Next Issue
Volume 15, February-2
Previous Issue
Volume 15, January-2
 
 
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 3
share announcement

Diagnostics, Volume 15, Issue 3 (February-1 2025) – 163 articles

Cover Story (view full-size image): In this study, ctDNA and [18F]FDG-PET/CT were investigated during the first cycle of anticancer therapy in patients with NSCLC to explore their potential for early response evaluation. Of the sixteen included patients, eight were non-responders. ctDNA mutations were detected in baseline blood samples in eight patients. Changes in ctDNA level, MTV4.0, and sumSULpeak at week 3 indicated response in 7 out of 8 patients, 13 out of 15 patients, and 9 out of 15 patients, respectively. At week 3, no false increases were seen with ctDNA and MTV4.0. These results suggest that early changes in ctDNA and [18F]FDG-PET/CT at 3 weeks of treatment could be used to early assess treatment response. Increased levels of ctDNA and MTV4.0 at week 3 were only observed in patients with treatment failure. 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:
34 pages, 2747 KiB  
Review
Optimizing Cancer Treatment: Exploring the Role of AI in Radioimmunotherapy
by Hossein Azadinejad, Mohammad Farhadi Rad, Ahmad Shariftabrizi, Arman Rahmim and Hamid Abdollahi
Diagnostics 2025, 15(3), 397; https://doi.org/10.3390/diagnostics15030397 - 6 Feb 2025
Viewed by 699
Abstract
Radioimmunotherapy (RIT) is a novel cancer treatment that combines radiotherapy and immunotherapy to precisely target tumor antigens using monoclonal antibodies conjugated with radioactive isotopes. This approach offers personalized, systemic, and durable treatment, making it effective in cancers resistant to conventional therapies. Advances in [...] Read more.
Radioimmunotherapy (RIT) is a novel cancer treatment that combines radiotherapy and immunotherapy to precisely target tumor antigens using monoclonal antibodies conjugated with radioactive isotopes. This approach offers personalized, systemic, and durable treatment, making it effective in cancers resistant to conventional therapies. Advances in artificial intelligence (AI) present opportunities to enhance RIT by improving precision, efficiency, and personalization. AI plays a critical role in patient selection, treatment planning, dosimetry, and response assessment, while also contributing to drug design and tumor classification. This review explores the integration of AI into RIT, emphasizing its potential to optimize the entire treatment process and advance personalized cancer care. Full article
(This article belongs to the Special Issue Machine Learning in Radiomics: Opportunities and Challenges)
►▼ Show Figures

Graphical abstract

24 pages, 1109 KiB  
Review
Harnessing Artificial Intelligence in Obesity Research and Management: A Comprehensive Review
by Sarfuddin Azmi, Faisal Kunnathodi, Haifa F. Alotaibi, Waleed Alhazzani, Mohammad Mustafa, Ishtiaque Ahmad, Riyasdeen Anvarbatcha, Miltiades D. Lytras and Amr A. Arafat
Diagnostics 2025, 15(3), 396; https://doi.org/10.3390/diagnostics15030396 - 6 Feb 2025
Viewed by 715
Abstract
Purpose: This review aims to explore the clinical and research applications of artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), in understanding, predicting, and managing obesity. It assesses the use of AI tools to identify obesity-related risk factors, predict outcomes, [...] Read more.
Purpose: This review aims to explore the clinical and research applications of artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), in understanding, predicting, and managing obesity. It assesses the use of AI tools to identify obesity-related risk factors, predict outcomes, personalize treatments, and improve healthcare interventions for obesity. Methods: A comprehensive literature search was conducted using PubMed and Google Scholar, with keywords including “artificial intelligence”, “machine learning”, “deep learning”, “obesity”, “obesity management”, and related terms. Studies focusing on AI’s role in obesity research, management, and therapeutic interventions were reviewed, including observational studies, systematic reviews, and clinical applications. Results: This review identifies numerous AI-driven models, such as ML and DL, used in obesity prediction, patient stratification, and personalized management strategies. Applications of AI in obesity research include risk prediction, early detection, and individualization of treatment plans. AI has facilitated the development of predictive models utilizing various data sources, such as genetic, epigenetic, and clinical data. However, AI models vary in effectiveness, influenced by dataset type, research goals, and model interpretability. Performance metrics such as accuracy, precision, recall, and F1-score were evaluated to optimize model selection. Conclusions: AI offers promising advancements in obesity management, enabling more personalized and efficient care. While technology presents considerable potential, challenges such as data quality, ethical considerations, and technical requirements remain. Addressing these will be essential to fully harness AI’s potential in obesity research and treatment, supporting a shift toward precision healthcare. Full article
(This article belongs to the Special Issue Advances in Disease Prediction)
►▼ Show Figures

Figure 1

21 pages, 2814 KiB  
Article
Three-Dimensional Geometric Morphometric Characterization of Facial Sexual Dimorphism in Juveniles
by Riccardo Solazzo, Annalisa Cappella, Daniele Gibelli, Claudia Dolci, Gianluca Tartaglia and Chiarella Sforza
Diagnostics 2025, 15(3), 395; https://doi.org/10.3390/diagnostics15030395 - 6 Feb 2025
Viewed by 448
Abstract
Background: The characterization of facial sexual dimorphic patterns in healthy populations serves as valuable normative data to tailor functionally effective surgical treatments and predict their aesthetic outcomes and to identify dysmorphic facial traits related to hormonal disorders and genetic syndromes. Although the analysis [...] Read more.
Background: The characterization of facial sexual dimorphic patterns in healthy populations serves as valuable normative data to tailor functionally effective surgical treatments and predict their aesthetic outcomes and to identify dysmorphic facial traits related to hormonal disorders and genetic syndromes. Although the analysis of facial sexual differences in juveniles of different ages has already been investigated, few studies have approached this topic with three-dimensional (3D) geometric morphometric (GMM) analysis, whose interpretation may add important clinical insight to the current understanding. This study aims to investigate the location and extent of facial sexual variations in juveniles through a spatially dense GMM analysis. Methods: We investigated 3D stereophotogrammetric facial scans of 304 healthy Italians aged 3 to 18 years old (149 males, 155 females) and categorized into four different age groups: early childhood (3–6 years), late childhood (7–12 years), puberty (13–15 years), and adolescence (16–18 years). Geometric morphometric analyses of facial shape (allometry, general Procrustes analysis, Principal Component Analysis, Procrustes distance, and Partial Least Square Regression) were conducted to detail sexually dimorphic traits in each age group. Results: The findings confirmed that males have larger faces than females of the same age, and significant differences in facial shape between the two sexes exist in all age groups. Juveniles start to express sexual dimorphism from 3 years, even though biological sex becomes a predictor of facial soft tissue morphology from the 7th year of life, with males displaying more protrusive medial facial features and females showing more outwardly placed cheeks and eyes. Conclusions: We provided a detailed characterization of facial change trajectories in the two sexes along four age classes, and the provided data can be valuable for several clinical disciplines dealing with the craniofacial region. Our results may serve as comparative data in the early diagnosis of craniofacial abnormalities and alterations, as a reference in the planning of personalized surgical and orthodontic treatments and their outcomes evaluation, as well as in several forensic applications such as the prediction of the face of missing juveniles. Full article
(This article belongs to the Topic Assessment of Craniofacial Morphology: Traditional Methods and Innovative Approaches)
►▼ Show Figures

