CycleULM: A unified label-free deep learning framework for ultrasound localisation microscopy

2026-03-10

AI Summary

This work proposes CycleULM, a novel unsupervised deep learning framework for ultrasound localization microscopy (ULM) that overcomes key limitations including low microbubble localization accuracy, time-consuming processing pipelines, and the reliance of existing deep learning methods on labeled data or high-fidelity simulations. By leveraging CycleGAN, CycleULM enables unpaired, unsupervised domain translation between real contrast-enhanced ultrasound (CEUS) and a simplified microbubble domain—eliminating the need for paired data or complex simulators. The approach supports both modular and end-to-end deployment, achieving substantial performance gains: 15.3 dB contrast enhancement, a 2.5-fold reduction in point spread function full-width at half-maximum, 40% and 46% improvements in recall and precision, respectively, a 14.0 μm reduction in average localization error, and real-time processing at 18.3 frames per second—an acceleration of 14.5×—thereby advancing ULM toward clinical real-time applications.

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Super-resolution ultrasound via microbubble (MB) localisation and tracking, also known as ultrasound localisation microscopy (ULM), can resolve microvasculature beyond the acoustic diffraction limit. However, significant challenges remain in localisation performance and data acquisition and processing time. Deep learning methods for ULM have shown promise to address these challenges, however, they remain limited by in vivo label scarcity and the simulation-to-reality domain gap. We present CycleULM, the first unified label-free deep learning framework for ULM. CycleULM learns a physics-emulating translation between the real contrast-enhanced ultrasound (CEUS) data domain and a simplified MB-only domain, leveraging the power of CycleGAN without requiring paired ground truth data. With this translation, CycleULM removes dependence on high-fidelity simulators or labelled data, and makes MB localisation and tracking substantially easier. Deployed as modular plug-and-play components within existing pipelines or as an end-to-end processing framework, CycleULM delivers substantial performance gains across both in silico and in vivo datasets. Specifically, CycleULM improves image contrast (contrast-to-noise ratio) by up to 15.3 dB and sharpens CEUS resolution with a 2.5{\times} reduction in the full width at half maximum of the point spread function. CycleULM also improves MB localisation performance, with up to +40% recall, +46% precision, and a -14.0 μm mean localisation error, yielding more faithful vascular reconstructions. Importantly, CycleULM achieves real-time processing throughput at 18.3 frames per second with order-of-magnitude speed-ups (up to ~14.5{\times}). By combining label-free learning, performance enhancement, and computational efficiency, CycleULM provides a practical pathway toward robust, real-time ULM and accelerates its translation to clinical applications.

Problem

• ultrasound localisation microscopy
• label scarcity
• domain gap
• microbubble localisation
• real-time processing

Innovation

• ultrasound localisation microscopy
• label-free deep learning
• CycleGAN
• microbubble localisation
• real-time super-resolution