Generative Image Translation for Data Augmentation in Colorectal Histopathology Images
This addresses data scarcity for rare polyp classes in colorectal cancer diagnosis, but it is incremental as it applies an existing method to a specific domain.
The paper tackled data imbalance in colorectal histopathology images by using CycleGANs to generate synthetic polyp images from normal mucosa, which improved the AUC of a CNN for detecting sessile serrated adenomas by over 10%.
We present an image translation approach to generate augmented data for mitigating data imbalances in a dataset of histopathology images of colorectal polyps, adenomatous tumors that can lead to colorectal cancer if left untreated. By applying cycle-consistent generative adversarial networks (CycleGANs) to a source domain of normal colonic mucosa images, we generate synthetic colorectal polyp images that belong to diagnostically less common polyp classes. Generated images maintain the general structure of their source image but exhibit adenomatous features that can be enhanced with our proposed filtration module, called Path-Rank-Filter. We evaluate the quality of generated images through Turing tests with four gastrointestinal pathologists, finding that at least two of the four pathologists could not identify generated images at a statistically significant level. Finally, we demonstrate that using CycleGAN-generated images to augment training data improves the AUC of a convolutional neural network for detecting sessile serrated adenomas by over 10%, suggesting that our approach might warrant further research for other histopathology image classification tasks.