UltraPIPS introduces domain‑specific foundation models for measuring perceptual similarity in B‑mode ultrasound images. The study shows that ultrasound‑trained LPIPS backbones better correlate with downstream tasks such as classification, segmentation, and reconstruction than natural‑image or general medical models. Optimizing LPIPS loss with an ultrasound backbone yields a strong balance between reconstruction quality and realism, and the authors provide an open‑source library for these metrics.
By Tal Grutman, Tali Ilovitsh
The paper introduces Segment Anything Small (SAS), a data‑augmentation method that improves deep‑learning segmentation of small anatomical structures in ultrasound images. SAS uses two transformations: resizing and embedding organ thumbnails into a black background to vary organ scale, and adding noise to regions of interest to mimic tissue texture variability. Experiments on one internal and five external datasets show Dice score gains up to 0.35, with an average improvement of 0.16, and demonstrate that SAS enhances model robustness and generalizability without adding hallucinations or artifacts.
By Danielle L. Ferreira, Ahana Gangopadhyay, Hsi-Ming Chang, Ravi Soni, Gopal Avinash
US-JEPA introduces a self‑supervised framework for ultrasound imaging that predicts masked latent representations instead of raw pixels, using a frozen, domain‑specific teacher to provide stable targets. This approach avoids the hyperparameter sensitivity and computational cost of traditional online teachers, enabling the student model to build upon the teacher’s semantic priors. The authors benchmark US‑JEPA against all publicly available ultrasound foundation models on UltraBench, showing competitive or superior performance across multiple organs and pathological conditions under linear probing.
By Ashwath Radhachandran, Vedrana Ivezi\'c, Shreeram Athreya, Corey W. Arnold, William Speier
arXiv:2606. 15176v1 Announce Type: cross Abstract: Ultrasound imaging is the most widely adopted medical modality globally due to its low cost and portability, yet artificial intelligence (AI) deployment remains constrained by reliance on GPU-accelerated models, creating a structural paradox where the cost of "intelligence" exceeds that of the imaging device itself.
By Weihao Gao
UltraG-Bench is a large‑scale, multi‑task benchmark designed to evaluate pixel‑level evidence grounding in ultrasound images. It comprises 40 public segmentation datasets covering 13 anatomical categories and includes three progressive tasks—instruction‑guided segmentation, evidence‑grounded VQA, and evidence‑grounded report generation—with a total of 736,726 annotations. Evaluation of 14 state‑of‑the‑art models shows a significant gap between semantic understanding and fine‑grained pixel‑level localization, and the authors propose UltraG‑Agent, which combines a vision‑language model with the ultrasound‑specific segmentation model UltraSAM to improve both semantic prediction and visual grounding.
By Quanhao Zhu, Bo Xu, Rui Lin, Chenyuan Wang, Yu Shao, Boling Zhu, Jiuyan Sun, Liang Zhao, Hongfei Lin, Feng Xia
The paper introduces ExiL, a mask‑conditioned progressive learning framework for bone ultrasound segmentation that models annotation as a structured refinement trajectory. ExiL uses a synthetic expert‑like brush simulator and a lightweight U‑Net to learn from imperfect masks, and it can be updated in real time from expert refinements. In experiments on UltraBones100k and a prospective volunteer dataset, ExiL cut average annotation time from 60 to 20 seconds per frame and improved mean Dice by about 0.045, achieving 0.87 Dice and 2.7 px boundary error with 10–50 ms inference.
By Arash Tavangar, Larissa K. Chiu, Hamidreza Khodashenas, Gregory K. Berry, Amir Hooshiar