TUS-REC2024: A Challenge to Reconstruct 3D Freehand Ultrasound Without External Tracker

2025-06-26

AI Summary

This work addresses the challenging problem of freehand 3D ultrasound reconstruction without external tracking devices. Methodologically, it introduces an end-to-end framework integrating recurrent neural networks, image-registration-driven voxel optimization, attention mechanisms, and physics-informed modeling for joint motion estimation and volumetric reconstruction. Key contributions include: (1) the first open-source benchmark dataset featuring ground-truth motion annotations and a multi-center acquisition protocol; (2) a unified, Dockerized evaluation framework supporting multi-dimensional assessment—encompassing geometric accuracy, physical plausibility, and clinical utility; and (3) empirical insights derived from a large-scale challenge involving 43 participating teams and 21 validated submissions, which identify long-sequence drift mitigation and cross-protocol generalization as critical bottlenecks. The benchmark establishes a reproducible foundation for advancing low-cost, portable 3D ultrasound imaging research.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Trackerless freehand ultrasound reconstruction aims to reconstruct 3D volumes from sequences of 2D ultrasound images without relying on external tracking systems, offering a low-cost, portable, and widely deployable alternative for volumetric imaging. However, it presents significant challenges, including accurate inter-frame motion estimation, minimisation of drift accumulation over long sequences, and generalisability across scanning protocols. The TUS-REC2024 Challenge was established to benchmark and accelerate progress in trackerless 3D ultrasound reconstruction by providing a publicly available dataset for the first time, along with a baseline model and evaluation framework. The Challenge attracted over 43 registered teams, of which 6 teams submitted 21 valid dockerized solutions. Submitted methods spanned a wide range of algorithmic approaches, including recurrent models, registration-driven volume refinement, attention, and physics-informed models. This paper presents an overview of the Challenge design, summarises the key characteristics of the dataset, provides a concise literature review, introduces the technical details of the underlying methodology working with tracked freehand ultrasound data, and offers a comparative analysis of submitted methods across multiple evaluation metrics. The results highlight both the progress and current limitations of state-of-the-art approaches in this domain, and inform directions for future research. The data, evaluation code, and baseline are publicly available to facilitate ongoing development and reproducibility. As a live and evolving benchmark, this Challenge is designed to be continuously developed and improved. The Challenge was held at MICCAI 2024 and will be organised again at MICCAI 2025, reflecting its growing impact and the sustained commitment to advancing this field.

Problem

• Reconstruct 3D volumes from 2D ultrasound without trackers
• Address motion estimation and drift in long sequences
• Improve generalisability across scanning protocols

Innovation

• Trackerless 3D ultrasound reconstruction from 2D images
• Public dataset and baseline model for benchmarking
• Diverse algorithmic approaches including attention models