Figure 1

13 pages, 578 KiB  
Systematic Review
A Systematic Review of Circulating miRNAs Validated by Multiple Independent Studies in Laryngeal Cancer
by Andreea Banta, Felix Bratosin, Ioana Golu, Ana-Olivia Toma and Eugenia Maria Domuta
Diagnostics 2025, 15(3), 394; https://doi.org/10.3390/diagnostics15030394 - 6 Feb 2025
Viewed by 495
Abstract
Background and Objectives: Laryngeal squamous cell carcinoma (LSCC) is a common head and neck cancer with significant morbidity and mortality. Circulating microRNAs (miRNAs) have emerged as promising non-invasive biomarkers for cancer diagnosis and prognosis. This systematic review aims to identify circulating miRNAs associated [...] Read more.
Background and Objectives: Laryngeal squamous cell carcinoma (LSCC) is a common head and neck cancer with significant morbidity and mortality. Circulating microRNAs (miRNAs) have emerged as promising non-invasive biomarkers for cancer diagnosis and prognosis. This systematic review aims to identify circulating miRNAs associated with LSCC, emphasizing those validated by at least two independent studies to improve reliability and clinical applicability. Methods: An extensive literature search was performed in the PubMed, Scopus, and Web of Science databases up to October 2024, using keywords related to LSCC and circulating miRNAs. Studies involving human participants that provided quantitative data on circulating miRNA expression levels and their clinical correlations were included. Data extraction and quality assessment were conducted following standardized protocols, highlighting miRNAs reported in multiple studies. Results: Nine high-quality studies encompassing 660 patients with LSCC and 212 controls were included. Several miRNAs were consistently identified across these studies. miR-21-5p was upregulated in four studies and associated with advanced disease stages, lymph node metastasis, and decreased survival rates. miR-125b-5p and miR-126-3p were consistently downregulated, linked to advanced clinical stages and poor tumor differentiation. miR-27a-3p was upregulated in two studies and correlated with poor prognosis, promoting LSCC progression by targeting Smad4. Additionally, miR-33a-5p was identified as a potential diagnostic biomarker with high sensitivity and specificity. These miRNAs show potential as non-invasive biomarkers for the diagnosis and prognosis of LSCC. Conclusions: This systematic review highlights specific circulating miRNAs—particularly miR-21-5p, miR-125b-5p, miR-126-3p, miR-27a-3p, and miR-33a-5p—as promising biomarkers for LSCC. The consistent findings across independent studies emphasize their potential clinical utility in early detection, prognostic assessment, and therapeutic targeting. However, further validation in larger and more diverse populations, along with the standardization of detection methods, is necessary before these biomarkers can be implemented in clinical practice. Full article
(This article belongs to the Special Issue Advances in the Diagnosis and Management of ENT (Ear–Nose–Throat) Diseases)
►▼ Show Figures

Figure 1

9 pages, 844 KiB  
Article
Cardiac Morpho-Functional Changes, Inflammation and Fibrosis in Systemic Sclerosis—A Pilot Study of a Tertiary Center Cohort
by Karolina Dorniak, Zuzanna Gogulska, Alessandro Viti, Anna Glińska, Dorota Kulawiak-Gałąska, Jadwiga Fijałkowska, Anna Wojteczek, Dagmara Wojtowicz, Katarzyna Sienkiewicz, Marcin Hellmann and Żaneta Smoleńska
Diagnostics 2025, 15(3), 393; https://doi.org/10.3390/diagnostics15030393 - 6 Feb 2025
Viewed by 590
Abstract
Background: Cardiac involvement (CI) in systemic sclerosis (SSc) is frequently subclinical and it can be identified in up to 80% of autopsied hearts. If present, symptoms are related to adverse prognosis, and CI represents one of the predominant causes of SSc-related mortality. [...] Read more.
Background: Cardiac involvement (CI) in systemic sclerosis (SSc) is frequently subclinical and it can be identified in up to 80% of autopsied hearts. If present, symptoms are related to adverse prognosis, and CI represents one of the predominant causes of SSc-related mortality. Methods: A total of 20 patients with a diagnosis of SSc were included and followed up, and 37 volunteers were included and subsequently scanned on a 1.5T MR system. Results: Overall, thirteen (65%) patients had one or more abnormal cardiac findings in CMR (defined as CI[+]), of which in seven (35%), baseline ECGs and standard echocardiograms were normal or unspecific. Compared to healthy volunteers, SSc patients had a lower LVEF% (56.6% vs. 61.6%; p = 0.0131), longer T1 (1028.3 ms vs. 993.1 ms; p = 0.0049) and T2 relaxation times (48.24 ms vs. 43 ms p = 0.0011), and higher extracellular volume (ECV, 27.9% vs. 26.0%; p = 0.0112). However, no difference in CMR-derived, feature-tracking GLS values between patients and healthy controls was found (−15.5[2,8] vs. −16.3[1,1], respectively, p = 0.11). Over 3.4 (1.9–5.5) years, three patients (15%) died, and two others (10%) sustained major cardiac complications. Conclusions: Cardiac magnetic resonance with modern quantitative techniques reveals subtle morpho-functional alterations and thus allows for early diagnosis of myocardial involvement in systemic sclerosis. Our findings emphasize the need for extended diagnostic workup in these patients and demonstrate the ability of cardiac MR to select patients requiring closer follow-up and/or treatment decisions. Full article
(This article belongs to the Special Issue Advances in Imaging Diagnosis and Management of Cardiovascular and Pulmonary Diseases)
►▼ Show Figures

Figure 1

16 pages, 655 KiB  
Review
Role of Ultrasound in Evaluating Ligament Injuries Around the Ankle: A Narrative Review
by Soichi Hattori, Rachit Saggar, Joseph Mullen, Abdulganeey Olawin, Eva Heidinger, Warren Austin, Akeem Williams, Glenn Reeves and MaCalus Vinson Hogan
Diagnostics 2025, 15(3), 392; https://doi.org/10.3390/diagnostics15030392 - 6 Feb 2025
Viewed by 596
Abstract
Ultrasound has emerged as a valuable imaging modality for evaluating ligamentous injuries around the ankle joint, offering several advantages over traditional imaging techniques. It is more cost-effective and widely available than MRI, and it avoids the ionizing radiation exposure associated with X-rays, making [...] Read more.
Ultrasound has emerged as a valuable imaging modality for evaluating ligamentous injuries around the ankle joint, offering several advantages over traditional imaging techniques. It is more cost-effective and widely available than MRI, and it avoids the ionizing radiation exposure associated with X-rays, making it a safer option, particularly for pediatric and adolescent populations. In cases of inversion ankle sprains, ultrasound allows for more accurate assessment of the anterior talofibular ligament (ATFL) and calcaneofibular ligament (CFL) compared to X-rays and manual examination and yields diagnostic results comparable to MRI. For high ankle sprains involving syndesmosis injuries, ultrasound—especially stress ultrasound—has shown high diagnostic accuracy. Additionally, ultrasound evaluation of the deltoid ligament (DL) in cases of ankle fractures can aid surgeons in determining the need for ligament repair in conjunction with fracture management. This review explores recent developments in ultrasound imaging of the lateral, medial, and syndesmotic ligaments of the ankle joint and discusses its potential applications for evaluating the spring and posterior ligaments. The review provides a comprehensive overview of the ever-expanding role of ultrasound in the management of ankle ligamentous injuries. Full article
(This article belongs to the Special Issue Diagnostic Imaging in Musculoskeletal Diseases)
►▼ Show Figures

Figure 1

3 pages, 424 KiB  
Correction
Correction: Ong et al. Underexpression of Carbamoyl Phosphate Synthetase I as Independent Unfavorable Prognostic Factor in Intrahepatic Cholangiocarcinoma: A Potential Theranostic Biomarker. Diagnostics 2023, 13, 2296
by Khaa Hoo Ong, Yao-Yu Hsieh, Ding-Ping Sun, Steven Kuan-Hua Huang, Yu-Feng Tian, Chia-Lin Chou, Yow-Ling Shiue, Keva Joseph and I-Wei Chang
Diagnostics 2025, 15(3), 391; https://doi.org/10.3390/diagnostics15030391 - 6 Feb 2025
Viewed by 294
Abstract
In the original publication [...] Full article
(This article belongs to the Special Issue Advanced Pathology and Diagnostics in Gastroenterology and Liver Diseases)
►▼ Show Figures

Figure 3

20 pages, 1267 KiB  
Article
Validation of a Compact and Self-Contained Pyrosequencing Platform for Clinical Screening of RAS Mutations in Thyroid Cancers
by Anne Burkhardt, Chelsey L. Smith and Rajesh R. Singh
Diagnostics 2025, 15(3), 390; https://doi.org/10.3390/diagnostics15030390 - 6 Feb 2025
Viewed by 542
Abstract
Background and Objectives: Accurate screening of clinically significant tumor mutations is critical for precision medicine in oncology. This requires genotyping platforms with high accuracy and compatibility with varying DNA yields from challenging sample types. Here, we have validated a new, improved, compact, and [...] Read more.
Background and Objectives: Accurate screening of clinically significant tumor mutations is critical for precision medicine in oncology. This requires genotyping platforms with high accuracy and compatibility with varying DNA yields from challenging sample types. Here, we have validated a new, improved, compact, and self-contained pyrosequencing platform (Pyromark Q48 Autoprep; Q48) for screening N-, K- and H-RAS mutations in thyroid cancers. Methods: A set of 73 thyroid cancer and 16 non-thyroid cancer samples (fine needle aspirates and formalin-fixed paraffin-embedded) with known mutation status of RAS genes were tested using the Q48 platform. Performance parameters such as accuracy, precision, and limit-of-detection were established. Q48 workflow was compared to an older Q96 pyrosequencing platform to highlight the differences and advantages. RAS testing by pyrosequencing was also compared to a clinically validated next-generation sequencing platform using 56 thyroid cancer samples. Results: The Q48 Pyromark was found to be a very reliable platform suited for quick testing of RAS genes with complete accuracy, high precision, and high detection sensitivity. It had comparable accuracy, with higher sequencing success rates than NGS. The hands-on time, workflow ease, and efficiency were also significantly improved in comparison with the Q96 platform. Conclusions: Overall, the Q48 platform was found to be a well-suited and agile clinical sequencing platform to rapidly screen RAS mutations. Full article
(This article belongs to the Section Pathology and Molecular Diagnostics)
►▼ Show Figures

