Geo-UNet: A Geometrically Constrained Neural Framework for Clinical-Grade Lumen Segmentation in Intravascular Ultrasound

TL;DR

Geo-UNet is a geometrically constrained neural framework designed to improve lumen segmentation accuracy in intravascular ultrasound, addressing limitations of existing models by incorporating lumen geometry and a dual-task approach.

Contribution

The paper introduces Geo-UNet, a novel segmentation framework that leverages lumen geometry, polar coordinate transformation, and a combined loss function for improved clinical-grade accuracy.

Findings

Achieves near clinical-grade segmentation accuracy on IVUS data.

Outperforms state-of-the-art models in lumen boundary detection.

Enhances segmentation smoothness with a lightweight inference technique.

Abstract

Precisely estimating lumen boundaries in intravascular ultrasound (IVUS) is needed for sizing interventional stents to treat deep vein thrombosis (DVT). Unfortunately, current segmentation networks like the UNet lack the precision needed for clinical adoption in IVUS workflows. This arises due to the difficulty of automatically learning accurate lumen contour from limited training data while accounting for the radial geometry of IVUS imaging. We propose the Geo-UNet framework to address these issues via a design informed by the geometry of the lumen contour segmentation task. We first convert the input data and segmentation targets from Cartesian to polar coordinates. Starting from a convUNet feature extractor, we propose a two-task setup, one for conventional pixel-wise labeling and the other for single boundary lumen-contour localization. We directly combine the two predictions by passing the predicted lumen contour through a new activation (named CDFeLU) to filter out spurious pixel-wise predictions. Our unified loss function carefully balances area-based, distance-based, and contour-based penalties to provide near clinical-grade generalization in unseen patient data. We also introduce a lightweight, inference-time technique to enhance segmentation smoothness. The efficacy of our framework on a venous IVUS dataset is shown against state-of-the-art models.