present in 5/14 (35.7%) patients, 3 more developed metastases during the following 5 years (8/14, 57.1%), and 2 additional developed late-onset metastasis after more than 5 years from the diagnosis (total of 10/14 metastatic patients 71.4%). LD and metastasis at diagnosis were significantly correlated (Pearson correlation = 72%, p-value = 0.004). A pre-treatment LD > 4 cm was significantly associated with the development of distant metastases within 5 years from diagnosis and in subsequent follow-up (p = 0.0003). LD > 4 cm represents an increase in risk of metastatic disease within 5 years and during the course of follow-up (OR = 195.00, 95%CI: 3.36–11285.55, p = 0.01). The presence of MRI signs of macroscopic necrosis represented an increase in risk of metastatic disease within 5 years (OR = 15.00, 95%CI: 1.03–218.31—p = 0.04). Conclusions: The identification of MRI features of aggressive biology is a key element for an early referral to sarcoma centers. In our study, a LD > 4 cm and the presence of MRI signs of macroscopic necrosis at the baseline images resulted in being a predictor of metastatic disease. Full article
(This article belongs to the Special Issue Diagnostic Imaging in Bone and Soft-Tissue Sarcomas: Practice, Education, and Innovation—2nd Edition)
►▼ Show Figures

Figure 1

14 pages, 1243 KiB  
Article
The Prognostic Value of the CALLY Index in Sepsis: A Composite Biomarker Reflecting Inflammation, Nutrition, and Immunity
by Ali Sarıdaş and Remzi Çetinkaya
Diagnostics 2025, 15(8), 1026; https://doi.org/10.3390/diagnostics15081026 - 17 Apr 2025
Viewed by 180
Abstract
Background/Objectives: Sepsis remains a leading cause of mortality worldwide, necessitating the development of effective prognostic markers for early risk stratification. The C-reactive protein–albumin–lymphocyte (CALLY) index is a novel biomarker that integrates inflammatory, nutritional, and immunological parameters. This study aimed to evaluate the [...] Read more.
Background/Objectives: Sepsis remains a leading cause of mortality worldwide, necessitating the development of effective prognostic markers for early risk stratification. The C-reactive protein–albumin–lymphocyte (CALLY) index is a novel biomarker that integrates inflammatory, nutritional, and immunological parameters. This study aimed to evaluate the association between the CALLY index and 30-day all-cause mortality in sepsis patients. Methods: This retrospective cohort study included adult patients diagnosed with sepsis in the emergency department between 1 January 2022, and 1 January 2025. The CALLY index was calculated as (CRP × absolute lymphocyte count)/albumin. The primary outcome was 30-day all-cause mortality. Five machine learning models—extreme gradient boosting (XGBoost), multilayer perceptron, random forest, support vector machine, and generalized linear model—were developed for mortality prediction. Four feature selection strategies (gain score, SHAP values, Boruta, and LASSO regression) were used to evaluate predictor consistency. The clinical utility of the CALLY index was assessed using decision curve analysis (DCA). Results: A total of 1644 patients were included, of whom 345 (21.0%) died within 30 days. Among the five machine learning models, the XGBoost model achieved the highest performance (AUC: 0.995, R2: 0.867, MAE: 0.063, RMSE: 0.145). In gain-based feature selection, the CALLY index emerged as the top predictor (gain: 0.187), followed by serum lactate (0.185) and white blood cell count (0.117). The CALLY index also ranked second in SHAP analysis (mean value: 0.317) and first in Boruta importance (mean importance: 37.54). DCA showed the highest net clinical benefit of the CALLY index within the 0.10–0.15 risk threshold range. Conclusions: This study demonstrates that the CALLY index is a significant predictor of 30-day mortality in sepsis patients. Machine learning analysis further reinforced the prognostic value of the CALLY index. Full article
(This article belongs to the Special Issue Diagnosis and Prognosis of Sepsis)
►▼ Show Figures

