Multi-task Learning for Optical Coherence Tomography Angiography (OCTA) Vessel Segmentation
This work addresses the time-consuming task of manual segmentation for OCTA images, which is important for diagnosing retinal diseases, but it appears incremental as it builds on multi-task learning with specific enhancements.
The paper tackled the problem of automated vessel segmentation in Optical Coherence Tomography Angiography (OCTA) images to reduce manual labor, and the proposed OCTA-MTL method achieved superior segmentation performance compared to baseline methods on the ROSE-2 dataset.
Optical Coherence Tomography Angiography (OCTA) is a non-invasive imaging technique that provides high-resolution cross-sectional images of the retina, which are useful for diagnosing and monitoring various retinal diseases. However, manual segmentation of OCTA images is a time-consuming and labor-intensive task, which motivates the development of automated segmentation methods. In this paper, we propose a novel multi-task learning method for OCTA segmentation, called OCTA-MTL, that leverages an image-to-DT (Distance Transform) branch and an adaptive loss combination strategy. The image-to-DT branch predicts the distance from each vessel voxel to the vessel surface, which can provide useful shape prior and boundary information for the segmentation task. The adaptive loss combination strategy dynamically adjusts the loss weights according to the inverse of the average loss values of each task, to balance the learning process and avoid the dominance of one task over the other. We evaluate our method on the ROSE-2 dataset its superiority in terms of segmentation performance against two baseline methods: a single-task segmentation method and a multi-task segmentation method with a fixed loss combination.