Journal of Imaging

Hysteroscopic lesion detection aims to automatically localize and classify lesions in hysteroscopic images, thereby facilitating intrauterine disease screening and clinical diagnosis. However, pronounced background clutter and interclass visual similarity in hysteroscopic images can impair feature discriminability. Although prevailing methods incorporate multiscale feature aggregation or local detail refinement, these operations rely on fixed processing schemes that constrain adaptive feature recalibration under varying imaging conditions, often resulting in representational instability and interclass confusion. To address this issue, we propose ADD-Net, an adaptive discriminative detection network tailored to multiclass hysteroscopic lesion detection. Specifically, a hybrid adaptive feature modulation strategy leverages an expert selection mechanism to dynamically recalibrate backbone features, improving model robustness under challenging hysteroscopic imaging conditions. A prototype confusion interaction mechanism enhances class discriminability by modeling class prototypes and interclass confusion relationships. In addition, the model uses lesion presence probabilities to improve detection stability. On the HS-CMU dataset, ADD-Net increases the three-run mean mAP@50 from 92.5% for Mamba YOLO-T to 93.3%, while reducing parameter count, computational cost, and inference latency by approximately 16.0%, 13.5%, and 33.3%, respectively. Experimental results demonstrate that ADD-Net improves detection performance while maintaining high computational efficiency, highlighting its potential for computer-aided diagnosis.

Coronary CT angiography (CCTA) may show reduced specificity in patients with extensive coronary artery calcification (CAC). We evaluated the diagnostic performance of CCTA alone versus integrated CCTA–stress myocardial CT perfusion (CTP) across different CAC burdens. In this retrospective single-center study, 102 symptomatic patients with suspected coronary artery disease underwent CCTA with stress-only dynamic CTP and were stratified into CAC 0–400 (n = 38), 401–1000 (n = 43), and >1000 (n = 21). Stress-induced hypoperfusion was defined using a prespecified relative myocardial blood flow ratio ≤ 0.85. The primary diagnostic-accuracy analysis included 68 patients with an invasive reference standard (ICA/QCA ± FFR); FFR ≤ 0.80 was used when available, whereas QCA stenosis ≥ 50% defined reference-positive disease otherwise. The remaining 34 patients had complete event-free 12-month clinical follow-up and were included exclusively in a supportive exploratory analysis. In the primary cohort, CCTA alone showed a sensitivity of 89.8%, specificity of 36.8%, and accuracy of 75.0%, compared with 87.8%, 84.2%, and 86.8%, respectively, for integrated CCTA–CTP. The integrated strategy increased specificity by 47.4 percentage points (95% CI, 24.9–69.8) and accuracy by 11.8 percentage points (95% CI, 3.1–20.4), with a significant paired difference (McNemar p = 0.021) and an NRI of 0.45 (95% CI, 0.22–0.68). In the supportive exploratory full-cohort analysis, integrated CCTA–CTP showed numerically higher accuracy across all CAC strata; however, CAC-stratified comparisons were not individually significant and these findings should be considered descriptive. Mean total radiation dose was 7.0 ± 1.4 mSv. Integrated stress CTP was associated with higher specificity and diagnostic accuracy than CCTA alone, primarily by reducing false-positive anatomical classifications.

Ovarian cancer (OC) is the second most common gynecological malignancy and remains one of the leading causes of gynecological cancer-related mortality worldwide. A major clinical challenge is the lack of an accurate and widely applicable strategy for identifying patients at high risk of malignancy at an early stage. In this context, artificial intelligence (AI) has emerged as a promising tool to improve diagnostic performance. Among AI technologies, large language models (LLMs) have recently shown considerable potential in healthcare applications. In this study, we evaluated the diagnostic performance of ChatGPT (GPT-5) in classifying 300 adnexal masses as benign or malignant and compared its performance with that of the IOTA Simple Rules, the ADNEX model, and expert subjective assessment. We also assessed ChatGPT’s ability to predict the most likely histological diagnosis for each lesion. All adnexal masses were described using the International Ovarian Tumor Analysis (IOTA) terminology, and histopathological examination served as the reference standard. Our findings showed that expert subjective assessment achieved the highest overall diagnostic performance for both benign/malignant classification (accuracy 87.3%; 95% CI, 83.0–90.9%) and prediction of the presumed histological diagnosis. ChatGPT A and ChatGPT B reached a sensitivity of 72.3% and 73.5%, a specificity of 74.5% and 75.9%, a positive predictive value of 75.2% and 76.5%, and a negative predictive value of 71.5% and 72.8%, respectively (inconclusive responses counted as misclassifications), with an overall accuracy of 73.3% and 74.7%. After adequate validation, large language models might complement existing decision-support tools for less experienced examiners, without replacing expert evaluation. Their ease of use and reliance on standardized ultrasound descriptors make them accessible to ultrasonographers with varying levels of expertise.