English

Transformer Lesion Tracker

Computer Vision and Pattern Recognition 2022-12-13 v1

Abstract

Evaluating lesion progression and treatment response via longitudinal lesion tracking plays a critical role in clinical practice. Automated approaches for this task are motivated by prohibitive labor costs and time consumption when lesion matching is done manually. Previous methods typically lack the integration of local and global information. In this work, we propose a transformer-based approach, termed Transformer Lesion Tracker (TLT). Specifically, we design a Cross Attention-based Transformer (CAT) to capture and combine both global and local information to enhance feature extraction. We also develop a Registration-based Anatomical Attention Module (RAAM) to introduce anatomical information to CAT so that it can focus on useful feature knowledge. A Sparse Selection Strategy (SSS) is presented for selecting features and reducing memory footprint in Transformer training. In addition, we use a global regression to further improve model performance. We conduct experiments on a public dataset to show the superiority of our method and find that our model performance has improved the average Euclidean center error by at least 14.3% (6mm vs. 7mm) compared with the state-of-the-art (SOTA). Code is available at https://github.com/TangWen920812/TLT.

Keywords

Cite

@article{arxiv.2206.06252,
  title  = {Transformer Lesion Tracker},
  author = {Wen Tang and Han Kang and Haoyue Zhang and Pengxin Yu and Corey W. Arnold and Rongguo Zhang},
  journal= {arXiv preprint arXiv:2206.06252},
  year   = {2022}
}

Comments

Accepted MICCAI 2022

R2 v1 2026-06-24T11:49:15.649Z