OCTAve: 2D En Face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning With Locality Augmentation
- 26 December 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 70 (6) , 1931-1942
Abstract
Objective: While the microvasculature annotation within Optical Coherence Tomography Angiography (OCTA) can be leveraged using deep-learning techniques, expensive annotation processes are required to create sufficient training data. One way to avoid the expensive annotation is to use a type of weak annotation in which only the center of the vessel is annotated. However, retaining the final segmentation quality with roughly annotated data remains a challenge. Methods: Our proposed methods, called OCTAve, provide a new way of using weak-annotation for microvasculature segmentation. Since the centerline labels are similar to scribble annotations, we attempted to solve this problem by using the scribble-based weakly-supervised learning method. Even though the initial results look promising, we found that the method could be significantly improved by adding our novel self-supervised deep supervision method based on Kullback-Liebler divergence. Results: The study on large public datasets with different annotation styles (i.e., ROSE, OCTA-500) demonstrates that our proposed method gives better quantitative and qualitative results than the baseline methods and a naive approach, with a p-value less than 0.001 on dice's coefficient and a lot fewer artifacts. Conclusion: The segmentation results are both qualitatively and quantitatively superior to baseline weakly-supervised methods when using scribble-based weakly-supervised learning augmented with self-supervised deep supervision, with an average drop in segmentation performance of less than 10%. Significance: This work gives a new perspective on how weakly-supervised learning can be used to reduce the cost of annotating microvasculature, which can make the annotating process easier and reduce the amount of work for domain experts.Keywords
All Related Versions
Funding Information
- PTT Public Company Limited
- SCB Public Company Limited
- National Research Council of Thailand (N41A640131)
This publication has 37 references indexed in Scilit:
- Automatic blood vessels segmentation based on different retinal maps from OCTA scansComputers in Biology and Medicine, 2017
- Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images2017
- Constrained Deep Weak Supervision for Histopathology Image SegmentationIEEE Transactions on Medical Imaging, 2017
- Detailed Vascular Anatomy of the Human Retina by Projection-Resolved Optical Coherence Tomography AngiographyScientific Reports, 2017
- Intensity and Compactness Enabled Saliency Estimation for Leakage Detection in Diabetic and Malarial RetinopathyIEEE Transactions on Medical Imaging, 2016
- ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation2016
- Automated Vessel Segmentation Using Infinite Perimeter Active Contour Model with Hybrid Region Information with Application to Retinal ImagesIEEE Transactions on Medical Imaging, 2015
- Trainable COSFIRE filters for vessel delineation with application to retinal imagesMedical Image Analysis, 2015
- A fast parallel algorithm for thinning digital patternsCommunications of the ACM, 1984
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951