ImplicitCell: Resolution Cell Modeling of Joint Implicit Volume Reconstruction and Pose Refinement in Freehand 3D Ultrasound
This work addresses the challenge of improving reconstruction quality for freehand 3D ultrasound, enhancing clinical diagnosis by providing more reliable and precise diagnostic information, though it appears incremental as it builds on existing implicit neural representation methods.
The paper tackled the problem of artifacts in freehand 3D ultrasound reconstruction due to tracking noise and irregular probe movements by proposing ImplicitCell, a framework that integrates implicit neural representation with a resolution cell model for joint optimization, resulting in significantly reduced artifacts and improved volume quality compared to existing methods, particularly in noisy scenarios.
Freehand 3D ultrasound enables volumetric imaging by tracking a conventional ultrasound probe during freehand scanning, offering enriched spatial information that improves clinical diagnosis. However, the quality of reconstructed volumes is often compromised by tracking system noise and irregular probe movements, leading to artifacts in the final reconstruction. To address these challenges, we propose ImplicitCell, a novel framework that integrates Implicit Neural Representation (INR) with an ultrasound resolution cell model for joint optimization of volume reconstruction and pose refinement. Three distinct datasets are used for comprehensive validation, including phantom, common carotid artery, and carotid atherosclerosis. Experimental results demonstrate that ImplicitCell significantly reduces reconstruction artifacts and improves volume quality compared to existing methods, particularly in challenging scenarios with noisy tracking data. These improvements enhance the clinical utility of freehand 3D ultrasound by providing more reliable and precise diagnostic information.