AUTHOR=Xu Jianguo , Shen Jianxin , Wan Cheng , Jiang Qin , Yan Zhipeng , Yang Weihua 

TITLE=A Few-Shot Learning-Based Retinal Vessel Segmentation Method for Assisting in the Central Serous Chorioretinopathy Laser Surgery

JOURNAL=Frontiers in Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2022.821565

DOI=10.3389/fmed.2022.821565

ISSN=2296-858X

ABSTRACT=Background: The location of retinal vessels is an important prerequisite for Central Serous Chorioretinopathy (CSC) Laser Surgery, which can not only assist the ophthalmologist in marking the location of leakage point (LP) on fundus color image, but also avoid the damage of laser spot to vessel tissue and the low efficiency of surgery caused by the absorption of laser energy by retinal vessels. For acquiring an excellent intra- and cross-domain adaptability, the existing deep learning (DL) based vessel segmentation scheme must be driven by big data, which makes the densely-annotated work tedious and costly.
Methods: This paper aims to explore a new vessel segmentation method with few samples and annotations to alleviate the above problems. Firstly, a key solution is presented to transform the vessel segmentation scene into the few-shot learning task, which lays a foundation for vessel segmentation task with few samples and annotations. Then, we improve the existing few-shot learning framework as our baseline model to adapt to the vessel segmentation scenario. Next, the baseline model is upgraded from the following three aspects: (1) A multi-scale class prototype extraction technique is designed to obtain more sufficient vessel features for better utilizing the information from the support images. (2) The multi-scale vessel features of the query images inferred by the support image class prototype information are gradually fused to provide more effective guidance for vessel extraction task. (3) A multi-scale attention module is proposed to promote the consideration of global information in the upgraded model to assist vessel localization. Concurrently, the integrated framework is further conceived to appropriately alleviate the low performance of a single model in the cross-domain vessel segmentation scene, enabling to boost the domain adaptabilities of both the baseline and upgraded models.   
Results: Extensive experiments showed the upgraded operation could further improve the performance of vessel segmentation significantly. Compared with the listed methods, both the baseline and upgraded models achieved competitive results on three public retinal image datasets (i.e., CHASE_DB, DRIVE and STARE). In the practical application of private CSC datasets, the integrated scheme partially enhanced the domain adaptabilities of the two proposed models.