# A texture-based framework for foundational ultrasound models

arXiv: https://arxiv.org/abs/2602.01444 · HTML: https://mlsanity.com/paper/2602.01444/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 54 references that are in the map.
- First posted on arXiv 1 Feb 2026.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images](https://mlsanity.com/paper/2201.01266/) (2022)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification](https://mlsanity.com/paper/1602.02068/) (2016)
- [Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography](https://mlsanity.com/paper/1908.06948/) (2019)
- [USFM: A Universal Ultrasound Foundation Model Generalized to Tasks and Organs towards Label Efficient Image Analysis](https://mlsanity.com/paper/2401.00153/) (2023)
- [High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy with Cardiovascular Deep Learning](https://mlsanity.com/paper/2106.12511/) (2021)
- [Echocardiography Segmentation with Enforced Temporal Consistency](https://mlsanity.com/paper/2112.02102/) (2021)
- [Foundation Models in Radiology: What, How, When, Why and Why Not](https://mlsanity.com/paper/2411.18730/) (2024)
- [UltraSam: A Foundation Model for Ultrasound using Large Open-Access Segmentation Datasets](https://mlsanity.com/paper/2411.16222/) (2024)
- [The Open Kidney Ultrasound Data Set](https://mlsanity.com/paper/2206.06657/) (2022)
- [MMOTU: A Multi-Modality Ovarian Tumor Ultrasound Image Dataset for Unsupervised Cross-Domain Semantic Segmentation](https://mlsanity.com/paper/2207.06799/) (2022)
- [Contrastive Pretraining for Echocardiography Segmentation with Limited Data](https://mlsanity.com/paper/2201.07219/) (2022)
- [COVID-BLUeS -- A Prospective Study on the Value of AI in Lung Ultrasound Analysis](https://mlsanity.com/paper/2509.10556/) (2025)
- [Less is More: Adaptive Curriculum Learning for Thyroid Nodule Diagnosis](https://mlsanity.com/paper/2207.00807/) (2022)
- [Deep Coherence Learning: An Unsupervised Deep Beamformer for High Quality Single Plane Wave Imaging in Medical Ultrasound](https://mlsanity.com/paper/2311.11169/) (2023)
- [A novel open-source ultrasound dataset with deep learning benchmarks for spinal cord injury localization and anatomical segmentation](https://mlsanity.com/paper/2409.16441/) (2024)
- [A Human-Centered Machine-Learning Approach for Muscle-Tendon Junction Tracking in Ultrasound Images](https://mlsanity.com/paper/2202.05199/) (2022)
- [CountXplain: Interpretable Cell Counting with Prototype-Based Density Map Estimation](https://mlsanity.com/paper/2511.19686/) (2025)

## Built on by (most cited first, 1 of 1)

- [UltraPIPS: Improving model perception in B-mode ultrasound with foundation models](https://mlsanity.com/paper/2608.26033/) (2026)

## Abstract (arXiv)

Ultrasound is the most widely used medical imaging modality, yet the images it produces are fundamentally unique, arising from tissue-dependent scattering, reflection, and speed-of-sound variations that produce a constrained set of characteristic textures that differ markedly from natural-image statistics. These acoustically driven patterns make ultrasound challenging for algorithms originally designed for natural images. To bridge this gap, the field has increasingly turned to foundation models, hoping to leverage their generalization capabilities. However, these models often falter in ultrasound applications because they are not designed for ultrasound physics, they are merely trained on ultrasound data. Therefore, it is essential to integrate ultrasound-specific domain knowledge into established learning frameworks. We achieve this by reformulating self-supervised learning as a texture-analysis problem, introducing texture ultrasound semantic analysis (TUSA). Using TUSA, models learn to leverage highly scalable contrastive methods to extract true domain-specific representations directly from simple B-mode images. We train a TUSA model on a combination of open-source, simulated, and in vivo data. The latent space is compared to several larger foundation models, demonstrating that our approach gives TUSA models better generalizability for difficult downstream tasks on unique online datasets as well as a clinical eye dataset collected for this study. Our model achieves higher accuracy in detecting COVID (70%), spinal hematoma (100%) and vitreous hemorrhage (97%) and correlates more closely with quantitative parameters like liver steatosis (r = 0.83), ejection fraction (r = 0.63), and oxygen saturation (r = 0.38). We open-source the model weights and training script: https://github.com/talg2324/tusa