BOTM: Echocardiography Segmentation via Bi-directional Optimal Token Matching


Zhihua Liu (University of Leicester), Lei Tong (AstraZeneca), Xilin He (The Chinese University of Hong Kong), Che Liu (Imperial College London), Rossella Arcucci (Imperial College London), Chen Jin (Astrazeneca), Huiyu Zhou (University of Leicester)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

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__ (**B**i-directional **O**ptimal **T**oken **M**atchig) 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.

Citation

@inproceedings{Liu_2025_BMVC,
author    = {Zhihua Liu and Lei Tong and Xilin He and Che Liu and Rossella Arcucci and Chen Jin and Huiyu Zhou},
title     = {BOTM: Echocardiography Segmentation via Bi-directional Optimal Token Matching},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_121/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection