Diagnostics

Background/Objectives: The aim of this study was to evaluate the cycle threshold (Ct) values of self-collected vaginal samples as a triage method to colposcopy for high-risk (hr) HPV-positive women. Methods: We analyzed data from GRECOSELF, a nationwide observational cross-sectional study on HPV primary cervical cancer screening in Greece. Self-collected vaginal samples were tested with the cobas^® HPV test (Roche^® Molecular Systems, Pleasanton, CA, USA). The Ct value, i.e., the number of cycles needed until DNA amplification occurs exponentially in a PCR, reflects the viral load, and it was evaluated as a triage method to colposcopy for hrHPV-positive women. Results: For CIN2 and more advanced lesions, the Ct value, as a dichotomous variable at a cut-off of 29.7, had 54.8% (95%CI: 38.7–70.2) sensitivity, 35.4% (23.9–48.2) Positive Predictive Value (PPV), 74.2% (66.8–80.8) specificity, and 86.4% (73.6–91.6) Negative Predictive Value (NPV) for HPV16/18, while for other hrHPV types, sensitivity was 26.7% (12.3–45.9), PPV 6.7% (2.9–12.8), specificity 78.8% (75.1–82.2), and NPV 95.0% (92.5–96.8). For CIN3 and more advanced lesions, the NPV for non-HPV16/18 was 97.9 (96.1–99.1). Conclusions: For self-collected vaginal samples of hrHPV-positive women, the Ct value may be used as a triage method to colposcopy. As Ct values inversely reflect the viral loads, they are lower in high-grade CIN and/or carcinoma.

Background/Objectives: Demodex mites are a common yet underdiagnosed cause of ocular surface diseases, including blepharitis and meibomian gland dysfunction (MGD). Traditional diagnosis via microscopic examination is labor-intensive and time-consuming. This study aimed to develop a deep learning-based system for the automated detection and quantification of Demodex mites from microscopic eyelash images. Methods: We collected 1610 microscopic images of eyelashes from patients clinically suspected to have ocular demodicosis. After quality screening, 665 images with visible Demodex features were annotated and processed. Two deep learning models, YOLOv11 and RT-DETR, were trained and evaluated using standard metrics. Grad-CAM visualization was applied to confirm model attention and feature localization. Results: Both YOLO and RT-DETR models were able to detect Demodex mites in our microscopic images. The YOLOv11 boxing model revealed an average precision of 0.9441, sensitivity of 0.9478, and F1-score of 0.9459 in our detection system, while the RT-DETR model showed an average precision of 0.7513, sensitivity of 0.9389, and F1-score of 0.8322. Moreover, Grad-CAM visualization confirmed the models’ focus on relevant mite features. Quantitative analysis enabled consistent mite counting across overlapping regions, with a confidence level of 0.4–0.8, confirming stable enumeration performance. Conclusions: The proposed artificial intelligence (AI)-based detection system demonstrates strong potential for assisting ophthalmologists in diagnosing ocular demodicosis efficiently and accurately, reducing reliance on manual microscopy and enabling faster clinical decision making.

Corneal diseases are a leading cause of blindness worldwide, although their early detection remains challenging due to subtle clinical presentations. Recent advances in artificial intelligence (AI) have shown promising diagnostic performance for anterior segment disorders. This narrative review summarizes current applications of AI in the detection of corneal conditions—including keratoconus (KC), dry eye disease (DED), infectious keratitis (IK), pterygium, Fuchs endothelial corneal dystrophy (FECD), and corneal transplantation. Many AI models report high accuracy on test datasets, comparable to, and in some studies exceeding, that of junior ophthalmologists. In addition to detection, AI systems can automate image labeling and support education and patient home monitoring. These findings highlight the potential of AI to improve early management and standardized classification of corneal diseases, supporting clinical practice and patient self-care.