BOTM: Echocardiography Segmentation via Bi-directional Optimal Token Matching

TL;DR

BOTM introduces a novel echocardiography segmentation method that ensures anatomical consistency across frames by matching image tokens bidirectionally, leading to more stable and accurate segmentation results in challenging low SNR conditions.

Contribution

The paper presents a new segmentation framework that performs optimal token matching and anatomical transportation, improving consistency and accuracy over existing methods.

Findings

Achieves -1.917 HD on CAMUS2H LV

Attains +1.9% Dice on TED

Provides better anatomical matching interpretation

Abstract

Existed echocardiography segmentation methods often suffer from anatomical inconsistency challenge caused by shape variation, partial observation and region ambiguity with similar intensity across 2D echocardiographic sequences, resulting in false positive segmentation with anatomical defeated structures in challenging low signal-to-noise ratio conditions. To provide a strong anatomical guarantee across different echocardiographic frames, we propose a novel segmentation framework named BOTM (Bi-directional Optimal Token Matching) that performs echocardiography segmentation and optimal anatomy transportation simultaneously. Given paired echocardiographic images, BOTM learns to match two sets of discrete image tokens by finding optimal correspondences from a novel anatomical transportation perspective. We further extend the token matching into a bi-directional cross-transport attention proxy to regulate the preserved anatomical consistency within the cardiac cyclic deformation in temporal domain. Extensive experimental results show that BOTM can generate stable and accurate segmentation outcomes (e.g. -1.917 HD on CAMUS2H LV, +1.9% Dice on TED), and provide a better matching interpretation with anatomical consistency guarantee.