AI皮肤镜系统在俄罗斯临床验证无漏诊，准确率超88%，可辅助基层医生筛查皮肤癌。
Clinical Validation of the Melanoscope AI Mobile Dermoscopy Clinical Decision Support System
- 采用级联深度学习模型+注意力热力图分析，提升AI决策可解释性
- 176例中无假阴性，特异性达88.3%，6种模型注意力图重合度超50%
- 三区分流策略适配不同医疗资源，适合基层医院推广使用
早期发现恶性皮肤病变对预后至关重要，但俄罗斯地区皮肤科医生短缺限制了筛查覆盖面。移动式皮肤镜临床决策支持系统（CDSS）具有潜力，但模型可解释性和标准化患者分流仍是主要障碍。本研究旨在开发级联深度学习模型的定量可解释性评估方法与三区患者分流算法，并在俄罗斯奥尔洛市开展单中心前瞻性临床验证。研究采用两阶段级联分类，通过注意力图可视化（ViT和Swin用attention rollout，ConvNeXt和EfficientNetV2用Grad-CAM），以交并比（IoU）量化激活图与专家标注的一致性；在2025年6月至2026年4月的四场“黑色素瘤日”活动中进行前瞻性验证。结果：176名患者中，与专家评估一致性达88.6%；5例恶性病变均未出现假阴性（95%置信区间：47.8%-100.0%），特异性为88.3%。经病理确诊3例黑色素瘤、2例基底细胞癌，6例发育不良痣进入随访。平均IoU值（共180张图）：ViT为0.69，Swin为0.64，ConvNeXt为0.53，EfficientNetV2为0.51。分流阈值设定为：P<0.15 / 0.15-0.50 / >=0.50。结论：未出现假阴性，特异性88.3%，支持用于筛查。集成的级联分类、注意力图与IoU评估、三区分流机制，提供可复现、可解释的临床决策支持，适用于不同资源水平的医疗机构。
原文摘要 · Abstract (English)
Introduction. Early detection of malignant skin lesions is critical for prognosis, yet dermatologist shortages in Russian regions limit screening coverage. Mobile dermoscopy clinical decision support systems (CDSS) offer a promising approach, with model interpretability and standardised patient routing remaining key barriers to adoption. Aim. To develop a quantitative interpretability assessment method for cascade deep learning models and a three-zone patient routing algorithm, and to conduct a preliminary single-centre prospective clinical validation of the Melanoscope AI CDSS in Russian outpatient practice. Material and methods. Two-stage cascade classification of dermoscopic images; attention map visualisation (attention rollout for ViT and Swin; Grad-CAM for ConvNeXt and EfficientNetV2); quantitative IoU-based agreement assessment between activation maps and expert annotations; prospective single-centre validation across four "Melanoma Day" sessions (Orel, Russia, June 2025 - April 2026). Results. On 176 patients: agreement with expert assessment 88.6%; no false negatives among 5 malignant lesions (95% CI: 47.8-100.0%); specificity 88.3%. Three melanomas and two basal cell carcinomas were histologically confirmed; six dysplastic naevi placed under follow-up. Mean IoU (n=180): ViT - 0.69; Swin - 0.64; ConvNeXt - 0.53; EfficientNetV2 - 0.51. Routing thresholds: P<0.15 / 0.15-0.50 / >=0.50. Conclusion. No false negatives were observed; specificity was 88.3%, supporting screening use. The integrated cascade classification, attention map visualisation with IoU assessment, and three-zone routing provide reproducible, interpretable clinical decision support adaptable to varying resource levels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。