# Anatomically Constrained Transformers for Echocardiogram Analysis

arXiv: https://arxiv.org/abs/2511.01109 · HTML: https://mlsanity.com/paper/2511.01109/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 47 references that are in the map.
- First posted on arXiv 2 Nov 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories](https://mlsanity.com/paper/2204.04153/) (2022)
- [Ultrasound Video Transformers for Cardiac Ejection Fraction Estimation](https://mlsanity.com/paper/2107.00977/) (2021)
- [EchoFM: Foundation Model for Generalizable Echocardiogram Analysis](https://mlsanity.com/paper/2410.23413/) (2024)
- [EchoApex: A General-Purpose Vision Foundation Model for Echocardiography](https://mlsanity.com/paper/2410.11092/) (2024)
- [EchoTracker: Advancing Myocardial Point Tracking in Echocardiography](https://mlsanity.com/paper/2405.08587/) (2024)
- [GEMTrans: A General, Echocardiography-based, Multi-Level Transformer Framework for Cardiovascular Diagnosis](https://mlsanity.com/paper/2308.13217/) (2023)
- [Low Complexity Point Tracking of the Myocardium in 2D Echocardiography](https://mlsanity.com/paper/2503.10431/) (2025)
- [BackMix: Mitigating Shortcut Learning in Echocardiography with Minimal Supervision](https://mlsanity.com/paper/2406.19148/) (2024)
- [Anatomically Constrained Transformers for Cardiac Amyloidosis Classification](https://mlsanity.com/paper/2509.19691/) (2025)

## Abstract (arXiv)

Video transformers have recently demonstrated strong potential for echocardiogram (echo) analysis, leveraging self-supervised pre-training and flexible adaptation across diverse tasks. However, like other models operating on videos, they are prone to learning spurious correlations from non-diagnostic regions such as image backgrounds. To overcome this limitation, we propose the Video Anatomically Constrained Transformer (ViACT), a novel framework that integrates anatomical priors directly into the transformer architecture. ViACT represents a deforming anatomical structure as a point set and encodes both its spatial geometry and corresponding image patches into transformer tokens. During pre-training, ViACT follows a masked autoencoding strategy that masks and reconstructs only anatomical patches, enforcing that representation learning is focused on the anatomical region. The pre-trained model can then be fine-tuned for tasks localized to this region. In this work we focus on the myocardium, demonstrating the framework on echo analysis tasks such as left ventricular ejection fraction (EF) regression and cardiac amyloidosis (CA) detection. The anatomical constraint focuses transformer attention within the myocardium, yielding interpretable attention maps aligned with regions of known CA pathology. Moreover, ViACT generalizes to myocardium point tracking without requiring task-specific components such as correlation volumes used in specialized tracking networks.