Unsupervised Deformable Ultrasound Image Registration and Its Application for Vessel Segmentation
This work addresses the challenge of vessel segmentation in ultrasound imaging for medical applications by enabling synthetic data generation without manual labeling, though it is incremental as it builds on existing RAFT methods.
The paper tackled the problem of deformable registration of ultrasound images by developing U-RAFT, a deep-learning model based on RAFT that can be trained unsupervised and generate synthetic images, achieving 98% and 81% SSIM on phantom and porcine datasets, and improving IoU segmentation performance through data augmentation.
This paper presents a deep-learning model for deformable registration of ultrasound images at online rates, which we call U-RAFT. As its name suggests, U-RAFT is based on RAFT, a convolutional neural network for estimating optical flow. U-RAFT, however, can be trained in an unsupervised manner and can generate synthetic images for training vessel segmentation models. We propose and compare the registration quality of different loss functions for training U-RAFT. We also show how our approach, together with a robot performing force-controlled scans, can be used to generate synthetic deformed images to significantly expand the size of a femoral vessel segmentation training dataset without the need for additional manual labeling. We validate our approach on both a silicone human tissue phantom as well as on in-vivo porcine images. We show that U-RAFT generates synthetic ultrasound images with 98% and 81% structural similarity index measure (SSIM) to the real ultrasound images for the phantom and porcine datasets, respectively. We also demonstrate that synthetic deformed images from U-RAFT can be used as a data augmentation technique for vessel segmentation models to improve intersection-over-union (IoU) segmentation performance