What question did this study set out to answer?

This research aims to improve multi-sweep freehand 3D ultrasound by addressing trajectory degradation issues in volumetric reconstruction.

GLA-NeRF: global-local aligned neural radiance fields for multi-sweep freehand 3D ultrasound

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved volumetric reconstruction in freehand 3D ultrasound, indicating enhanced anatomical fidelity.

This research aims to improve multi-sweep freehand 3D ultrasound by addressing trajectory degradation issues in volumetric reconstruction.
Developed GLA-NeRF framework for joint pose and neural representation optimization in ultrasound.
Implemented global registration and local denoising modules to correct inter-sweep bias and intra-sweep jitter.
Conducted experiments on in vivo ultrasound datasets to assess performance and accuracy.
Achieved global accuracy of 3.95mm/1.53° regardless of initialization.
Reduced local tracking error from 2.5mm/2.0° to 0.65mm/0.52°.
Improved anatomical fidelity in synthesized ultrasound views.

Fang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark