DualDoctor: A Mutual Learning Method with Dynamic Knowledge Transfer and Class-Level Alignment for Classifying Medical Images

Mutual learning that can be seen as a derivative method of knowledge distillation takes advantages of the collective capabilities of multiple neural networks to promote the precision and stability of classification outcomes, and achieved great success in the field of computer vision. Recently, mutual learning has been exploited in the task of medical image classification. However, medical images belonging to different classes may be very similar, which may affect the classification performance of the mutual learning based methods. In this paper, we propose a novel mutual learning model, named DualDoctor, especially for the classification of medical images. DualDoctor is built by embedding the channel and spatial feature-based dynamic knowledge transfer module and the logit-based class alignment module into the vanilla mutual learning framework. The dynamic knowledge transfer module makes two sub-models sharing the critical information at the feature level, while the logit-based class alignment module enforces two sub-models to absorb the class correlation knowledge from each other at the logit level. Therefore, DualDoctor can adapt well to the characteristics of medical images so as to make more accurate classifications. The evaluation results on two public datasets, BUSI and ISIC2018, indicate that the proposed DualDoctor model performs better than the comparison methods in medical image classification tasks.