Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation
This work addresses the challenge of robust segmentation for retinal OCT images in medical diagnosis, representing an incremental improvement over prior GAN-based methods by incorporating geometric relations.
The paper tackles the problem of limited robustness in medical image segmentation due to conventional data augmentation by proposing a method that jointly encodes geometric relationships to generate diverse synthetic images, resulting in improved segmentation performance on the RETOUCH dataset.
Medical image segmentation is an important task for computer aided diagnosis. Pixelwise manual annotations of large datasets require high expertise and is time consuming. Conventional data augmentations have limited benefit by not fully representing the underlying distribution of the training set, thus affecting model robustness when tested on images captured from different sources. Prior work leverages synthetic images for data augmentation ignoring the interleaved geometric relationship between different anatomical labels. We propose improvements over previous GAN-based medical image synthesis methods by jointly encoding the intrinsic relationship of geometry and shape. Latent space variable sampling results in diverse generated images from a base image and improves robustness. Given those augmented images generated by our method, we train the segmentation network to enhance the segmentation performance of retinal optical coherence tomography (OCT) images. The proposed method outperforms state-of-the-art segmentation methods on the public RETOUCH dataset having images captured from different acquisition procedures. Ablation studies and visual analysis also demonstrate benefits of integrating geometry and diversity.