Evaluation of Blood Vessel Segmentation Methods on Hard-to-Detect Vascular Structures

Abstract:Due to the intricate structure of vascular trees, minor segmentation errors can significantly alter connectivity patterns and increase variability in extracted morphological properties. Global metrics such as the Dice coefficient, precision, and recall often overlook inaccuracies in specific regions of a sample. To address this, we define a Local Vessel Salience (LVS) index to quantify the difficulty of identifying specific vessel segments. This index is used to evaluate the performance of 16 segmentation methods across six widely used 2D datasets. The LVS index is calculated for each vessel pixel by comparing local vessel intensity against the surrounding background. We introduce a metric termed mean Low-Salience Recall (mLSR) to quantify how effectively algorithms recover hard-to-detect vessels. Furthermore, we propose a proof-of-concept data augmentation procedure guided by the LVS index aimed at improving neural network segmentation performance. Our findings demonstrate that segmentation performance strongly correlates with LVS, revealing systematic errors in vessels with low salience. The mLSR across all evaluated methods was significantly lower than standard recall values, with a typical performance decrease of 20 percentage points. In benchmark datasets such as DRIVE and OCTA-500, mLSR values for the top-performing methods were approximately 58%. The developed methodology provides a quantitative basis for the design of segmentation algorithms with improved sensitivity to hard-to-detect vessels and enhanced capabilities for preserving vascular connectivity.

Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

arXiv:2406.13128 [cs.CV]

(or arXiv:2406.13128v2 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2406.13128 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.