Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation

2020/03/31 by Dwarikanath Mahapatra, Behzad Bozorgtabar, Mahapatra, Dwarikanath +6 · 13 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · Medicine · #AI in cancer detection #Artificial intelligence #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Image segmentation #Optical coherence tomography #Pattern recognition (psychology) #Retinal Imaging and Analysis #Robustness (evolution) #Scale-space segmentation #Segmentation #cs.CV #eess.IV #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2003.14119

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2020/03/31 · openalex created_date 2020/04/10 · arxiv created 2020/04/25 · arxiv updated 2020/04/28 · openalex updated_date 2026/08/06

Abstract

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.

Citations

• Adam: A Method for Stochastic Optimization
• Consensus Based Medical Image Segmentation Using Semi-Supervised Learning And Graph Cuts
• Retinal Vasculature Segmentation Using Local Saliency Maps and Generative Adversarial Networks For Image Super Resolution
• Data Augmentation Generative Adversarial Networks
• Chest X-rays Classification: A Multi-Label and Fine-Grained Problem
• Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes
• GAN Based Medical Image Registration

Cited by

• CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysis

Related

• SD-RetinaNet: Topologically Constrained Semi-Supervised Retinal Lesion and Layer Segmentation in OCT
• Deep Learning based Retinal OCT Segmentation
• Retinal Image Segmentation with Small Datasets
• Y-Net: A Spatiospectral Dual-Encoder Networkfor Medical Image Segmentation
• Segmentation-guided Domain Adaptation and Data Harmonization of Multi-device Retinal Optical Coherence Tomography using Cycle-Consistent Generative Adversarial Networks