DeepSeeNet:基于彩色眼底照片自动分类患者水平年龄相关性黄斑变性严重程度的深度学习模型
DeepSeeNet是一个深度学习模型,利用双眼彩色眼底照片按AREDS简化严重程度量表(0-5分)自动分类患者。患者水平分类准确率0.671、kappa 0.558,优于视网膜专科医生的0.599和0.467;检测大玻璃膜疣、色素异常和晚期AMD的AUC分别为0.94、0.93和0.97。
要点
- DeepSeeNet模拟人工分级流程,先检测每只眼的AMD风险因素再计算患者水平严重程度评分。
- 患者水平分类准确率和kappa均优于视网膜专科医生。
- 检测大玻璃膜疣和色素异常优于专科医生,但检测晚期AMD的准确率和kappa低于专科医生。
核心结论
- DeepSeeNet通过模拟人工分级过程,在基于AREDS简化严重程度量表的患者AMD风险分类中表现出高准确性和更高透明度。
- 深度学习有潜力辅助和增强AMD患者的临床决策,如早期AMD检测和晚期AMD风险预测。
研究设计与样本
- 开发深度学习模型DeepSeeNet,使用双眼彩色眼底照片自动按AREDS简化严重程度量表(0-5分)分类患者。
- 金标准标签来自阅片中心分级。
主要发现
- 患者水平分类:DeepSeeNet准确率0.671、kappa 0.558,优于视网膜专科医生的准确率0.599、kappa 0.467。
- 检测大玻璃膜疣AUC 0.94,检测色素异常AUC 0.93,检测晚期AMDAUC 0.97。
- 检测大玻璃膜疣:DeepSeeNet准确率0.742 vs. 专科医生0.696,kappa 0.601 vs. 0.517。
- 检测色素异常:DeepSeeNet准确率0.890 vs. 专科医生0.813,kappa 0.723 vs. 0.535。
- 检测晚期AMD:DeepSeeNet准确率0.967 vs. 专科医生0.973,kappa 0.663 vs. 0.754。
关键数值与推荐
- AREDS简化严重程度量表评分为0-5分,用于患者水平AMD严重程度分类。
- DeepSeeNet检测大玻璃膜疣的AUC为0.94,检测色素异常的AUC为0.93,检测晚期AMD的AUC为0.97。
- 患者水平分类准确率0.671、kappa 0.558;视网膜专科医生准确率0.599、kappa 0.467。
临床怎么用
- 可基于双眼彩色眼底照片自动输出患者水平AMD严重程度评分,辅助早期AMD检测和晚期AMD风险预测。
- 模型公开可用(https://github.com/ncbi-nlp/DeepSeeNet),便于临床验证和进一步研究。
局限性
- 检测晚期AMD的准确率和kappa低于视网膜专科医生。
- 训练和测试数据来自AREDS纵向随访队列,外部泛化性未在原文中报告。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: In assessing the severity of age-related macular degeneration (AMD), the Age-Related Eye Disease Study (AREDS) Simplified Severity Scale predicts the risk of progression to late AMD. However, its manual use requires the time-consuming participation of expert practitioners. Although several automated deep learning systems have been developed for classifying color fundus photographs (CFP) of individual eyes by AREDS severity score, none to date has used a patient-based scoring system that uses images from both eyes to assign a severity score. DESIGN: DeepSeeNet, a deep learning model, was developed to classify patients automatically by the AREDS Simplified Severity Scale (score 0-5) using bilateral CFP. PARTICIPANTS: DeepSeeNet was trained on 58 402 and tested on 900 images from the longitudinal follow-up of 4549 participants from AREDS. Gold standard labels were obtained using reading center grades. METHODS: DeepSeeNet simulates the human grading process by first detecting individual AMD risk factors (drusen size, pigmentary abnormalities) for each eye and then calculating a patient-based AMD severity score using the AREDS Simplified Severity Scale. MAIN OUTCOME MEASURES: Overall accuracy, specificity, sensitivity, Cohen's kappa, and area under the curve (AUC). The performance of DeepSeeNet was compared with that of retinal specialists. RESULTS: DeepSeeNet performed better on patient-based classification (accuracy = 0.671; kappa = 0.558) than retinal specialists (accuracy = 0.599; kappa = 0.467) with high AUC in the detection of large drusen (0.94), pigmentary abnormalities (0.93), and late AMD (0.97). DeepSeeNet also outperformed retinal specialists in the detection of large drusen (accuracy 0.742 vs. 0.696; kappa 0.601 vs. 0.517) and pigmentary abnormalities (accuracy 0.890 vs. 0.813; kappa 0.723 vs. 0.535) but showed lower performance in the detection of late AMD (accuracy 0.967 vs. 0.973; kappa 0.663 vs. 0.754). CONCLUSIONS: By simulating the human grading process, DeepSeeNet demonstrated high accuracy with increased transparency in the automated assignment of individual patients to AMD risk categories based on the AREDS Simplified Severity Scale. These results highlight the potential of deep learning to assist and enhance clinical decision-making in patients with AMD, such as early AMD detection and risk prediction for developing late AMD. DeepSeeNet is publicly available on https://github.com/ncbi-nlp/DeepSeeNet.
引用
- Peng Y, Dharssi S, Chen Q, et al. DeepSeeNet: A Deep Learning Model for Automated Classification of Patient-based Age-related Macular Degeneration Severity from Color Fundus Photographs. Ophthalmology. 2018. PMID: 30471319. doi:10.1016/j.ophtha.2018.11.015
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。