Figure 1

16 pages, 5497 KiB  
Article
Validation of Ultrasound for Quantification of Knee Meniscal Tissue: A Cadaveric Study
by Jacobo Rodríguez-Sanz, Miguel Malo-Urriés, Sergio Borrella-Andrés, Isabel Albarova-Corral and Carlos López-de-Celis
Diagnostics 2025, 15(3), 389; https://doi.org/10.3390/diagnostics15030389 - 6 Feb 2025
Viewed by 437
Abstract
Background: While MRI is the gold standard for meniscal assessment, its cost and accessibility limitations have led to growing interest in ultrasound, though its validity for quantifying meniscal tissue remains unclear. To validate the use of ultrasound in quantifying meniscal tissue across [...] Read more.
Background: While MRI is the gold standard for meniscal assessment, its cost and accessibility limitations have led to growing interest in ultrasound, though its validity for quantifying meniscal tissue remains unclear. To validate the use of ultrasound in quantifying meniscal tissue across the anterior, middle, and posterior regions of both menisci (medial and lateral) in longitudinal and transverse planes by comparison with cadaveric dissection. Methods: A cross-sectional study was conducted on ten cryopreserved anatomical donors, obtaining a total of 120 ultrasound scans from the different meniscal regions. Following ultrasound imaging, cadaveric dissection was performed to facilitate photometric measurements, thereby enabling validation of the ultrasound findings. The intra-examiner reliability of the ultrasound measurements was also assessed. Results: The intra-examiner reliability of ultrasound measurements ranged from moderate to excellent. A strong and statistically significant positive correlation was observed between ultrasound and photometric measurements across all meniscal regions (r > 0.821; p < 0.05). In the medial meniscus, ultrasound visualized 99.1% of the anterior region (8.71 mm with ultrasound; 8.64 mm with photometry), 96.3% of the middle region (9.09 mm with ultrasound; 9.39 mm with photometry), and 98.5% of the posterior region (10.54 mm with ultrasound; 10.61 mm with photometry). In the lateral meniscus, ultrasound visualized 107.1% of the anterior region, 105.1% of the middle region, and 97.8% of the posterior region. The observed excess in tissue visualization in some regions likely reflects the inclusion of adjacent connective tissue, indistinguishable from meniscal tissue on ultrasound. Conclusions: Ultrasound is a valid and reliable modality for visualizing most meniscal tissue across regions, with a measurement discrepancy under 0.7 mm compared to anatomical dissection. However, caution is advised as adjacent connective tissue may sometimes be misidentified as meniscal tissue during evaluations. Full article
(This article belongs to the Special Issue New Advances in Forensic Radiology and Imaging)
►▼ Show Figures

Figure 1

13 pages, 1453 KiB  
Review
The Value of MRI and Radiomics for the Diagnostic Evaluation of Thyroid-Associated Ophthalmopathy
by Weiyi Zhou, Yan Song, Jufeng Shi and Tuo Li
Diagnostics 2025, 15(3), 388; https://doi.org/10.3390/diagnostics15030388 - 6 Feb 2025
Viewed by 403
Abstract
Thyroid-associated ophthalmopathy (TAO) is a vision-threatening autoimmune disease that involves the extraocular muscles (EOMs) and periorbital fat. Typical signs of TAO include eyelid recession, proptosis, diplopia, and decreased visual acuity. As a self-limited disease, there is major bipolarity in clinical outcomes in TAO [...] Read more.
Thyroid-associated ophthalmopathy (TAO) is a vision-threatening autoimmune disease that involves the extraocular muscles (EOMs) and periorbital fat. Typical signs of TAO include eyelid recession, proptosis, diplopia, and decreased visual acuity. As a self-limited disease, there is major bipolarity in clinical outcomes in TAO population. The early diagnosis and prediction of these refractory and relapsed patients is essential. Unfortunately, commonly used tools such as CAS/NOSPECTS, are based on clinical symptoms and signs alone, have significant limitations. Some imaging techniques or examinations, such as magnetic resonance imaging (MRI), can be very effective in assisting TAO assessment, from exhaustive whiteboard notes to optimized patient outcomes. Being one of the most commonly used and accurate objective examinations for TAO assessment, MRI boosts no ionizing radiation, high soft tissue contrast, better reflection of tissue water content, and the ability to quantify multiple parameters. In addition, novel MR sequences are becoming increasingly more familiar in TAO and other areas of clinical and scientific research. Moreover, radiomics, a method involving the extraction of a large number of features from medical images through algorithms, is a more recent approach used in the analysis and characterization of TAO data. Thus, this review aims to summarize and compare the value of routine and novel functional MRI sequences and radiomics prediction models in the diagnosis and evaluation of TAO. Full article
(This article belongs to the Special Issue Advances in Eye Imaging)
►▼ Show Figures

Figure 1

15 pages, 5378 KiB  
Protocol
HEALS-A and GRADES: Novel Histological and Clinical Scales for Assessing Skin Regeneration in Murine Wound Healing Models
by Jose R. Muñoz-Torres, Idalia Garza-Veloz, Perla Velasco-Elizondo and Margarita L. Martinez-Fierro
Diagnostics 2025, 15(3), 387; https://doi.org/10.3390/diagnostics15030387 - 6 Feb 2025
Viewed by 416
Abstract
Background: Wounds affect approximately 15 out of every 1000 individuals, representing a significant healthcare challenge. The preclinical evaluation of novel wound treatments is important for advancing therapies that promote effective skin regeneration and improve healing outcomes. Methods: In this study, we integrated existing [...] Read more.
Background: Wounds affect approximately 15 out of every 1000 individuals, representing a significant healthcare challenge. The preclinical evaluation of novel wound treatments is important for advancing therapies that promote effective skin regeneration and improve healing outcomes. Methods: In this study, we integrated existing knowledge from the literature on murine wound healing models, histological features of the skin, and clinical scores described in humans to propose two complementary assessment tools: the HEALS-A histological score (healing, epithelialization, angiogenesis, leukocytes, scar tissue, appendages) and the GRADES clinical score (granulation tissue, redness/edema, appearance of wound, devitalized tissue). Results: These scales combine real-time clinical observation with detailed histological analysis, providing a practical and comprehensive approach to assessing wound healing. Unlike existing wound assessing approaches, HEALS-A does not require specialized software and considers regenerated tissue structures, ensuring a broader and more-detailed evaluation. Conclusions: The assessment of wound closure over time, combined with clinical evaluation and histological analysis of skin, provides a comprehensive approach to determining the true impact of new treatments on skin regeneration and the recovery of its functions in wounds. Full article
(This article belongs to the Special Issue Skin Disease: Diagnosis and Management)
►▼ Show Figures

Figure 1

12 pages, 2236 KiB  
Article
Limitations of Semi-Automated Immunomagnetic Separation of HLA-G-Positive Trophoblasts from Papanicolaou Smears for Prenatal Genetic Diagnostics
by Eddy N. de Boer, Nicole Corsten-Janssen, Elles Wierenga, Theo Bijma, Jurjen T. Knapper, Gerard J. te Meerman, Gwendolyn T. R. Manten, Nine V. A. M. Knoers, Katelijne Bouman, Leonie K. Duin and Cleo C. van Diemen
Diagnostics 2025, 15(3), 386; https://doi.org/10.3390/diagnostics15030386 - 6 Feb 2025
Viewed by 434
Abstract
Background: In prenatal genetic diagnostics, the detection of single-gene defects relies on chorionic villus sampling (CVS) and amniocentesis, which carry a miscarriage risk of 0.2–0.3%. To mitigate this risk, fetal trophoblasts have been isolated from a Papanicolaou smear using Trophoblast Retrieval and Isolation [...] Read more.
Background: In prenatal genetic diagnostics, the detection of single-gene defects relies on chorionic villus sampling (CVS) and amniocentesis, which carry a miscarriage risk of 0.2–0.3%. To mitigate this risk, fetal trophoblasts have been isolated from a Papanicolaou smear using Trophoblast Retrieval and Isolation from the Cervix (TRIC). However, this method is labor-intensive and has been shown to be challenging to implement in clinical practice. Here, we describe our experiences in using semi-automated immunomagnetic cell sorting for isolating trophoblasts from clinically obtained Papanicolaou smears during ongoing pregnancies. Methods: Using HLA-G-positive Jeg-3 and HLA-G-negative HeLa cell lines in 10%, 1%, and 0.1% dilutions, we tested and optimized the isolation of HLA-G-positive cells using FACS and semi-automated immunomagnetic cell sorting. We used the latter technique for isolation of HLA-G-positive cells from Papanicolaou smears collected from 26 pregnant women, gestational age between 6 and 20 weeks, who underwent CVS. Results: In four independent dilution series, the mean percentages of Jeg-3 cells went from 7.1% to 53.5%, 0.9% to 32.6%, and 0.4% to 2.6% (7.5, 36, and 6.5-fold enrichment, respectively) using immunomagnetic cell sorting. After sorting of the Papanicolaou smears, HLA-G-positive cells were moderately increased in the positive (14.61 vs. 11.63%) and decreased in the negative fraction (7.87 vs. 11.63%) compared to baseline pre-sorting. However, we could not identify fetal cells using XY-chromosomal FISH in a male sample. Conclusions: Our study supports previous findings that careful sampling of fetal cells from Papanicolaou smears in a clinical context poses significant challenges to cell retrieval. Full article
(This article belongs to the Section Pathology and Molecular Diagnostics)
►▼ Show Figures

