• Abstract The clinical translation of miniature medical devices (MMDs) for minimally invasive surgery promises transformative advances in biomedical engineering, offering enhanced precision, reduced patient trauma and faster recovery times. • However, their effective deployment in complex anatomies under real-time X-ray guidance-a widely used surgical imaging modality-presents challenges such as low imaging quality and difficulties of spatial MMD control. • Manual identification and operation are labour intensive and error prone. • Meanwhile, deep learning-based automation is limited by the scarcity of annotated X-ray datasets of MMDs owing to costly data collection, laborious annotation and privacy constraints. • Here we introduce MicroSyn-X, a framework for training computer vision models to enable robotic teleoperation of MMDs using synthesized high-fidelity, pixel-accurate, auto-labelled and domain-randomized X-ray images, eliminating manual data curation. • Integrating MicroSyn-X into a teleoperated robotic system enables real-time localization and navigation of magnetic soft and magnetic liquid MMDs within both ex vivo and dynamic in vivo environments, demonstrating robustness under challenging imaging conditions of low contrast, high noise and occlusion.

Article Summaries:

  • MicroSyn‑X is a new framework that generates high‑fidelity, pixel‑accurate synthetic X‑ray images of miniature medical devices (MMDs) for training computer‑vision models. By eliminating the need for costly, manually annotated real X‑ray data, the system enables robotic teleoperation of magnetic soft and liquid MMDs in real‑time fluoroscopic guidance. Experiments show robust localization and navigation in both ex‑vivo and dynamic in‑vivo settings, even under low contrast, high noise, and occlusion. The authors also release an open‑source X‑ray MMD dataset to benchmark future work. This approach addresses data scarcity and improves precision and efficiency in minimally invasive surgery.
  • Synthetic X‑ray‑driven tracking and control of miniature medical devices

Researchers have developed MicroSyn‑X, a framework that generates high‑fidelity, pixel‑accurate, auto‑labelled X‑ray images of miniature medical devices (MMDs). By synthesizing diverse, domain‑randomized datasets, the system eliminates the need for costly manual annotation and overcomes the scarcity of real X‑ray data. Integrated into a teleoperated robotic platform, MicroSyn‑X enables real‑time localization and navigation of magnetic soft and liquid MMDs in ex‑vivo and dynamic in‑vivo settings, even under low‑contrast, noisy, or occluded imaging conditions. The team has released the synthetic dataset publicly, aiming to benchmark and accelerate the clinical deployment of MMD‑assisted minimally invasive surgery.

Sources: