arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.05280cs.CV
收藏

ContrastDiagnosis:利用对比学习提升肺结节诊断的可解释性

ContrastDiagnosis: Enhancing Interpretability in Lung Nodule Diagnosis Using Contrastive Learning

East China Normal University(华东师范大学);NVIDIA Corp.(英伟达公司);Nagoya University(名古屋大学);National Institute of Informatics(信息学研究所);The First Affiliated Hospital of Nanjing Medical University(南京医科大学第一附属医院)

Chenglong Wang, Yinqiao Yi, Yida Wang, Chengxiu Zhang, Yun Liu, Kensaku Mori, Mei Yuan, Guang Yang

AI总结:

针对AI诊断模型黑箱特性阻碍临床部署的问题,提出融合对比学习的可解释诊断框架ContrastDiagnosis,通过案例推理依据和相似区域高亮提升透明度,在肺结节诊断中实现0.977的AUC且兼具高可解释性。

摘要:

随着深度学习的持续发展,越来越多的AI模型性能已经超越了人类临床从业者的水平。然而,AI诊断产品在实际临床实践中的普及度仍远低于预期。造成这一差距的一个关键原因是AI模型所谓的“黑箱”特性。临床医生对黑箱模型的不信任直接阻碍了AI产品的临床部署。为应对这一挑战,我们提出了ContrastDiagnosis,这是一个简洁却有效的可解释诊断框架。该框架旨在为深度学习模型引入内在透明度并提供丰富的事后可解释性,使其更适用于临床医学诊断。ContrastDiagnosis融入了对比学习机制,以提供基于案例推理的诊断依据,提升模型透明度,同时还通过高亮相似区域来提供事后可解释性。该方法在保持高透明度和可解释性的同时,取得了较高的诊断准确率,AUC达0.977。

英文摘要:

With the ongoing development of deep learning, an increasing number of AI models have surpassed the performance levels of human clinical practitioners. However, the prevalence of AI diagnostic products in actual clinical practice remains significantly lower than desired. One crucial reason for this gap is the so-called `black box' nature of AI models. Clinicians' distrust of black box models has directly hindered the clinical deployment of AI products. To address this challenge, we propose ContrastDiagnosis, a straightforward yet effective interpretable diagnosis framework. This framework is designed to introduce inherent transparency and provide extensive post-hoc explainability for deep learning model, making them more suitable for clinical medical diagnosis. ContrastDiagnosis incorporates a contrastive learning mechanism to provide a case-based reasoning diagnostic rationale, enhancing the model's transparency and also offers post-hoc interpretability by highlighting similar areas. High diagnostic accuracy was achieved with AUC of 0.977 while maintain a high transparency and explainability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