End-to-end Ultrasound Frame to Volume Registration
This work addresses a multimodal 2D/3D registration problem for prostate biopsy, which can increase biopsy yield, but it appears incremental as it builds on existing registration methods without hardware tracking.
The paper tackles the challenging problem of fusing intra-operative 2D transrectal ultrasound (TRUS) images with pre-operative 3D magnetic resonance (MR) volumes for prostate biopsy guidance, proposing an end-to-end frame-to-volume registration network (FVR-Net) that achieves highly competitive registration accuracy and superior efficiency for real-time guidance.
Fusing intra-operative 2D transrectal ultrasound (TRUS) image with pre-operative 3D magnetic resonance (MR) volume to guide prostate biopsy can significantly increase the yield. However, such a multimodal 2D/3D registration problem is a very challenging task. In this paper, we propose an end-to-end frame-to-volume registration network (FVR-Net), which can efficiently bridge the previous research gaps by aligning a 2D TRUS frame with a 3D TRUS volume without requiring hardware tracking. The proposed FVR-Net utilizes a dual-branch feature extraction module to extract the information from TRUS frame and volume to estimate transformation parameters. We also introduce a differentiable 2D slice sampling module which allows gradients backpropagating from an unsupervised image similarity loss for content correspondence learning. Our model shows superior efficiency for real-time interventional guidance with highly competitive registration accuracy.