DK-Consistency: A Domain Knowledge Guided Consistency Regularization Method for Semi-supervised Breast Cancer Diagnosis

The performance of deep learning models generally relies on large and high-quality labeled datasets. However, in medical domain, as labeling process is much more laborious and time-consuming, most medical datasets are much smaller compared with natural image datasets. To mitigate this weakness, recent researches in medical image analysis adopt semi-supervised learning methods, especially consistency regularization methods to learn from a large amount of unlabeled medical data. However, as these semi-supervised learning methods are originally designed for tasks of natural images, specific properties of medical domain are not fully investigated and utilized. In this paper, we present DK-Consistency, a domain knowledge guided consistency regularization method for semi-supervised breast cancer diagnosis in ultrasound images. In DK-Consistency, domain knowledge of medical doctors is first incorporated into the generation process of perturbed samples for each unlabeled image. Then consistency regularization is adopted to force the model to make consistent predictions for unlabeled images and their perturbed samples. Extensive experiments demonstrate that, by injecting domain knowledge, DK-Consistency significantly improves the diagnostic performance of breast cancer and outperforms many state-of the-art semi-supervised methods.