文献速递眼底病与葡萄膜炎

低样本深度学习在糖尿病视网膜病变诊断中的应用及缓解AI偏倚的潜力

Low-Shot Deep Learning of Diabetic Retinopathy With Potential Applications to Address Artificial Intelligence Bias in Retinal Diagnostics and Rare Ophthalmic Diseases.
PubMed 文献 · JAMA Ophthalmol · 2020-01-01

当每类训练样本充足(5120例)时两者AUC相当;但样本极少时低样本学习明显更优,提示其可用于罕见眼病或缓解AI偏倚。

要点

  • 每类5120例训练时,传统方法与低样本方法AUC相当(0.8330 vs 0.8348)。
  • 每类160例时,低样本方法AUC 0.7467优于传统方法0.6585。
  • 每类仅10例时,传统方法AUC 0.5178接近随机,低样本方法为0.5778。

核心结论

  • 当标注训练视网膜图像有限时,低样本深度学习方法对AI视网膜诊断可能有益,例如用于罕见眼病或缓解潜在AI偏倚。

研究设计与样本

  • cross-sectional study,2019年7月1日至2020年6月21日开展,比较传统与低样本糖尿病视网膜病变分类算法(需转诊 vs 不需转诊的二分类)。

主要发现

  • 每类5120例训练时,传统方法(如微调ResNet)AUC为0.8330(95%CI 0.8140-0.8520),低样本方法(自监督Deep InfoMax,记为DIM)AUC为0.8348(95%CI 0.8159-0.8537)。
  • 每类160例训练时,传统深度学习方法AUC降至0.6585(95%CI 0.6332-0.6838),低于自监督低样本方法的0.7467(95%CI 0.7239-0.7695)。
  • 每类仅10例训练时,传统方法AUC为0.5178(95%CI 0.4909-0.5447),接近随机水平;最佳低样本方法AUC为0.5778(95%CI 0.5512-0.6044)。

关键数值与推荐

  • 以受试者工作特征曲线下面积(AUC)、精确率-召回率曲线、准确率和F1分数评估不同AI算法性能。
  • 训练数据规模从每类5120例至每类10例,比较传统与低样本方法。

临床怎么用

  • 在标注视网膜图像有限时(如罕见眼病或需缓解AI偏倚),可考虑采用低样本深度学习方法进行自动视网膜诊断。

局限性

  • 研究为横断面设计,仅使用EyePACS公开数据集,未涉及其他人群或罕见眼病的直接验证。

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

IMPORTANCE: Recent studies have demonstrated the successful application of artificial intelligence (AI) for automated retinal disease diagnostics but have not addressed a fundamental challenge for deep learning systems: the current need for large, criterion standard-annotated retinal data sets for training. Low-shot learning algorithms, aiming to learn from a relatively low number of training data, may be beneficial for clinical situations involving rare retinal diseases or when addressing potential bias resulting from data that may not adequately represent certain groups for training, such as individuals older than 85 years. OBJECTIVE: To evaluate whether low-shot deep learning methods are beneficial when using small training data sets for automated retinal diagnostics. DESIGN, SETTING, AND PARTICIPANTS: This cross-sectional study, conducted from July 1, 2019, to June 21, 2020, compared different diabetic retinopathy classification algorithms, traditional and low-shot, for 2-class designations (diabetic retinopathy warranting referral vs not warranting referral). The public domain EyePACS data set was used, which originally included 88 692 fundi from 44 346 individuals. Statistical analysis was performed from February 1 to June 21, 2020. MAIN OUTCOMES AND MEASURES: The performance (95% CIs) of the various AI algorithms was measured via receiver operating curves and their area under the curve (AUC), precision recall curves, accuracy, and F1 score, evaluated for different training data sizes, ranging from 5120 to 10 samples per class. RESULTS: Deep learning algorithms, when trained with sufficiently large data sets (5120 samples per class), yielded comparable performance, with an AUC of 0.8330 (95% CI, 0.8140-0.8520) for a traditional approach (eg, fined-tuned ResNet), compared with low-shot methods (AUC, 0.8348 [95% CI, 0.8159-0.8537]) (using self-supervised Deep InfoMax [our method denoted as DIM]). However, when far fewer training images were available (n = 160), the traditional deep learning approach had an AUC decreasing to 0.6585 (95% CI, 0.6332-0.6838) and was outperformed by a low-shot method using self-supervision with an AUC of 0.7467 (95% CI, 0.7239-0.7695). At very low shots (n = 10), the traditional approach had performance close to chance, with an AUC of 0.5178 (95% CI, 0.4909-0.5447) compared with the best low-shot method (AUC, 0.5778 [95% CI, 0.5512-0.6044]). CONCLUSIONS AND RELEVANCE: These findings suggest the potential benefits of using low-shot methods for AI retinal diagnostics when a limited number of annotated training retinal images are available (eg, with rare ophthalmic diseases or when addressing potential AI bias).

来源:JAMA Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Burlina P, Paul W, Mathew P, et al. Low-Shot Deep Learning of Diabetic Retinopathy With Potential Applications to Address Artificial Intelligence Bias in Retinal Diagnostics and Rare Ophthalmic Diseases. JAMA Ophthalmol. 2020. PMID: 32880609. doi:10.1001/jamaophthalmol.2020.3269

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。