Uncertainty guided semi-supervised segmentation of retinal layers in OCT images

TL;DR

This paper introduces an uncertainty-guided semi-supervised learning framework for retinal layer segmentation in OCT images, effectively utilizing limited labeled data and unlabeled images to improve segmentation accuracy.

Contribution

It presents a novel student-teacher approach with Bayesian deep learning to leverage unlabeled data, enhancing segmentation performance in medical imaging.

Findings

Improved segmentation accuracy over fully supervised methods

Achieved performance comparable to expert annotations

Effective use of uncertainty maps for training with limited labels

Abstract

Deep convolutional neural networks have shown outstanding performance in medical image segmentation tasks. The usual problem when training supervised deep learning methods is the lack of labeled data which is time-consuming and costly to obtain. In this paper, we propose a novel uncertainty-guided semi-supervised learning based on a student-teacher approach for training the segmentation network using limited labeled samples and a large number of unlabeled images. First, a teacher segmentation model is trained from the labeled samples using Bayesian deep learning. The trained model is used to generate soft segmentation labels and uncertainty maps for the unlabeled set. The student model is then updated using the softly segmented samples and the corresponding pixel-wise confidence of the segmentation quality estimated from the uncertainty of the teacher model using a newly designed loss function. Experimental results on a retinal layer segmentation task show that the proposed method improves the segmentation performance in comparison to the fully supervised approach and is on par with the expert annotator. The proposed semi-supervised segmentation framework is a key contribution and applicable for biomedical image segmentation across various imaging modalities where access to annotated medical images is challenging