Inter-subject registration-based one-shot segmentation with alternating union network for cardiac MRI images |
| |
| Institution: | 1. School of Computer Science and Technology, Harbin Institute of Technology, Nangang District, Harbin 150000, China;2. Peng Cheng Laboratory, Nanshan District, Shenzhen 518000, China;3. School of Physics and Astronomy, The University of Manchester, Manchester M139PL, UK;4. Key Laboratory of Medical Electrophysiology of Ministry of Education and Medical Electrophysiological Key Laboratory of Sichuan Province, Institute of Cardiovascular Research, Southwest Medical University, Luzhou 646000, China;1. Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS UMR 5220, U1294, LYON, F-69100, France;2. Université de Technologie de Troyes / Laboratoire Informatique et Société Numérique, 10004 Troyes, France;3. Atys Medical, 17 Parc Arbora, Soucieu-en-Jarrest 69510, France;1. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA;2. A.A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA;3. Philips Research Laboratories, Hamburg, Germany;4. Department of Cardiology, Boston Children’s Hospital, Boston, MA, USA;5. Department of Pediatrics, Harvard Medical School, Boston, MA, USA;1. School of Electronic Engineering, Xidian University, Xi’an 710071, China;2. Radiology and Radiological Sciences, Johns Hopkins University, United States;3. Department of Diagnostic Imaging, Brown University, United States;4. The 38th Research Institute of China Electronics Technology Group Corporation, Hefei, 230088, China;1. Department of Artificial Intelligence, Sun Yat-sen University, Guangzhou 510006, China;2. Orthopedics Department, The First Affiliated Hospital of Zhejiang University, Hangzhou, Zhejiang, China;3. Nanjing XiaoZhuang University, Nanjing, Jiangsu, China;4. Western University, London, Canada;1. Centre for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), School of Computing, University of Leeds, Leeds, UK;2. Biomedical Imaging Department, Leeds Institute for Cardiovascular and Metabolic Medicine (LICAMM), School of Medicine, University of Leeds, Leeds, UK;3. Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, University of Oxford, John Radcliffe Hospital, Oxford, UK;4. William Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of London, London, UK;5. Barts Heart Centre, St Bartholomew’s Hospital, Barts Health NHS Trust, London, UK;6. Department of Cardiovascular Sciences, KU Leuven, Leuven, Belgium;7. Department of Electrical Engineering, KU Leuven, Leuven, Belgium;8. Alan Turing Institute, London, UK |
| |
| Abstract: | Medical image segmentation based on deep-learning networks makes great progress in assisting disease diagnosis. However, currently, the training of most networks still requires a large amount of data with labels. In reality, labeling a considerable number of medical images is challenging and time-consuming. In order to tackle this challenge, a new one-shot segmentation framework for cardiac MRI images based on an inter-subject registration model called Alternating Union Network (AUN) is proposed in this study. The label of the source image is warped with deformation fields discovered from AUN to segment target images directly. Initially, the volumes are pre-processed by aligning affinely and adjusting the global intensity to simplify subsequent deformation registration. AUN consists of two kinds of subnetworks trained alternately to optimize segmentation gradually. The first kind of subnetwork takes a pair of volumes as inputs and registers them using global intensity similarity. The second kind of subnetwork, which takes the predicted labels generated from the previous subnetwork and the labels refined using the information of intrinsic anatomical structures of interest as inputs, is intensity-independent and focuses attention on registering structures of interest. Specifically, the input of AUN is a pair of a labeled image with the texture in regions of interest removed and a target image. Additionally, a new similarity measurement more appropriate for registering such image pair is defined as Local Squared Error (LSE). The proposed registration-based one-shot segmentation pays attention to the problem of the lack of labeled medical images. In AUN, only one labeled volume is required and a large number of unlabeled ones can be leveraged to improve segmentation performance, which has great advantages in clinical application. In addition, the intensity-independent subnetwork and LSE proposed in this study empower the framework to segment medical images with complicated intensity distribution. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
