VesselShot: Few-shot learning for cerebral blood vessel segmentation

TL;DR

VesselShot introduces a few-shot learning method for cerebral blood vessel segmentation that reduces the need for extensive labeled data, demonstrating promising results on a public dataset.

Contribution

The paper presents VesselShot, a novel few-shot learning approach tailored for cerebrovascular segmentation, addressing data scarcity and annotation challenges in medical imaging.

Findings

Achieved a mean Dice coefficient of 0.62 on the TubeTK dataset.

Reduces reliance on large annotated datasets for vessel segmentation.

Demonstrates effectiveness of few-shot learning in medical image analysis.

Abstract

Angiography is widely used to detect, diagnose, and treat cerebrovascular diseases. While numerous techniques have been proposed to segment the vascular network from different imaging modalities, deep learning (DL) has emerged as a promising approach. However, existing DL methods often depend on proprietary datasets and extensive manual annotation. Moreover, the availability of pre-trained networks specifically for medical domains and 3D volumes is limited. To overcome these challenges, we propose a few-shot learning approach called VesselShot for cerebrovascular segmentation. VesselShot leverages knowledge from a few annotated support images and mitigates the scarcity of labeled data and the need for extensive annotation in cerebral blood vessel segmentation. We evaluated the performance of VesselShot using the publicly available TubeTK dataset for the segmentation task, achieving a mean Dice coefficient (DC) of 0.62(0.03).