A Parameterized Generative Adversarial Network Using Cyclic Projection for Explainable Medical Image Classification
This work addresses data insufficiency and uncertainty in medical image classification for small-scale datasets, representing an incremental improvement.
The paper tackles the problem of generating uncertain synthetic images in small-scale medical datasets by proposing a parameterized GAN (ParaGAN) that controls changes among domains and highlights attention regions, resulting in consistent outperformance over existing augmentation methods with explainable classification on two small-scale medical datasets.
Although current data augmentation methods are successful to alleviate the data insufficiency, conventional augmentation are primarily intra-domain while advanced generative adversarial networks (GANs) generate images remaining uncertain, particularly in small-scale datasets. In this paper, we propose a parameterized GAN (ParaGAN) that effectively controls the changes of synthetic samples among domains and highlights the attention regions for downstream classification. Specifically, ParaGAN incorporates projection distance parameters in cyclic projection and projects the source images to the decision boundary to obtain the class-difference maps. Our experiments show that ParaGAN can consistently outperform the existing augmentation methods with explainable classification on two small-scale medical datasets.