Figure 1

13 pages, 4984 KiB  
Article
Particularities in the “Oldie but Goldie” Tc-99m DMSA Renography: A Retrospective Reference Centre Overview of 931 Children
by Irena Cristina Grierosu, Iuliana Magdalena Starcea, Wael Jalloul, Maria Adriana Mocanu, Roxana Alexandra Bogos, Tudor Ilie Lazaruc, Madalina Andreea Beldie, Ruxandra Tibu, Teodor Marian Ionescu, Cati Raluca Stolniceanu, Brindusa Casiana Acsinte, Cipriana Stefanescu, Alexandra Saviuc and Vlad Ghizdovat
Diagnostics 2025, 15(8), 1025; https://doi.org/10.3390/diagnostics15081025 - 17 Apr 2025
Viewed by 154
Abstract
Background/Objectives: The Tc-99m dimercaptosuccinic acid (DMSA) renal scan clearly images the renal cortex, highlighting functional tissue areas and indicating regions of renal scarring, infection, malformations, or other types of renal damage. To enhance the management of paediatric cases involving renal malformations and [...] Read more.
Background/Objectives: The Tc-99m dimercaptosuccinic acid (DMSA) renal scan clearly images the renal cortex, highlighting functional tissue areas and indicating regions of renal scarring, infection, malformations, or other types of renal damage. To enhance the management of paediatric cases involving renal malformations and to reduce the incidence of chronic and progressive kidney diseases in “future adults”, our study aims to identify and categorise various renal anomalies. Methods: This has been achieved by analysing the Tc-99m DMSA renal scans of a large cohort of 931 children diagnosed with different renal pathologies. After interpreting the scans, we categorised the renal malformations and cortical modifications into four groups: kidney number anomalies, positional anomalies, structural anomalies, and shape anomalies. Results: There has been a notable increase in the demand for renal scintigraphy in recent years, rising from 82 cases in 2019 to 183 cases in 2024. Structural anomalies were the most common type of malformations (73% from all patients), featuring a significant variety of cortical modifications. In total, 98 cases (93% from kidney number anomalies and 10.5% from all children) were diagnosed with renal agenesis. Additionally, 30 children (3.2% from all patients) had positional anomalies, primarily ectopic kidneys, and 54 patients (5.8% from all cases) had shape malformations, especially fused kidneys. Conclusions: Combining the Tc-99m DMSA renal scan with ultrasound provides a more reliable diagnosis of paediatric renal progressive diseases. A more accurate diagnosis allows for quicker treatment and prevention of potential complications, ultimately improving the quality of life and decreasing hospital costs of paediatric patients becoming adults. Full article
(This article belongs to the Special Issue Critical Issues in Diagnosis and Management of Pediatric Diseases)
►▼ Show Figures

Figure 1

13 pages, 796 KiB  
Article
Artificial Intelligence in Oral Diagnosis: Detecting Coated Tongue with Convolutional Neural Networks
by Sümeyye Coşgun Baybars, Merve Hacer Talu, Çağla Danacı and Seda Arslan Tuncer
Diagnostics 2025, 15(8), 1024; https://doi.org/10.3390/diagnostics15081024 - 17 Apr 2025
Viewed by 161
Abstract
Background/Objectives: Coated tongue is a common oral condition with notable clinical relevance, often overlooked due to its asymptomatic nature. Its presence may reflect poor oral hygiene and can serve as an early indicator of underlying systemic diseases. This study aimed to develop a [...] Read more.
Background/Objectives: Coated tongue is a common oral condition with notable clinical relevance, often overlooked due to its asymptomatic nature. Its presence may reflect poor oral hygiene and can serve as an early indicator of underlying systemic diseases. This study aimed to develop a robust diagnostic model utilizing convolutional neural networks and machine learning classifiers to improve the detection of coated tongue lesions. Methods: A total of 200 tongue images (100 coated and 100 healthy) were analyzed. Images were acquired using a DSLR camera (Nikon D5500 with Sigma Macro 105 mm lens, Nikon, Tokyo, Japan) under standardized daylight conditions. Following preprocessing, feature vectors were extracted using CNN architectures (VGG16, VGG19, ResNet, MobileNet, and NasNet) and classified using Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Multi-Layer Perceptron (MLP) classifiers. Performance metrics included sensitivity, specificity, accuracy, and F1 score. Results: The SVM + VGG19 hybrid model achieved the best performance among all tested configurations, with a sensitivity of 82.6%, specificity of 88.23%, accuracy of 85%, and an F1 score of 86.36%. Conclusions: The SVM + VGG19 model demonstrated high accuracy and reliability in diagnosing coated tongue lesions, highlighting its potential as an effective clinical decision support tool. Future research with larger datasets may further enhance model robustness and applicability in diverse populations. Full article
(This article belongs to the Special Issue AI and Digital Health for Disease Diagnosis and Monitoring)
►▼ Show Figures

