A Knowledge Distillation-Based Approach to Enhance Transparency of Classifier Models
This work addresses the need for explainability in medical AI to help clinicians trust decision-making processes, though it appears incremental as it builds on existing Knowledge Distillation methods.
The authors tackled the problem of enhancing transparency in AI models for medical image analysis by proposing a Knowledge Distillation-based approach that simplifies CNN architectures while retaining data features, resulting in reduced network layers and faster interpretability analysis with remarkable test set performance.
With the rapid development of artificial intelligence (AI), especially in the medical field, the need for its explainability has grown. In medical image analysis, a high degree of transparency and model interpretability can help clinicians better understand and trust the decision-making process of AI models. In this study, we propose a Knowledge Distillation (KD)-based approach that aims to enhance the transparency of the AI model in medical image analysis. The initial step is to use traditional CNN to obtain a teacher model and then use KD to simplify the CNN architecture, retain most of the features of the data set, and reduce the number of network layers. It also uses the feature map of the student model to perform hierarchical analysis to identify key features and decision-making processes. This leads to intuitive visual explanations. We selected three public medical data sets (brain tumor, eye disease, and Alzheimer's disease) to test our method. It shows that even when the number of layers is reduced, our model provides a remarkable result in the test set and reduces the time required for the interpretability analysis.