Figure 1

11 pages, 2425 KiB  
Review
Integrative Insights into Philadelphia-like B-Cell Acute Lymphoblastic Leukemia: A Genetic and Molecular Landscape
by Stacey Chuang, Alexandra Chu, Rodrigo Hurtado and Carlos A. Tirado
Diagnostics 2025, 15(3), 385; https://doi.org/10.3390/diagnostics15030385 - 6 Feb 2025
Viewed by 552
Abstract
Philadelphia-like chromosome acute lymphoblastic leukemia (Ph-like ALL) is a new subtype of B-ALL that was discovered in 2009 and recognized in the 2016 revision of the World Health Organization criteria under the classification of myeloid neoplasms and acute leukemia. This new subtype has [...] Read more.
Philadelphia-like chromosome acute lymphoblastic leukemia (Ph-like ALL) is a new subtype of B-ALL that was discovered in 2009 and recognized in the 2016 revision of the World Health Organization criteria under the classification of myeloid neoplasms and acute leukemia. This new subtype has an extremely poor prognosis compared to that for other subtypes of ALL, with a 41% five-year overall survival (OS) rate. Ph-like ALL is chemoresistant, with a high minimum residual disease (MRD) level after induction therapy, and it is associated with a high relapse rate. Clinical trials are currently being conducted to study the effectiveness of specific tyrosine kinase inhibitors against different genetic alterations in Ph-like ALL patients and the effect of allogeneic hematopoietic cell transplants (allo-HCT) on treatments. This review summarizes the current findings on Ph-like ALL, focusing on its molecular landscape and clinical implications. Full article
(This article belongs to the Section Clinical Laboratory Medicine)
►▼ Show Figures

Figure 1

36 pages, 11202 KiB  
Article
Deep Learning-Driven Single-Lead ECG Classification: A Rapid Approach for Comprehensive Cardiac Diagnostics
by Mohamed Ezz
Diagnostics 2025, 15(3), 384; https://doi.org/10.3390/diagnostics15030384 - 6 Feb 2025
Viewed by 564
Abstract
Background/Objectives: This study aims to address the critical need for accessible, early, and accurate cardiac di-agnostics, especially in resource-limited or remote settings. By shifting focus from traditional multi-lead ECG analysis to single-lead ECG data, this research explores the potential of advanced deep [...] Read more.
Background/Objectives: This study aims to address the critical need for accessible, early, and accurate cardiac di-agnostics, especially in resource-limited or remote settings. By shifting focus from traditional multi-lead ECG analysis to single-lead ECG data, this research explores the potential of advanced deep learning models for classifying cardiac conditions, including Nor-mal, Abnormal, Previous Myocardial Infarction (PMI), and Myocardial Infarction (MI). Methods: Five state-of-the-art deep learning architectures—Inception, DenseNet201, MobileNetV2, NASNetLarge, and VGG16—were systematically evaluated on individual ECG leads. Key performance metrics, such as model accuracy, inference time, and size, were analyzed to determine the optimal configurations for practical applications. Results: VGG16 emerged as the most accurate model, achieving an F1-score of 98.11% on lead V4 with a prediction time of 4.2 ms and a size of 528 MB, making it suitable for high-precision clinical settings. MobileNetV2, with a compact size of 13.4 MB, offered a balanced performance, achieving a 97.24% F1-score with a faster inference time of 3.2 ms, positioning it as an ideal candidate for real-time monitoring and telehealth applications. Conclusions: This study bridges a critical gap in cardiac diagnostics by demonstrating the feasibility of lightweight, scalable, single-lead ECG analysis using advanced deep learning models. The findings pave the way for deploying portable diagnostic tools across diverse settings, enhancing the accessibility and efficiency of cardiac care globally. Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
►▼ Show Figures

Figure 1

18 pages, 3584 KiB  
Article
Hematopathological Patterns in Acute Myeloid Leukemia with Complications of Overt Disseminated Intravascular Coagulation
by Bernhard Strasser, Sebastian Mustafa, Josef Seier, Josef Tomasits and Alexander Haushofer
Diagnostics 2025, 15(3), 383; https://doi.org/10.3390/diagnostics15030383 - 6 Feb 2025
Viewed by 508
Abstract
Background: Acute myeloid leukemia (AML) complicated by disseminated intravascular coagulation (DIC) poses major diagnostic and therapeutic challenges. While DIC is well documented in acute promyelocytic leukemia, its manifestations in non-APL AML remain underexplored, necessitating precise diagnostic strategies for effective management. Methods: AML patients [...] Read more.
Background: Acute myeloid leukemia (AML) complicated by disseminated intravascular coagulation (DIC) poses major diagnostic and therapeutic challenges. While DIC is well documented in acute promyelocytic leukemia, its manifestations in non-APL AML remain underexplored, necessitating precise diagnostic strategies for effective management. Methods: AML patients with overt DIC were analyzed, including morphological, immunophenotypic, cytogenetic, and genetic evaluations. DIC was diagnosed using the ISTH scoring system, and AML subtypes were classified following WHO criteria. Results: Three diagnostic patterns were identified. (1) Acute promyelocytic leukemia: Leukemia characterized by PML::RARa rearrangements, FLT3 co-mutations, and frequent Auer rods and faggot bundles. Immunocytological analysis showed CD34 and HLA-DR negativity. (2) AML with FLT3 and/or NPM1 mutations: A high prevalence of cup-like blasts was found in 70% of cases. FLT3 mutations, often co-occurring with NPM1, dominated, while karyotypes were typically normal. Immunophenotyping revealed strong myeloid marker expression (MPO+, CD13+, and CD33+), with occasional CD34 negativity. (3) AML with monocytic differentiation: Leukemia defined by monoblastic/promonocytic morphology, DNMT3A mutations, and complex karyotypes or 11q23 rearrangements. Immunophenotyping demonstrated a dominance of monocytic markers (CD4+, CD14+, CD15+, and CD64+). Two patients presented unique profiles with no alignment to these patterns. Conclusions: This study highlights distinct hematopathological patterns of AML with overt DIC, providing a framework for early and precise diagnosis. Recognizing these patterns is critical for tailoring diagnostic and therapeutic approaches to improve outcomes in this high-risk population. Full article
(This article belongs to the Special Issue Advances in Diagnostic Pathology)
►▼ Show Figures

