Abstract
In medical imaging, it is common to use learned perceptual image patch similarity (LPIPS) to compare images semantically in feature space. Although backbones pretrained on natural images are widely used for LPIPS computation, B-mode ultrasound images possess distinct speckle patterns and acoustic-specific image statistics that are fundamentally different from natural images and even from other images in radiology. Consequently, we propose that domain-specific models are needed to measure perceptual similarity in ultrasound data, a finding which is not necessarily the case for other imaging modalities. We compare deep feature distances across downstream tasks like classification, segmentation and reconstruction using natural image, medical generalist and ultrasound backbone models and show that backbone selection is a non-trivial design choice. In particular, the ultrasound backbone models were more correlated with downstream performance of supervised models than classical and natural image models, and optimization of a deep feature distance loss with an ultrasound backbone achieved the best reconstruction and texture statistics. Our code is available at https://github.com/talg2324/UltraPIPS and introduces the UltraPIPS library, a set of perceptual distance metrics based on the open-source foundation models analyzed in this paper.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/ASMUS_010.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: https://papers.miccai.org/miccai-2026-sat/supp/ASMUS_010_supp.pdf
Link to Open Review
Open Review Page: https://openreview.net/forum?id=GPAxfO5xCB
BibTex
@InProceedings{GruTal_UltraPIPS_MICCAISAT2026,
author = { Grutman, Tal AND Ilovitsh, Tali},
title = { { UltraPIPS: Improving model perception in B-mode ultrasound with foundation models } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17276},
month = {pending},
page = {pending}
}
