Yao, Xing; Yu, Runxuan; Hu, Dewei; Yang, Hao; Lou, Ange; Wang, Jiacheng; Lu, Daiwei; Arenas, Gabriel; Oguz, Baris; Pouch, Alison; Schwartz, Nadav; Byram, Brett C.; Oguz, Ipek. “SynStitch: A self-supervised learning network for ultrasound image stitching using synthetic training pairs and indirect supervision.” Proceedings – International Symposium on Biomedical Imaging (2025). https://doi.org/10.1109/ISBI60581.2025.10981027.
Ultrasound (US) imaging is commonly used to see inside the body, but each image only shows a small area. To get a bigger picture, doctors can “stitch” multiple ultrasound images together—kind of like making a panoramic photo. However, it’s hard to accurately combine these images when they only partly overlap or show slightly different views of the same body part.
In this work, we introduce SynStitch, a new self-supervised method that helps stitch together 2D ultrasound images more effectively. SynStitch has two main parts: a Synthetic Stitching Pair Generation Module (SSPGM) and an Image Stitching Module (ISM). The SSPGM uses an AI model called ControlNet to create realistic pairs of ultrasound images from a single image, where the relationship between the two images is known. These pairs are used to teach the ISM how to properly stitch ultrasound images together.
We tested SynStitch on kidney ultrasound images and found that it worked better than several top existing methods. It produced clearer and more accurate stitched images, as shown by both visual results and data measurements. You can find the code for this project at https://github.com/MedICL-VU/SynStitch.
Fig. 1.
SynStitch overview. We first train the SSPGM to generate a realistic 2DUS image Is from an input image I with a random affine matrix A. Then we freeze the SSPGM and we train ISM on the synthetic stitching pairs.
