自动化机器学习在超广角伪彩眼底图像中分类视网膜病变的准确性
本研究评估自动化机器学习(AutoML)在超广角伪彩眼底图像中区分视网膜静脉阻塞(RVO)、视网膜色素变性(RP)和视网膜脱离(RD)与正常眼底的判别性能。两位无编程经验的眼科医生使用公开数据集(2137张标注图像)设计AutoML模型,并与文献中定制深度学习模型比较。AutoML二分类模型诊断性能高,与定制模型总体相当;多分类模型AUPRC为0.876,敏感度77.93%,阳性预测值82.59%。
要点
- 无编程经验眼科医生可设计AutoML模型,在超广角图像中检测RVO、RP和RD。
- 二分类AutoML模型AUPRC 0.921-1,敏感度84.91%-89.77%,特异度78.72%-100%。
- 多分类模型对RD的敏感度79.55%、特异度96.80%,性能与定制模型可比。
核心结论
- 无编程经验眼科医生创建的AutoML模型能在超广角图像中检测RVO、RP和RD,诊断准确性很好。
- AutoML模型性能与AI专家定制深度学习模型在RVO和RP上可比,但在RD上不可比。
研究设计与样本
- 两位无编程经验眼科医生使用公开图像数据集(2137张标注图像)设计AutoML模型。
- 数据经低质量和误标注审查后上传至Google Cloud AutoML Vision平台进行训练和测试。
- 设计了多个二分类模型区分RVO、RP、RD与正常眼底,并与文献中定制模型比较;另设计多分类模型检测RVO、RP和RD。
- 生成显著性图评估模型可解释性。
主要发现
- 二分类AutoML模型在区分RVO、RP、RD与正常眼底任务中表现出高诊断性能,与定制深度学习模型总体可比(AUPRC 0.921-1,敏感度84.91%-89.77%,特异度78.72%-100%)。
- 多分类AutoML模型AUPRC为0.876,敏感度77.93%,阳性预测值82.59%。
- 多分类模型各标签敏感度和特异度分别为:正常眼底(91.49%,86.75%)、RVO(83.02%,92.50%)、RP(72.00%,100%)、RD(79.55%,96.80%)。
关键数值与推荐
- 二分类AutoML模型:AUPRC 0.921-1,敏感度84.91%-89.77%,特异度78.72%-100%。
- 多分类AutoML模型:AUPRC 0.876,敏感度77.93%,阳性预测值82.59%。
- 多分类模型各标签敏感度和特异度:正常眼底(91.49%,86.75%)、RVO(83.02%,92.50%)、RP(72.00%,100%)、RD(79.55%,96.80%)。
临床怎么用
- 眼科医生无需编程经验即可利用AutoML平台构建视网膜病变分类模型,辅助超广角眼底图像判读。
- AutoML模型对RVO、RP和RD具有较高诊断准确性,但RD性能不及定制模型,临床应用中需注意病种差异。
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
AIMS: Automated machine learning (AutoML) is a novel tool in artificial intelligence (AI). This study assessed the discriminative performance of AutoML in differentiating retinal vein occlusion (RVO), retinitis pigmentosa (RP) and retinal detachment (RD) from normal fundi using ultra-widefield (UWF) pseudocolour fundus images. METHODS: Two ophthalmologists without coding experience carried out AutoML model design using a publicly available image data set (2137 labelled images). The data set was reviewed for low-quality and mislabeled images and then uploaded to the Google Cloud AutoML Vision platform for training and testing. We designed multiple binary models to differentiate RVO, RP and RD from normal fundi and compared them to bespoke models obtained from the literature. We then devised a multiclass model to detect RVO, RP and RD. Saliency maps were generated to assess the interpretability of the model. RESULTS: The AutoML models demonstrated high diagnostic properties in the binary classification tasks that were generally comparable to bespoke deep-learning models (area under the precision-recall curve (AUPRC) 0.921-1, sensitivity 84.91%-89.77%, specificity 78.72%-100%). The multiclass AutoML model had an AUPRC of 0.876, a sensitivity of 77.93% and a positive predictive value of 82.59%. The per-label sensitivity and specificity, respectively, were normal fundi (91.49%, 86.75%), RVO (83.02%, 92.50%), RP (72.00%, 100%) and RD (79.55%,96.80%). CONCLUSION: AutoML models created by ophthalmologists without coding experience can detect RVO, RP and RD in UWF images with very good diagnostic accuracy. The performance was comparable to bespoke deep-learning models derived by AI experts for RVO and RP but not for RD.
引用
- Antaki F, Coussa RG, Kahwati G, et al. Accuracy of automated machine learning in classifying retinal pathologies from ultra-widefield pseudocolour fundus images. Br J Ophthalmol. 2021. PMID: 34344669. doi:10.1136/bjophthalmol-2021-319030
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。