Purpose To classify fleck lesions and assess artificial intelligence (AI) in identifying flecks in Stargardt disease (STGD). Methods A retrospective study of 170 eyes from 85 consecutive patients with confirmed STGD. Fundus autofluorescence images were extracted, and flecks were manually outlined. A deep learning model was trained, and a hold-out testing subset was used to compare with manually identified flecks and for graders to assess. Flecks were clustered using K-means clustering. Results Of the 85 subjects, 45 were female, and the median age was 37 years (IQR 25–59). A subset of subjects (n=41) had clearly identifiable fleck lesions, and an AI was successfully trained to identify these lesions (average Dice score of 0.53, n=18). The AI segmentation had smaller (0.018 compared with 0.034 mm2, p<0.001) but more numerous flecks (75.5 per retina compared with 40.0, p<0.001), but the total size of flecks was not different. The AI model had higher sensitivity to detect flecks but resulted in more false positives. There were two clusters of flecks based on morphology: broadly, one cluster of small round flecks and another of large amorphous flecks. The per cent frequency of small round flecks negatively correlated with subject age (r=−0.31, p<0.005). Conclusions AI-based detection of flecks shows greater sensitivity than human graders but with a higher false-positive rate. With further optimisation to address current shortcomings, this approach could be used to prescreen subjects for clinical research. The feasibility and utility of quantifying fleck morphology in conjunction with AI-based segmentation as a biomarker of progression require further study. All data relevant to the study are included in the article or uploaded as supplementary information.

中文翻译：

---

使用深度学习自动识别 Stargardt 病的斑点病变可提高病变检测灵敏度并实现斑点的形态计量分析

目的 对雀斑病变进行分类并评估人工智能 (AI) 识别斯塔加特病 (STGD) 雀斑的能力。方法 对 85 名连续确诊 STGD 患者的 170 只眼睛进行回顾性研究。提取眼底自发荧光图像，并手动勾勒出斑点轮廓。训练了深度学习模型，并使用保留测试子集与手动识别的斑点进行比较并供评分者进行评估。使用 K 均值聚类对斑点进行聚类。结果 85 名受试者中，45 名女性，中位年龄为 37 岁（IQR 25-59）。一部分受试者 (n=41) 具有可清晰识别的斑点病变，并且成功训练人工智能来识别这些病变（平均 Dice 评分为 0.53，n=18）。AI 分割的斑点较小（0.018 与 0.034 mm2 相比，p<0.001），但斑点数量较多（每个视网膜 75.5 个与 40.0 相比，p<0.001），但斑点的总大小没有差异。人工智能模型检测斑点的灵敏度更高，但误报率更高。根据形态有两簇斑点：大体上，一簇是小圆形斑点，另一簇是大的无定形斑点。小圆形斑点的百分比频率与受试者年龄负相关（r=-0.31，p<0.005）。结论 基于人工智能的斑点检测比人类分级人员表现出更高的灵敏度，但假阳性率更高。通过进一步优化以解决当前的缺点，该方法可用于预筛选临床研究的受试者。量化斑点形态与基于人工智能的分割相结合作为进展生物标志物的可行性和实用性需要进一步研究。与研究相关的所有数据都包含在文章中或作为补充信息上传。