End-to-end Ultrasound Frame to Volume Registration
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| 3D/2D Registration | S2V | MAE(R) mean7.65 | 8 | |
| Ultrasound Frame to Volume Registration | TRUS (test) | Distance Error (mm)2.73 | 6 | |
| 2D-3D Ultrasound Registration | µ-RegPro ultrasound | Displacement Error (DisErr)11.83 | 4 | |
| 2D-3D Ultrasound Registration | CAMUS (official split) | Displacement Error (DisErr)9.38 | 4 |