Abstract
Accurate computer-assisted diagnosis using Convolutional Neural Networks (CNNs) requires large-scale annotated training data, associated with expert physicians’ time-consuming labor; thus, Data Augmentation (DA) using Generative Adversarial Networks (GANs) is essential in Medical Imaging, since they can synthesize additional annotated training data to handle small and fragmented medical images from various scanners; those images are realistic but completely different from the original ones, filling the data lack in the real image distribution. As a tutorial, this paper introduces background on GAN-based Medical Image Augmentation, along with tricks to achieve high classification/object detection/segmentation performance using them, based on our empirical experience and related work. Moreover, we show our first GAN-based DA work using automatic bounding box annotation, for robust CNN-based brain metastases detection on 256 x 256 MR images; GAN-based DA can boost 10% sensitivity in diagnosis with a clinically acceptable amount of additional False Positives, even with highly-rough and inconsistent bounding boxes.
Abstract (translated by Google)
URL
http://arxiv.org/abs/1904.00838