Figure 1

13 pages, 2077 KiB  
Systematic Review
Can Blood Flow Restriction Be the Key to Reducing Quadriceps Weakness in the Early and Mid-Phases After Anterior Cruciate Ligament Reconstruction with a Hamstring Graft? A Systematic Review of Randomized Controlled Trials
by Ayrton Moiroux--Sahraoui, Jean Mazeas, Marine Blossier, Maurice Douryang, Georges Kakavas, Timothy E. Hewett and Florian Forelli
Diagnostics 2025, 15(3), 382; https://doi.org/10.3390/diagnostics15030382 - 6 Feb 2025
Viewed by 769
Abstract
Background: Injury to the anterior cruciate ligament is one of the most common knee injuries. Following anterior cruciate ligament reconstruction, strength deficits and reduced quadriceps and hamstring muscle mass are common. Traditional strengthening protocols recommend the use of heavy loads. However, following surgery, [...] Read more.
Background: Injury to the anterior cruciate ligament is one of the most common knee injuries. Following anterior cruciate ligament reconstruction, strength deficits and reduced quadriceps and hamstring muscle mass are common. Traditional strengthening protocols recommend the use of heavy loads. However, following surgery, heavy-load exercises are contraindicated to protect the joint and graft. Blood flow restriction resistance training is an alternative that optimizes muscle recovery. The aim of this study was to evaluate the effects of blood flow restriction resistance training on muscle mass and strength after ACLR. Methods: The Pubmed, Cochrane Library, and PEDro databases were used to constitute the corpus of this systematic review. The methodological quality of the studies was assessed with the Cochrane Collaboration’s analysis grid. Results: Thirty-four articles were identified in the initial search, and five randomized controlled trials were included in this review. Not all studies reported significant results regarding strength and muscle mass. Two of these studies observed a significant improvement in strength associated with blood flow restriction resistance training compared with the control group. A significant increase in muscle mass was observed in one study. Conclusions: The blood flow restriction resistance training method shows superior efficacy to training without occlusion, yet this device has not been shown to be more effective than heavy-load resistance training in terms of muscular strength and muscle mass. Blood flow restriction resistance training shows superior efficacy in both these variables when used with low loads. However, there are still few random controlled trials on this subject, and this review presents their limitations and biases. Future research is needed on guidelines for the application of blood flow restriction resistance training in clinical populations. Full article
(This article belongs to the Special Issue Diagnosis and Management of Sports Medicine)
►▼ Show Figures

Figure 1

13 pages, 1651 KiB  
Article
Towards Parkinson’s Disease Detection Through Analysis of Everyday Handwriting
by Jeferson David Gallo-Aristizabal, Daniel Escobar-Grisales, Cristian David Ríos-Urrego, Jesús Francisco Vargas-Bonilla, Adolfo M. García and Juan Rafael Orozco-Arroyave
Diagnostics 2025, 15(3), 381; https://doi.org/10.3390/diagnostics15030381 - 5 Feb 2025
Viewed by 574
Abstract
Background: Parkinson’s disease (PD) is the second most prevalent neurodegenerative disorder worldwide. People suffering from PD exhibit motor symptoms that affect the control of upper and lower limb movement. Among daily activities that depend on proper upper limb control is the handwriting process, [...] Read more.
Background: Parkinson’s disease (PD) is the second most prevalent neurodegenerative disorder worldwide. People suffering from PD exhibit motor symptoms that affect the control of upper and lower limb movement. Among daily activities that depend on proper upper limb control is the handwriting process, which has been studied in state-of-the-art research, mainly considering non-semantic drawings like spirals, geometric figures, cursive lines, and others. Objectives: This paper analyzes the suitability of modeling the handwriting process of digits from 0 to 9 to automatically discriminate between PD patients and healthy control subjects. The main hypothesis is that modeling these numbers allows a more natural evaluation of upper limb control. Methods: Two approaches are considered: modeling of the images resulting from the strokes collected by the digital tablet and modeling of the time series yielded by the digital tablet while performing the strokes, i.e., time-dependent signals. The first approach is implemented by fine-tuning a CNN-based architecture, while the second approach is based on hand-crafted features measured upon the time series, namely pressure and kinematic measurements. Features extracted from time-dependent signals are represented following two strategies, one based on statistical functionals and the other one based on creating Gaussian Mixture Models (GMMs). Results: The experiments indicate that pressure-based features modeled with functionals are the ones that yield the highest accuracy, indicating that PD-related symptoms are better modeled with dynamic approaches than those based on images. Conclusions: The dynamic approach outperformed the image-based model, indicating that the writing process, modeled with signals collected over time, reveals motor symptoms more clearly than images resulting from handwriting. This finding is in line with previous results in the state-of-the-art research and constitutes a step forward to create more accurate and informative methods to detect and monitor PD symptoms. Full article
(This article belongs to the Special Issue Medical Data Processing and Analysis—2nd Edition)
►▼ Show Figures

Figure 1

12 pages, 2370 KiB  
Essay
The Art of Medical Diagnosis: Lessons on Interpretation of Signs from Italian High Renaissance Paintings
by Marcin Śniadecki, Anna Malitowska, Oliwia Musielak, Jarosław Meyer-Szary, Paweł Guzik, Zuzanna Boyke, Martyna Danielkiewicz, Joanna Konarzewska and Cynthia Aristei
Diagnostics 2025, 15(3), 380; https://doi.org/10.3390/diagnostics15030380 - 5 Feb 2025
Viewed by 612
Abstract
Medicine is struggling with the constantly rising incidence of breast cancer. The key to this fight is to be able to speed up diagnosis, as rapid diagnosis reduces the number of aggressive or advanced cases. For this process to be effective, it is [...] Read more.
Medicine is struggling with the constantly rising incidence of breast cancer. The key to this fight is to be able to speed up diagnosis, as rapid diagnosis reduces the number of aggressive or advanced cases. For this process to be effective, it is necessary to have the right attitude toward diagnosis as a research practice. Our critical analysis of diagnosis, as a methodology of medical science, reflects on it as a research practice that is regulated in a socio-subjective way by a methodological culture. This position allows us to contrast critical methodological culture with the habitual–practical, or methodical, culture of practicing diagnosis. We point to the interpretative status of medical analyses performed by medical historians by referring to Italian Renaissance paintings and historical–artistic interpretations. In this field, analyzing disputes between researchers as a clash of methodologies in the ways interpretation transforms signs into meaning is a critical methodological reflection. Medicine is a diverse scientific discourse with a paradigmatic structure in which new ways of conducting diagnostic tests may appear. It is only possible to see this from the methodological level. In addition, passive respect for existing patterns of conduct hinders an exchange of views between researchers, which limits the possibility of correcting research procedures. The ultimate consequence of such passivity is an inability to improve diagnosis, which, in turn, harms the interests of patients. In this regard, it is worth remembering that the paramount objective of diagnosis is not the disease, but the patient. Full article
(This article belongs to the Special Issue Advances in the Diagnosis and Management of Breast Cancer)
►▼ Show Figures

Figure 1

25 pages, 4389 KiB  
Article
Melatonin Pattern: A New Method for Machine Learning-Based Classification of Sleep Deprivation
by Nursena Baygin
Diagnostics 2025, 15(3), 379; https://doi.org/10.3390/diagnostics15030379 - 5 Feb 2025
Viewed by 448
Abstract
Background: Pattern recognition and machine learning-based classification approaches are frequently used, especially in the health field. In this research, a new feature extraction model inspired by the melatonin hormone (sleep hormone) and named MelPat (melatonin pattern) has been developed. The developed model [...] Read more.
Background: Pattern recognition and machine learning-based classification approaches are frequently used, especially in the health field. In this research, a new feature extraction model inspired by the melatonin hormone (sleep hormone) and named MelPat (melatonin pattern) has been developed. The developed model has been tested on an open access dataset. Materials and Methods: An open access sleep deprivation electroencephalography (EEG) dataset was tested to evaluate the MelPat method. There are two classes in the dataset. These are (a) sleep deprivation (SD) and (b) healthy control (HC) groups, respectively. In this study, EEG signals were divided into 15 s segments, thus obtaining 1377 SD and 1378 HC samples. In the next phase of the research, a new feature extraction model was proposed, and this model was named MelPat as it was inspired by the melatonin hormone. Additionally, the feature vector was expanded using the statistical moment approach. In the signal decomposition phase of the model, the Tunable Q-Wavelet Transform (TQWT) method was used. Thus, the signal was decomposed into sub-bands, and feature extraction was applied to each band. Neighborhood Component Analysis (NCA) and Chi2 methods were used together to reduce the dimension of the feature vector and select the most significant features. In this phase, the most significant features from both feature selection algorithms were combined, and the final feature vector was obtained. In the classification phase of the model, the Support Vector Machine (SVM) algorithm, which is a shallow classifier, was used. The dataset used in the research has 61 channels. Therefore, after obtaining channel-based results, the iterative majority voting (IMV) algorithm was applied to achieve higher classification performance and generalize the results, and the most accurate results were automatically selected. Results: With the proposed MelPat algorithm, a high classification success of 97.71% was achieved on the open access sleep deprivation dataset. Conclusions: The obtained results show that the MelPat-based new classification approach is highly effective on the dataset collected for SD detection. Moreover, the fact that the proposed method is inspired by the melatonin chemical, which is the sleep hormone, makes the method attractive and ironic. Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
►▼ Show Figures

