# Baseline Method of the Foundation Model Challenge for Ultrasound Image Analysis

arXiv: https://arxiv.org/abs/2602.01055 · HTML: https://mlsanity.com/paper/2602.01055/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 13 references that are in the map.
- First posted on arXiv 1 Feb 2026.

## Builds on (most cited first, 3 of 3)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [PSFHS Challenge Report: Pubic Symphysis and Fetal Head Segmentation from Intrapartum Ultrasound Images](https://mlsanity.com/paper/2409.10980/) (2024)

## Built on by (most cited first, 4 of 4)

- [Beyond Benchmarks of IUGC: Rethinking Requirements of Deep Learning Methods for Intrapartum Ultrasound Biometry from Fetal Ultrasound Videos](https://mlsanity.com/paper/2602.12922/) (2026)
- [TAP-SLF: Parameter-Efficient Adaptation of Vision Foundation Models for Multi-Task Ultrasound Image Analysis](https://mlsanity.com/paper/2603.00433/) (2026)
- [AURORA: Adaptive Unified Representation for Robust Ultrasound Analysis](https://mlsanity.com/paper/2603.19364/) (2026)
- [Unified Ultrasound Intelligence Toward an End-to-End Agentic System](https://mlsanity.com/paper/2604.16914/) (2026)

## Abstract (arXiv)

Ultrasound (US) imaging exhibits substantial heterogeneity across anatomical structures and acquisition protocols, posing significant challenges to the development of generalizable analysis models. Most existing methods are task-specific, limiting their suitability as clinically deployable foundation models. To address this limitation, the Foundation Model Challenge for Ultrasound Image Analysis (FMUIA~2026) introduces a large-scale multi-task benchmark comprising 27 subtasks across segmentation, classification, detection, and regression. In this paper, we present the official baseline for FMUIA~2026 based on a unified Multi-Head Multi-Task Learning (MH-MTL) framework that supports all tasks within a single shared network. The model employs an ImageNet-pretrained EfficientNet--B4 backbone for robust feature extraction, combined with a Feature Pyramid Network (FPN) to capture multi-scale contextual information. A task-specific routing strategy enables global tasks to leverage high-level semantic features, while dense prediction tasks exploit spatially detailed FPN representations. Training incorporates a composite loss with task-adaptive learning rate scaling and a cosine annealing schedule. Validation results demonstrate the feasibility and robustness of this unified design, establishing a strong and extensible baseline for ultrasound foundation model research. The code and dataset are publicly available at hrefhttps://github.com/lijiake2408/Foundation-Model-Challenge-for-Ultrasound-Image-AnalysisGitHub.