Learning to Match 2D Keypoints Across Preoperative MR and Intraoperative Ultrasound
This addresses a domain-specific problem in medical imaging for improved surgical guidance, but it is incremental as it builds on existing matching techniques.
The paper tackles the problem of matching 2D keypoints between preoperative MR and intraoperative ultrasound images by proposing a texture-invariant descriptor, achieving 80.35% matching precision and outperforming state-of-the-art methods.
We propose in this paper a texture-invariant 2D keypoints descriptor specifically designed for matching preoperative Magnetic Resonance (MR) images with intraoperative Ultrasound (US) images. We introduce a matching-by-synthesis strategy, where intraoperative US images are synthesized from MR images accounting for multiple MR modalities and intraoperative US variability. We build our training set by enforcing keypoints localization over all images then train a patient-specific descriptor network that learns texture-invariant discriminant features in a supervised contrastive manner, leading to robust keypoints descriptors. Our experiments on real cases with ground truth show the effectiveness of the proposed approach, outperforming the state-of-the-art methods and achieving 80.35% matching precision on average.