Figure 1

32 pages, 5010 KiB  
Article
CART-ANOVA-Based Transfer Learning Approach for Seven Distinct Tumor Classification Schemes with Generalization Capability
by Shiraz Afzal, Muhammad Rauf, Shahzad Ashraf, Shahrin Bin Md Ayob and Zeeshan Ahmad Arfeen
Diagnostics 2025, 15(3), 378; https://doi.org/10.3390/diagnostics15030378 - 5 Feb 2025
Viewed by 865
Abstract
Background/Objectives: Deep transfer learning, leveraging convolutional neural networks (CNNs), has become a pivotal tool for brain tumor detection. However, key challenges include optimizing hyperparameter selection and enhancing the generalization capabilities of models. This study introduces a novel CART-ANOVA (Cartesian-ANOVA) hyperparameter tuning framework, which [...] Read more.
Background/Objectives: Deep transfer learning, leveraging convolutional neural networks (CNNs), has become a pivotal tool for brain tumor detection. However, key challenges include optimizing hyperparameter selection and enhancing the generalization capabilities of models. This study introduces a novel CART-ANOVA (Cartesian-ANOVA) hyperparameter tuning framework, which differs from traditional optimization methods by systematically integrating statistical significance testing (ANOVA) with the Cartesian product of hyperparameter values. This approach ensures robust and precise parameter tuning by evaluating the interaction effects between hyperparameters, such as batch size and learning rate, rather than relying solely on grid or random search. Additionally, it implements seven distinct classification schemes for brain tumors, aimed at improving diagnostic accuracy and robustness. Methods: The proposed framework employs a ResNet18-based knowledge transfer learning (KTL) model trained on a primary dataset, with 20% allocated for testing. Hyperparameters were optimized using CART-ANOVA analysis, and statistical validation ensured robust parameter selection. The model’s generalization and robustness were evaluated on an independent second dataset. Performance metrics, including precision, accuracy, sensitivity, and F1 score, were compared against other pre-trained CNN models. Results: The framework achieved exceptional testing accuracy of 99.65% for four-class classification and 98.05% for seven-class classification on the source 1 dataset. It also maintained high generalization capabilities, achieving accuracies of 98.77% and 96.77% on the source 2 datasets for the same tasks. The incorporation of seven distinct classification schemes further enhanced variability and diagnostic capability, surpassing the performance of other pre-trained models. Conclusions: The CART-ANOVA hyperparameter tuning framework, combined with a ResNet18-based KTL approach, significantly improves brain tumor classification accuracy, robustness, and generalization. These advancements demonstrate strong potential for enhancing diagnostic precision and informing effective treatment strategies, contributing to advancements in medical imaging and AI-driven healthcare solutions. Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
►▼ Show Figures

Figure 1

27 pages, 4940 KiB  
Article
Alzheimer’s Prediction Methods with Harris Hawks Optimization (HHO) and Deep Learning-Based Approach Using an MLP-LSTM Hybrid Network
by Raheleh Ghadami and Javad Rahebi
Diagnostics 2025, 15(3), 377; https://doi.org/10.3390/diagnostics15030377 - 5 Feb 2025
Viewed by 499
Abstract
Background/Objective: Alzheimer’s disease is a progressive brain syndrome causing cognitive decline and, ultimately, death. Early diagnosis is essential for timely medical intervention, with MRI medical imaging serving as a primary diagnostic tool. Machine learning (ML) and deep learning (DL) methods are increasingly [...] Read more.
Background/Objective: Alzheimer’s disease is a progressive brain syndrome causing cognitive decline and, ultimately, death. Early diagnosis is essential for timely medical intervention, with MRI medical imaging serving as a primary diagnostic tool. Machine learning (ML) and deep learning (DL) methods are increasingly utilized to analyze these images, but accurately distinguishing between healthy and diseased states remains a challenge. This study aims to address these limitations by developing an integrated approach combining swarm intelligence with ML and DL techniques for Alzheimer’s disease classification. Method: This proposal methodology involves sourcing Alzheimer’s disease-related MRI images and extracting features using convolutional neural networks (CNNs) and the Gray Level Co-occurrence Matrix (GLCM). The Harris Hawks Optimization (HHO) algorithm is applied to select the most significant features. The selected features are used to train a multi-layer perceptron (MLP) neural network and further processed using a long short-term (LSTM) memory network in order to classify tumors as malignant or benign. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset is utilized for assessment. Results: The proposed method achieved a classification accuracy of 97.59%, sensitivity of 97.41%, and precision of 97.25%, outperforming other models, including VGG16, GLCM, and ResNet-50, in diagnosing Alzheimer’s disease. Conclusions: The results demonstrate the efficacy of the proposed approach in enhancing Alzheimer’s disease diagnosis through improved feature extraction and selection techniques. These findings highlight the potential for advanced ML and DL integration to improve diagnostic tools in medical imaging applications. Full article
(This article belongs to the Special Issue Artificial Intelligence in Alzheimer’s Disease Diagnosis)
►▼ Show Figures

Figure 1

15 pages, 1192 KiB  
Article
A Robust and Comprehensive Study of the Molecular and Genetic Basis of Neurodevelopmental Delay in a Sample of 3244 Patients, Evaluated by Exome Analysis in a Latin Population
by Julian Lamilla, Taryn A. Castro-Cuesta, Paula Rueda-Gaitán, Laura Camila Rios Pinto, Diego Alejandro Rodríguez Gutiérrez, Yuri Natalia Sanchez Rubio, Carlos Estrada-Serrato, Olga Londoño, Cynthia Rucinski, Mauricio Arcos-Burgos, Mario Isaza-Ruget and Juan Javier López Rivera
Diagnostics 2025, 15(3), 376; https://doi.org/10.3390/diagnostics15030376 - 5 Feb 2025
Viewed by 700
Abstract
Background and Objectives: Neurodevelopmental disorders (NDDs), including developmental delay (DD), autism spectrum disorder (ASD), intellectual disability (ID), attention-deficit/hyperactivity disorder (ADHD), and specific learning disorders, affect 15% of children and adolescents worldwide. Advances in next-generation sequencing, particularly whole exome sequencing (WES), have improved [...] Read more.
Background and Objectives: Neurodevelopmental disorders (NDDs), including developmental delay (DD), autism spectrum disorder (ASD), intellectual disability (ID), attention-deficit/hyperactivity disorder (ADHD), and specific learning disorders, affect 15% of children and adolescents worldwide. Advances in next-generation sequencing, particularly whole exome sequencing (WES), have improved the understanding of NDD genetics. Methodology: This study analyzed 3244 patients undergoing WES (single, duo, trio analyses), with 1028 meeting inclusion criteria (67% male; aged 0–50 years). Results: Pathogenic (P) or likely pathogenic (LP) variants were identified in 190 patients, achieving a diagnostic yield of 13.4% (singleton), 14% (duo), and 21.2% (trio). A total of 207 P/LP variants were identified in NDD-associated genes: 38% were missense (48 de novo), 29% frameshift (26 de novo), 21% nonsense (14 de novo), 11% splicing site (14 de novo), and 1% inframe (1 de novo). De novo variants accounted for 49.8% of cases, with 86 novels de novo variants and 27 novel non de novo variants unreported in databases like ClinVar or scientific literature. Conclusions: This is the largest study on WES in Colombian children with NDDs and one of the largest in Latino populations. It highlights WES as a cost-effective first-tier diagnostic tool in low-income settings, reducing diagnostic timelines and improving clinical care. These findings underscore the feasibility of implementing WES in underserved populations and contribute significantly to understanding NDD genetics, identifying novel variants with potential for further research and clinical applications. Full article
(This article belongs to the Special Issue Assessment and Diagnosis of Cognitive Disorders)
►▼ Show Figures

