UltrasODM: A Dual Stream Optical Flow Mamba Network for 3D Freehand Ultrasound Reconstruction

TL;DR

UltrasODM is a dual-stream framework that enhances 3D freehand ultrasound reconstruction by integrating optical flow, uncertainty estimation, and clinician feedback to reduce errors and improve clinical trust.

Contribution

The paper introduces UltrasODM, a novel dual-stream approach combining optical flow, uncertainty, and saliency maps for improved ultrasound reconstruction accuracy.

Findings

Reduces drift by 15.2%

Decreases distance error by 12.1%

Lowers Hausdorff distance by 10.1%

Abstract

Clinical ultrasound acquisition is highly operator-dependent, where rapid probe motion and brightness fluctuations often lead to reconstruction errors that reduce trust and clinical utility. We present UltrasODM, a dual-stream framework that assists sonographers during acquisition through calibrated per-frame uncertainty, saliency-based diagnostics, and actionable prompts. UltrasODM integrates (i) a contrastive ranking module that groups frames by motion similarity, (ii) an optical-flow stream fused with Dual-Mamba temporal modules for robust 6-DoF pose estimation, and (iii) a Human-in-the-Loop (HITL) layer combining Bayesian uncertainty, clinician-calibrated thresholds, and saliency maps highlighting regions of low confidence. When uncertainty exceeds the threshold, the system issues unobtrusive alerts suggesting corrective actions such as re-scanning highlighted regions or slowing the sweep. Evaluated on a clinical freehand ultrasound dataset, UltrasODM reduces drift by 15.2%, distance error by 12.1%, and Hausdorff distance by 10.1% relative to UltrasOM, while producing per-frame uncertainty and saliency outputs. By emphasizing transparency and clinician feedback, UltrasODM improves reconstruction reliability and supports safer, more trustworthy clinical workflows. Our code is publicly available at https://github.com/AnandMayank/UltrasODM.