Figure 1

13 pages, 1371 KiB  
Article
A Noninvasive Method of Diagnosing Metabolic Dysfunction-Associated Steatohepatitis Using Cytokeratin-18 Fragment and FIB-3 Index
by Tomoko Tadokoro, Miwa Kawanaka, Hirokazu Takahashi, Shinichi Aishima, Wenli Zhao, Rie Yano, Kei Takuma, Mai Nakahara, Kyoko Oura, Koji Fujita, Kiyoyuki Kobayashi, Shima Mimura, Joji Tani, Asahiro Morishita, Reiji Haba, Tsutomu Masaki, Hideki Kobara and Masafumi Ono
Diagnostics 2025, 15(8), 1023; https://doi.org/10.3390/diagnostics15081023 - 17 Apr 2025
Viewed by 129
Abstract
Background/Objectives: We aim to determine if cytokeratin-18 fragment (CK-18F) could be used to diagnose metabolic dysfunction-associated steatohepatitis (MASH). Methods: A total of 289 patients with metabolic dysfunction-associated steatotic liver disease (MASLD) were enrolled in the analysis. To evaluate the association between CK-18F levels [...] Read more.
Background/Objectives: We aim to determine if cytokeratin-18 fragment (CK-18F) could be used to diagnose metabolic dysfunction-associated steatohepatitis (MASH). Methods: A total of 289 patients with metabolic dysfunction-associated steatotic liver disease (MASLD) were enrolled in the analysis. To evaluate the association between CK-18F levels and the histological features of MASH, weighted receiver operating characteristic (ROC) curve analyses were performed. The diagnostic utility of CK-18F was compared with that of the Mac-2 binding protein glycan isomer (M2BPGi). Additionally, we assessed the predictive performance of combining CK-18F with either the FIB-4 index or the FIB-3 index for diagnosing MASH and investigated predictors of future progression to cirrhosis. Results: CK-18F was more useful for MASH diagnosis than M2BPGi and the FIB-4 index in the multivariate analysis, with a sensitivity of 47% and specificity of 80% at a CK-18F cutoff value of 750 U/L. Because CK-18F decreases with advanced liver fibrosis, the combination of the FIB-4 or FIB-3 index with CK-18F was examined to identify cases with cirrhosis. The combination of the CK-18F level and the FIB-3 index better predicted MASH than the combination of the CK-18F level and the FIB-4 index. The FIB-3 index was the most useful predictor of cirrhosis on imaging five years after diagnosis with F2 or less disease. Conclusions: CK-18F is useful for MASH diagnosis, and the diagnostic algorithm combining CK-18F with the FIB-3 index may be more useful than the previously reported MASH diagnostic algorithm that combined it with the FIB-4 index. Full article
(This article belongs to the Section Pathology and Molecular Diagnostics)
►▼ Show Figures

Figure 1

18 pages, 3561 KiB  
Article
Improving TMJ Diagnosis: A Deep Learning Approach for Detecting Mandibular Condyle Bone Changes
by Kader Azlağ Pekince, Adem Pekince and Buse Yaren Kazangirler
Diagnostics 2025, 15(8), 1022; https://doi.org/10.3390/diagnostics15081022 - 17 Apr 2025
Viewed by 167
Abstract
Objectives: This paper evaluates the potential of using deep learning approaches for the detection of degenerative bone changes in the mandibular condyle. The aim of this study is to enable the detection and diagnosis of mandibular condyle degenerations, which are difficult to [...] Read more.
Objectives: This paper evaluates the potential of using deep learning approaches for the detection of degenerative bone changes in the mandibular condyle. The aim of this study is to enable the detection and diagnosis of mandibular condyle degenerations, which are difficult to observe and diagnose on panoramic radiographs, using deep learning methods. Methods: A total of 3875 condylar images were obtained from panoramic radiographs. Condylar bone changes were represented by flattening, osteophyte, and erosion, and images in which two or more of these changes were observed were labeled as “other”. Due to the limited number of images containing osteophytes and erosion, two approaches were used. In the first approach, images containing osteophytes and erosion were combined into the “other” group, resulting in three groups: normal, flattening, and deformation (“deformation” encompasses the “other” group, together with osteophyte and erosion). In the second approach, images containing osteophytes and erosion were completely excluded, resulting in three groups: normal, flattening, and other. The study utilizes a range of advanced deep learning algorithms, including Dense Networks, Residual Networks, VGG Networks, and Google Networks, which are pre-trained with transfer learning techniques. Model performance was evaluated using datasets with different distributions, specifically 70:30 and 80:20 training-test splits. Results: The GoogleNet architecture achieved the highest accuracy. Specifically, with the 80:20 split of the normal-flattening-deformation dataset and the Adamax optimizer, an accuracy of 95.23% was achieved. The results demonstrate that CNN-based methods are highly successful in determining mandibular condyle bone changes. Conclusions: This study demonstrates the potential of deep learning, particularly CNNs, for the accurate and efficient detection of TMJ-related condylar bone changes from panoramic radiographs. This approach could assist clinicians in identifying patients requiring further intervention. Future research may involve using cross-sectional imaging methods and training the right and left condyles together to potentially increase the success rate. This approach has the potential to improve the early detection of TMJ-related condylar bone changes, enabling timely referrals and potentially preventing disease progression. Full article
(This article belongs to the Special Issue Advancements in Artificial Intelligence for Dentomaxillofacial Radiology)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-108
Previous Issue
Next Issue
Back to TopTop