Enabling Real-Time Point-of-Care Ultrasound Segmentation: A GPU-Free Deployment in Resource-Limited Settings

2026-06-13

AI Summary

This study addresses the high deployment costs of current AI-based ultrasound image analysis, which heavily relies on GPUs and thus remains inaccessible in resource-limited settings. To overcome this barrier, the authors propose UltraSeg, an ultra-lightweight model with only 0.13–0.5 million parameters, enabling real-time, clinical-grade point-of-care ultrasound segmentation on single-core CPUs and refurbished mobile devices without GPU acceleration. Evaluated across ten public multi-anatomical datasets, UltraSeg-500K achieves 44.6 frames per second on CPU while matching the Dice performance of a 31M-parameter U-Net and approaching that of a 105M-parameter TransUNet. Furthermore, it demonstrates strong zero-shot cross-domain generalization in external validation, highlighting its robustness and potential for broad clinical deployment.

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. Here, we present the systematic adaptation and extensive evaluation of UltraSeg, an ultra-lightweight architecture originally developed for colonoscopic polyp segmentation, now engineered for point-of-care ultrasound (POCUS) across ten public datasets spanning six anatomical sites (breast, thyroid, kidney, carotid, fetal, and small-animal tumor). We systematically validate both variants in ultrasound domains: UltraSeg-130K (0.13M parameters) achieves 89.7 FPS on single-core CPUs and 34.8 FPS on a refurbished mobile device, while UltraSeg-500K (0.5M parameters) delivers 44.6 FPS on CPU and 16.1 FPS on mobile device. UltraSeg-500K matches or exceeds the Dice performance of the 31M-parameter UNet and approaches 105M-parameter TransUNet in average performance, with superior zero-shot cross-dataset generalization on external validation sets (UDIAT, DDTI). By enabling clinical-grade segmentation without GPU dependency, this work brings AI costs in line with ultrasound accessibility, making advanced diagnostics available in resource-limited settings.

Problem

• ultrasound segmentation
• point-of-care
• GPU-free deployment
• resource-limited settings
• real-time AI

Innovation

• ultra-lightweight architecture
• GPU-free deployment
• real-time ultrasound segmentation
• zero-shot generalization
• point-of-care ultrasound