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 ≈200k 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.
@article{arxiv.2310.16872,
title = {SonoSAMTrack -- Segment and Track Anything on Ultrasound Images},
author = {Hariharan Ravishankar and Rohan Patil and Vikram Melapudi and Harsh Suthar and Stephan Anzengruber and Parminder Bhatia and Kass-Hout Taha and Pavan Annangi},
journal= {arXiv preprint arXiv:2310.16872},
year = {2023}
}