Weakly-supervised Generative Adversarial Networks for medical image classification
This addresses the problem of data scarcity in medical imaging for researchers and practitioners, but it is incremental as it builds on existing weakly-supervised and GAN techniques.
The paper tackles medical image classification with limited labeled data by proposing WSGAN, a weakly-supervised method that generates fake images and uses pseudo-labeling, achieving an 11% accuracy improvement over MIXMATCH on the OCT dataset with 100 labeled and 1000 unlabeled images.
Weakly-supervised learning has become a popular technology in recent years. In this paper, we propose a novel medical image classification algorithm, called Weakly-Supervised Generative Adversarial Networks (WSGAN), which only uses a small number of real images without labels to generate fake images or mask images to enlarge the sample size of the training set. First, we combine with MixMatch to generate pseudo labels for the fake images and unlabeled images to do the classification. Second, contrastive learning and self-attention mechanism are introduced into the proposed problem to enhance the classification accuracy. Third, the problem of mode collapse is well addressed by cyclic consistency loss. Finally, we design global and local classifiers to complement each other with the key information needed for classification. The experimental results on four medical image datasets show that WSGAN can obtain relatively high learning performance by using few labeled and unlabeled data. For example, the classification accuracy of WSGAN is 11% higher than that of the second-ranked MIXMATCH with 100 labeled images and 1000 unlabeled images on the OCT dataset. In addition, we also conduct ablation experiments to verify the effectiveness of our algorithm.