ContrastDiagnosis: Enhancing Interpretability in Lung Nodule Diagnosis Using Contrastive Learning
This addresses the distrust of black-box AI models among clinicians, potentially improving clinical deployment, though it appears incremental as it builds on existing contrastive learning methods for interpretability.
The paper tackled the problem of AI model interpretability in lung nodule diagnosis by proposing ContrastDiagnosis, a framework using contrastive learning to enhance transparency and post-hoc explainability, achieving a diagnostic AUC of 0.977.
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.