用对抗样本解释深度学习青光眼决策的原理
该研究在1653名健康筛查参与者中,用6430张眼底图像训练了针对可转诊青光眼、杯盘比增大、盘沿变窄和视网膜神经纤维层缺损的深度学习模型,并比较对抗样本与GradCAM两种解释方法。结果显示对抗样本在位置可解释性和原理可解释性评分上均显著优于GradCAM,可能帮助临床医生更好理解模型决策依据。
要点
- 对抗样本解释在位置和原理可解释性评分上均显著优于GradCAM。
- 四个深度学习模型在0.90特异性下AUC为0.79至0.99,敏感度为0.55至1.00。
- 生成的对抗样本显示出有效的临床特征改变。
核心结论
- 对抗样本解释比传统热力图方法GradCAM提供更好的可解释性。
- 对抗样本解释可能帮助医疗专业人员更清晰地理解深度学习模型用于临床决策的原理。
研究设计与样本
- 研究为对深度学习模型解释方法的评估,纳入1653名健康筛查参与者。
- 使用6430张视网膜眼底图像训练可转诊青光眼、杯盘比增大、盘沿变窄和视网膜神经纤维层缺损的深度学习模型。
- 针对400只病理和健康眼生成对抗样本和GradCAM解释调查,由经过委员会培训的青光眼专家评分,采用配对Wilcoxon符号秩检验比较。
主要发现
- 可转诊青光眼、杯盘比增大、盘沿变窄和视网膜神经纤维层缺损模型的AUC分别为0.90、0.99、0.95和0.79。
- 在0.90特异性下,上述四个模型的敏感度分别为0.79、1.00、0.82和0.55。
- 对抗样本的位置可解释性评分为3.94 ± 1.33,GradCAM为2.55 ± 1.24(满分5分)。
- 对抗样本的原理可解释性评分为3.97 ± 1.31,GradCAM为2.10 ± 1.25。
- 对抗样本提供的可解释性显著优于GradCAM。
临床怎么用
- 临床医生可借助对抗样本解释更直观地理解深度学习模型对青光眼相关发现的决策依据。
- 在评估人工智能辅助青光眼诊断时,可优先考虑采用对抗样本解释方法以增强对模型结论的信任。
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: To illustrate what is inside the so-called black box of deep learning models (DLMs) so that clinicians can have greater confidence in the conclusions of artificial intelligence by evaluating adversarial explanation on its ability to explain the rationale of DLM decisions for glaucoma and glaucoma-related findings. Adversarial explanation generates adversarial examples (AEs), or images that have been changed to gain or lose pathologic characteristic-specific traits, to explain the DLM's rationale. DESIGN: Evaluation of explanation methods for DLMs. PARTICIPANTS: Health screening participants (n = 1653) at the Seoul National University Hospital Health Promotion Center, Seoul, Republic of Korea. METHODS: We trained DLMs for referable glaucoma (RG), increased cup-to-disc ratio (ICDR), disc rim narrowing (DRN), and retinal nerve fiber layer defect (RNFLD) using 6430 retinal fundus images. Surveys consisting of explanations using AE and gradient-weighted class activation mapping (GradCAM), a conventional heatmap-based explanation method, were generated for 400 pathologic and healthy patient eyes. For each method, board-trained glaucoma specialists rated location explainability, the ability to pinpoint decision-relevant areas in the image, and rationale explainability, the ability to inform the user on the model's reasoning for the decision based on pathologic features. Scores were compared by paired Wilcoxon signed-rank test. MAIN OUTCOME MEASURES: Area under the receiver operating characteristic curve (AUC), sensitivities, and specificities of DLMs; visualization of clinical pathologic changes of AEs; and survey scores for locational and rationale explainability. RESULTS: The AUCs were 0.90, 0.99, 0.95, and 0.79 and sensitivities were 0.79, 1.00, 0.82, and 0.55 at 0.90 specificity for RG, ICDR, DRN, and RNFLD DLMs, respectively. Generated AEs showed valid clinical feature changes, and survey results for location explainability were 3.94 ± 1.33 and 2.55 ± 1.24 using AEs and GradCAMs, respectively, of a possible maximum score of 5 points. The scores for rationale explainability were 3.97 ± 1.31 and 2.10 ± 1.25 for AEs and GradCAM, respectively. Adversarial example provided significantly better explainability than GradCAM. CONCLUSIONS: Adversarial explanation increased the explainability over GradCAM, a conventional heatmap-based explanation method. Adversarial explanation may help medical professionals understand more clearly the rationale of DLMs when using them for clinical decisions.
引用
- Chang J, Lee J, Ha A, et al. Explaining the Rationale of Deep Learning Glaucoma Decisions with Adversarial Examples. Ophthalmology. 2020. PMID: 32598951. doi:10.1016/j.ophtha.2020.06.036
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。