Figure 1

11 pages, 408 KiB  
Article
Can Galectin-3 Be Used as a Predictor of Obstructive Sleep Apnea Severity: Insights from High-Volume Patient Single Center
by Milica Brajkovic, Sofija Nikolic, Viseslav Popadic, Natasa Milic, Nina Rajovic, Novica Nikolic, Ana Sekulic, Marija Brankovic, Mihailo Stjepanovic, Spasoje Popevic, Branko Milovanovic and Marija Zdravkovic
Diagnostics 2025, 15(3), 375; https://doi.org/10.3390/diagnostics15030375 - 5 Feb 2025
Viewed by 470
Abstract
Background/Objectives: Obstructive sleep apnea (OSA) is a condition characterized by intermittent airway obstructions, leading to reduced oxygen levels and increased sympathetic nervous system activity. OSA can cause a range of health problems, including an increased risk of cardiovascular diseases and mortality. Galectin-3, a [...] Read more.
Background/Objectives: Obstructive sleep apnea (OSA) is a condition characterized by intermittent airway obstructions, leading to reduced oxygen levels and increased sympathetic nervous system activity. OSA can cause a range of health problems, including an increased risk of cardiovascular diseases and mortality. Galectin-3, a member of the galectin family, plays a significant role in inflammation and fibrosis, and studies show that it is elevated in various conditions, including heart and lung diseases. The aim of this study was to determine whether galectin-3 levels are related to the severity of sleep apnea. Methods: A total of 191 participants from the University Clinical Hospital Center Bezanijska Kosa, Belgrade, Serbia, between January 2023 and May 2024, were included in the analyses. All patients were hospitalized under suspicion of OSA, and they all underwent a polysomnography test. Various demographic, respiratory, laboratory, and clinical parameters were obtained. Correlations between numerical variables and galectin-3 were assessed by the Pearson or Spearman correlation coefficients. Univariate and multivariate linear regression models were used to assess the predictors of galectin-3 values. In all analyses, the significance level was set at 0.05. Results: The mean age of the study participants was 56.2 years, mostly male (68.9%). Of the comorbidities, two-thirds of patients had hypertension (66.1%), 46.8% had hyperlipoproteinemia, and 21.1% had diabetes mellitus. Patients who had an AHI of more than fifteen events per hour more often had higher values of galectin-3. OSA severity had a significant positive correlation with galectin-3 (p = 0.014). In multivariate linear regression analysis, significant independent predictors of higher galectin-3 values were older age, presence of coronary disease, hypoventilation syndrome, higher BMI, NTproBNP, lactate, creatinine, lower LDL, and lower FEV1 (p < 0.05). Conclusions: The present study demonstrated that galectin-3 is linked to the severity of OSA and plays a crucial role in inflammation induced by intermittent hypoxia in OSA. Further screening and interventions targeting galectin-3 could aid in preventing inflammatory diseases related to sleep disturbances. Full article
(This article belongs to the Special Issue Advances in Diagnosis and Treatment of Obstructive Sleep Apnea)
►▼ Show Figures

Figure 1

19 pages, 3581 KiB  
Article
Multi-Classification of Skin Lesion Images Including Mpox Disease Using Transformer-Based Deep Learning Architectures
by Seyfettin Vuran, Murat Ucan, Mehmet Akin and Mehmet Kaya
Diagnostics 2025, 15(3), 374; https://doi.org/10.3390/diagnostics15030374 - 5 Feb 2025
Viewed by 574
Abstract
Background/Objectives: As reported by the World Health Organization, Mpox (monkeypox) is an important disease present in 110 countries, mostly in South Asia and Africa. The number of Mpox cases has increased rapidly, and the medical world is worried about the emergence of a [...] Read more.
Background/Objectives: As reported by the World Health Organization, Mpox (monkeypox) is an important disease present in 110 countries, mostly in South Asia and Africa. The number of Mpox cases has increased rapidly, and the medical world is worried about the emergence of a new pandemic. Detection of Mpox by traditional methods (using test kits) is a costly and slow process. For this reason, there is a need for methods that have high success rates and can diagnose Mpox disease from skin images with a deep-learning-based autonomous method. Methods: In this work, we propose a multi-class, fast, and reliable autonomous disease diagnosis model using transformer-based deep learning architectures and skin lesion images, including for Mpox disease. Our other aim is to investigate the effects of self-supervised learning, self-distillation, and shifted window techniques on classification success when multi-class skin lesion images are trained with transformer-based deep learning architectures. The Mpox Skin Lesion Dataset, Version 2.0, which was publicly released in 2024, was used in the training, validation, and testing processes of the study. Results: The SwinTransformer architecture we proposed in our study achieved about 8% higher accuracy evaluation metric classification success compared to its closest competitor in the literature. ViT, MAE, DINO, and SwinTransformer architectures achieved 93.10%, 84.60%, 90.40%, and 93.71% accuracy classification success, respectively. Conclusions: The results obtained in the study showed that Mpox disease and other skin lesion images can be diagnosed with high success and can support doctors in decision-making. In addition, the study provides important results that can be used in other medical fields where the number of images is low in terms of transformer-based architecture and technique to use. Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
►▼ Show Figures

Figure 1

10 pages, 2722 KiB  
Article
Computed Tomography Assessment of Os Trigonum in the Omani Population and Its Clinical Relevance
by Zahran Al Thuhli, Mohammed Al Farsi, Yasser Mahfouz, Ghassan Al Mamari, Younis Al-Mufargi, Yassine Bouchareb and Srinivasa Rao Sirasanagandla
Diagnostics 2025, 15(3), 373; https://doi.org/10.3390/diagnostics15030373 - 5 Feb 2025
Viewed by 431
Abstract
Background: Os trigonum (OT) is an accessory ossicle that develops from the failure of the secondary ossification center of the posterior talar process fusion. It is clinically significant due to its association with posterior ankle pain and impingement syndromes. Despite its tremendous [...] Read more.
Background: Os trigonum (OT) is an accessory ossicle that develops from the failure of the secondary ossification center of the posterior talar process fusion. It is clinically significant due to its association with posterior ankle pain and impingement syndromes. Despite its tremendous clinical relevance, limited data exist on the frequency of OT in Middle Eastern populations. Objectives: This study aimed to determine the frequency, morphological variations, and dimensions of OT in Omani subjects using computed tomography (CT) imaging and to evaluate the sex and laterality differences in its occurrence. Methods: A retrospective cross-sectional study of 352 foot and ankle CT scans were conducted to assess the OT at Sultan Qaboos University Hospital. OT presence, dimensions, and classification along with patient demographics, including age and sex, were recorded. Descriptive statistical analysis and the chi-square test were employed to present the data. Results: The overall prevalence of OT was 10.2%, with a frequency of 11.2% on the left side and 8.9% on the right side. Type IIA was the most prevalent subtype in both feet (41.2% right, 44.4% left). The average minor-axis and macro-axis dimensions were 7.88 ± 2.998 mm and 10.76 ± 4.280 mm on the right side, while they were 8.06 ± 2.600 mm and 11.50 ± 4.997 mm on the left side. No statistically significant sex or laterality differences were observed with regard to the OT frequency (p > 0.05). Conclusions: This study provides the first detailed evaluation of OT in the Omani population, highlighting its frequency and morphological variability. These findings emphasize the importance of CT imaging in identifying OT and guiding clinical management. Future studies should explore OT’s clinical correlations to enhance its diagnostic and therapeutic implications. Full article
(This article belongs to the Special Issue Advances in Anatomy—Third Edition)
►▼ Show Figures

Figure 1

10 pages, 1484 KiB  
Case Report
Monochorionic Diamniotic Twins with Sex Discordance: Case Series
by Valentina Sala, Luigina Spaccini, Stefano Faiola, Daniela Casati, Arianna Laoreti, Lisanne S. A. Tollenaar, Enrico Lopriore and Mariano M. Lanna
Diagnostics 2025, 15(3), 372; https://doi.org/10.3390/diagnostics15030372 - 4 Feb 2025
Viewed by 513
Abstract
Background and Clinical Significance: Ultrasonographic diagnosis of twin pregnancies has become routine, with chorionicity playing a crucial role in assessing associated risks. Traditionally, monochorionic (MC) twins were believed to derive from a single zygote, ensuring sex concordance. However, recent cases of dizygotic monochorionic [...] Read more.
Background and Clinical Significance: Ultrasonographic diagnosis of twin pregnancies has become routine, with chorionicity playing a crucial role in assessing associated risks. Traditionally, monochorionic (MC) twins were believed to derive from a single zygote, ensuring sex concordance. However, recent cases of dizygotic monochorionic (MCDZ) twins challenge this paradigm. In this paper, four cases of MCDZ twins with sex discordance are described. Case presentation: Case 1 and case 2 describe two spontaneous MC/diamniotic twin pregnancies in which sex discordance between twins was attributed to blood chimerism. Case 3 is about a MC/diamniotic twin pregnancy derived from a single blastocyst transfer after in vitro fertilization (IVF), and that was complicated by twin-to-twin transfusion syndrome, with zygosity testing confirming the dizygosity. Case 4 is a twin anemia polycythemia sequence diagnosed after birth in twins considered dichorionic during pregnancy (due to sex difference) and defined as monochorionic after placental examination. Conclusions: The prevalence of monochorionic dizygotic (MCDZ) twins remains uncertain, and many cases likely go unnoticed, particularly when twins are of the same sex. In twin pregnancies, determining chorionicity during the first-trimester ultrasound (US) is critical. Accurate identification of monochorionicity is essential for managing potential complications. Careful verification of sex concordance between twins is necessary. In cases of sex discordance, amniocentesis is required for karyotype evaluation and zygosity testing. Full article
(This article belongs to the Special Issue Prenatal Diagnosis and Clinical Management of Twin Pregnancy)
►▼ Show Figures

