SynStitch: a Self-Supervised Learning Network for Ultrasound Image Stitching Using Synthetic Training Pairs and Indirect Supervision
This work addresses a domain-specific challenge in medical imaging by improving ultrasound image stitching, which is incremental as it builds on existing methods with a novel training approach.
The paper tackles the problem of stitching ultrasound images with partially overlapping anatomical contents by introducing SynStitch, a self-supervised framework that uses synthetic training pairs and indirect supervision, achieving superior performance on a kidney ultrasound dataset compared to leading methods.
Ultrasound (US) image stitching can expand the field-of-view (FOV) by combining multiple US images from varied probe positions. However, registering US images with only partially overlapping anatomical contents is a challenging task. In this work, we introduce SynStitch, a self-supervised framework designed for 2DUS stitching. SynStitch consists of a synthetic stitching pair generation module (SSPGM) and an image stitching module (ISM). SSPGM utilizes a patch-conditioned ControlNet to generate realistic 2DUS stitching pairs with known affine matrix from a single input image. ISM then utilizes this synthetic paired data to learn 2DUS stitching in a supervised manner. Our framework was evaluated against multiple leading methods on a kidney ultrasound dataset, demonstrating superior 2DUS stitching performance through both qualitative and quantitative analyses. The code will be made public upon acceptance of the paper.