SynStitch: a Self-Supervised Learning Network for Ultrasound Image Stitching Using Synthetic Training Pairs and Indirect Supervision

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: 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
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929587107135488
author 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
author_facet 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
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06750
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SynStitch: a Self-Supervised Learning Network for Ultrasound Image Stitching Using Synthetic Training Pairs and Indirect Supervision
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
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title SynStitch: a Self-Supervised Learning Network for Ultrasound Image Stitching Using Synthetic Training Pairs and Indirect Supervision
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.06750