Figure 1

12 pages, 1380 KiB  
Article
Prediction of the Cause of Fundus-Obscuring Vitreous Hemorrhage Using Machine Learning
by Jinsoo Kim, Bo Sook Han, Joo Eun Ha, Min Seon Park, Soonil Kwon and Bum-Joo Cho
Diagnostics 2025, 15(3), 371; https://doi.org/10.3390/diagnostics15030371 - 4 Feb 2025
Viewed by 444
Abstract
Objectives: This study aimed to predict the unknown etiology of fundus-obscuring vitreous hemorrhage (FOVH) based on preoperative conditions using machine learning (ML) and to identify key preoperative factors. Methods: Medical records of 223 eyes from 204 patients who underwent vitrectomy for FOVH of [...] Read more.
Objectives: This study aimed to predict the unknown etiology of fundus-obscuring vitreous hemorrhage (FOVH) based on preoperative conditions using machine learning (ML) and to identify key preoperative factors. Methods: Medical records of 223 eyes from 204 patients who underwent vitrectomy for FOVH of unknown etiology between January 2012 and July 2022 were retrospectively reviewed. Preoperative data, including demographic information, systemic disease, ophthalmic history, and retinal status of the unaffected eye, were collected. The postoperatively identified etiologies of FOVH were categorized into six groups: proliferative diabetic retinopathy (PDR), retinal vein occlusion (RVO) or rupture of retinal arterial macroaneurysm, neovascular age-related macular degeneration (nAMD), retinal tear, Terson syndrome, and other causes. Four ML algorithms were trained and evaluated using seven-fold cross-validation. Results: The ML algorithms achieved mean accuracies of 76.2% for artificial neural network, 74.5% for XG-Boost, 74.4% for LASSO logistic regression, and 68.5% for decision tree. Key predictive factors commonly selected by the ML algorithms included PDR in the fellow eye, underlying diabetes mellitus, subarachnoid hemorrhage, and a history of retinal tear, RVO, or nAMD in the affected eye. Conclusions: The unknown etiology of FOVH could be predicted preoperatively with considerable accuracy by ML algorithms. Previous ophthalmic conditions in the affected eye and the condition of the fellow eye were important variables for prediction. This approach might assist in determining appropriate treatment plans. Full article
(This article belongs to the Special Issue Artificial Intelligence in Clinical Decision Support—2nd Edition)
►▼ Show Figures

Figure 1

17 pages, 1178 KiB  
Review
The Role of Dynamic Computed Tomography Angiography in Endoleak Detection and Classification After Endovascular Aneurysm Repair: A Comprehensive Review
by Alexandra Catasta, Claudio Bianchini Massoni, Davide Esposito, Sara Seitun, Giovanni Pratesi, Nicola Cicala, Antonio Freyrie and Paolo Perini
Diagnostics 2025, 15(3), 370; https://doi.org/10.3390/diagnostics15030370 - 4 Feb 2025
Viewed by 619
Abstract
Backgroud: The use of dynamic computed tomography angiography (dCTA) for the detection of endoleaks in patients who underwent endovascular repair of abdominal aortic aneurysms is gaining interest. This study aims to provide an overview of the current applications of dCTA technologies in vascular [...] Read more.
Backgroud: The use of dynamic computed tomography angiography (dCTA) for the detection of endoleaks in patients who underwent endovascular repair of abdominal aortic aneurysms is gaining interest. This study aims to provide an overview of the current applications of dCTA technologies in vascular surgery. Methods: We performed a comprehensive review by searching in the PubMed database and Cochrane Library (last search: 1 November 2024). We included studies considering endoleak investigation after endovascular aneurysm repair (EVAR). We included papers that reported the outcome of applications of dCTA, excluding case reports or very limited case series (≤4). Finally, 14 studies regarding 377 computed tomography angiographies (CTA) were included and evaluated. Results: Persistent perfusion of the aneurysm sac is the most common complication after EVAR. Imaging-based surveillance post-EVAR is essential with the aim of early detection, characterization, and localization of endoleaks to guide therapeutic intervention or follow-up. dCTA detected 36 type I endoleaks versus 16 identified with standard CTA and 138 versus 95 type II endoleaks. Conclusions: The emergence of dCTA offers a promising solution through enhanced temporal resolution, allowing the visualization of real-time flow dynamics within the aneurysmal sac essential to establishing endoleak treatment or post-EVAR follow-up. Full article
(This article belongs to the Special Issue Recent Advances in Radiomics in Medical Imaging)
►▼ Show Figures

Figure 1

13 pages, 10701 KiB  
Case Report
Characterization of Syphilitic Chorioretinitis as a White Dot Syndrome with Multimodal Imaging: Case Series
by Robert J. Contento, Neha Gupta and Mark P. Breazzano
Diagnostics 2025, 15(3), 369; https://doi.org/10.3390/diagnostics15030369 - 4 Feb 2025
Viewed by 600
Abstract
Background/Objectives: To investigate the role of multimodal imaging, including ultra-widefield fundus autofluorescence (UWFAF), in diagnosing and monitoring syphilitic chorioretinitis, focusing on the detection of placoid appearance and white dots/spots. We aim to classify syphilitic chorioretinitis as a white dot syndrome, given evident [...] Read more.
Background/Objectives: To investigate the role of multimodal imaging, including ultra-widefield fundus autofluorescence (UWFAF), in diagnosing and monitoring syphilitic chorioretinitis, focusing on the detection of placoid appearance and white dots/spots. We aim to classify syphilitic chorioretinitis as a white dot syndrome, given evident features in the context of recent case reports and previously unavailable multimodal imaging. Methods: This single-institution study was conducted as a consecutive, observational case series. Five eyes from three patients were diagnosed with syphilitic chorioretinitis using multimodal imaging, including ultra-widefield pseudocolor fundus photography and intravenous fluorescein angiography, UWFAF, and swept-source optical coherence tomography, upon laboratory results. Results: In all five eyes with serologically confirmed syphilitic chorioretinitis, UWFAF revealed hyperautofluorescent white dots and spots scattered in the fundus, a finding minimally apparent with fluorescein angiography. Two eyes did not show evidence of classic placoid lesions. The hyperautofluorescence resolved after standard neurosyphilis treatment with intravenous course of penicillin. Conclusions: The presence of dots and spots identified through UWFAF may indicate syphilitic chorioretinitis and support its classification as a white dot syndrome. Based on the presence of hyperautofluorescent placoid lesions in some but not all cases with dots and spots, this study highlights the utility of multimodal imaging, including the more recent availability of UWFAF, in diagnosing syphilitic chorioretinitis. Future research is needed to determine whether the dots and spots in syphilitic chorioretinitis represent direct spirochete infiltration or a secondary inflammatory response. Full article
(This article belongs to the Special Issue OCT and OCTA Assessment of Retinal and Choroidal Diseases)
►▼ Show Figures

Figure 1

24 pages, 954 KiB  
Review
The Promise of Infrared Spectroscopy in Liquid Biopsies for Solid Cancer Detection
by Charlotte Delrue, Sander De Bruyne and Marijn M. Speeckaert
Diagnostics 2025, 15(3), 368; https://doi.org/10.3390/diagnostics15030368 - 4 Feb 2025
Viewed by 695
Abstract
Attenuated total reflection-Fourier transform infrared (ATR-FTIR) spectroscopy has shown significant promise in the context of liquid biopsy, offering a potential tool for cancer diagnostics. Unlike traditional tissue biopsies, which may not fully capture the clonal heterogeneity of tumors, liquid biopsy reflects the dynamic [...] Read more.
Attenuated total reflection-Fourier transform infrared (ATR-FTIR) spectroscopy has shown significant promise in the context of liquid biopsy, offering a potential tool for cancer diagnostics. Unlike traditional tissue biopsies, which may not fully capture the clonal heterogeneity of tumors, liquid biopsy reflects the dynamic state of the disease and its progression more comprehensively. Biofluids such as serum and plasma are low-cost, minimally invasive diagnostic media with well-established clinical uses. This review assesses the use of ATR-FTIR spectroscopy to detect biochemical changes in biofluids linked to various malignancies, including breast, ovarian, endometrial, prostate, bladder, kidney, pancreatic, colorectal, hepatic, esophageal, gastric, lung, and brain cancers. While ATR-FTIR offers the advantages of rapid, minimally invasive detection and real-time disease monitoring, its integration into clinical practice faces challenges, particularly in terms of reproducibility due to variability in sample preparation, spectral acquisition, and data processing. The translation of ATR-FTIR into routine diagnostics will require validation through large-scale cohort studies and multicenter trials to ensure its clinical reliability and effectiveness. Full article
(This article belongs to the Section Biomedical Optics)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-163
Previous Issue
Next Issue
Back to TopTop