SonoSAMTrack -- Segment and Track Anything on Ultrasound Images

TL;DR

SonoSAMTrack introduces a promptable segmentation and contour tracking framework for ultrasound images, achieving state-of-the-art accuracy, efficient annotation, and applicability to 2D+t and 3D data in clinical settings.

Contribution

The paper presents SonoSAMTrack, a novel model combining segmentation and tracking for ultrasound images, with fine-tuning and knowledge distillation for practical deployment.

Findings

State-of-the-art performance on 7 unseen ultrasound datasets.

Effective dense annotation with fewer user interactions.

Superior segmentation accuracy compared to existing methods.

Abstract

In this paper, we present SonoSAMTrack - that combines a promptable foundational model for segmenting objects of interest on ultrasound images called SonoSAM, with a state-of-the art contour tracking model to propagate segmentations on 2D+t and 3D ultrasound datasets. Fine-tuned and tested exclusively on a rich, diverse set of objects from $\approx200$k ultrasound image-mask pairs, SonoSAM demonstrates state-of-the-art performance on 7 unseen ultrasound data-sets, outperforming competing methods by a significant margin. We also extend SonoSAM to 2-D +t applications and demonstrate superior performance making it a valuable tool for generating dense annotations and segmentation of anatomical structures in clinical workflows. Further, to increase practical utility of the work, we propose a two-step process of fine-tuning followed by knowledge distillation to a smaller footprint model without comprising the performance. We present detailed qualitative and quantitative comparisons of SonoSAM with state-of-the-art methods showcasing efficacy of the method. This is followed by demonstrating the reduction in number of clicks in a dense video annotation problem of adult cardiac ultrasound chamber segmentation using SonoSAMTrack.