Cargando…

Co-optimization Learning Network for MRI Segmentation of Ischemic Penumbra Tissues

Convolutional neural networks (CNNs) have brought hope for the medical image auxiliary diagnosis. However, the shortfall of labeled medical image data is the bottleneck that limits the performance improvement of supervised CNN methods. In addition, annotating a large number of labeled medical image...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Liangliang, Zhang, Jing, Wang, Jin-xiang, Xiong, Shufeng, Zhang, Hui
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8717777/
https://www.ncbi.nlm.nih.gov/pubmed/34975444
http://dx.doi.org/10.3389/fninf.2021.782262
_version_ 1784624593716117504
author Liu, Liangliang
Zhang, Jing
Wang, Jin-xiang
Xiong, Shufeng
Zhang, Hui
author_facet Liu, Liangliang
Zhang, Jing
Wang, Jin-xiang
Xiong, Shufeng
Zhang, Hui
author_sort Liu, Liangliang
collection PubMed
description Convolutional neural networks (CNNs) have brought hope for the medical image auxiliary diagnosis. However, the shortfall of labeled medical image data is the bottleneck that limits the performance improvement of supervised CNN methods. In addition, annotating a large number of labeled medical image data is often expensive and time-consuming. In this study, we propose a co-optimization learning network (COL-Net) for Magnetic Resonance Imaging (MRI) segmentation of ischemic penumbra tissues. COL-Net base on the limited labeled samples and consists of an unsupervised reconstruction network (R), a supervised segmentation network (S), and a transfer block (T). The reconstruction network extracts the robust features from reconstructing pseudo unlabeled samples, which is the auxiliary branch of the segmentation network. The segmentation network is used to segment the target lesions under the limited labeled samples and the auxiliary of the reconstruction network. The transfer block is used to co-optimization the feature maps between the bottlenecks of the reconstruction network and segmentation network. We propose a mix loss function to optimize COL-Net. COL-Net is verified on the public ischemic penumbra segmentation challenge (SPES) with two dozen labeled samples. Results demonstrate that COL-Net has high predictive accuracy and generalization with the Dice coefficient of 0.79. The extended experiment also shows COL-Net outperforms most supervised segmentation methods. COL-Net is a meaningful attempt to alleviate the limited labeled sample problem in medical image segmentation.
format Online
Article
Text
id pubmed-8717777
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-87177772021-12-31 Co-optimization Learning Network for MRI Segmentation of Ischemic Penumbra Tissues Liu, Liangliang Zhang, Jing Wang, Jin-xiang Xiong, Shufeng Zhang, Hui Front Neuroinform Neuroscience Convolutional neural networks (CNNs) have brought hope for the medical image auxiliary diagnosis. However, the shortfall of labeled medical image data is the bottleneck that limits the performance improvement of supervised CNN methods. In addition, annotating a large number of labeled medical image data is often expensive and time-consuming. In this study, we propose a co-optimization learning network (COL-Net) for Magnetic Resonance Imaging (MRI) segmentation of ischemic penumbra tissues. COL-Net base on the limited labeled samples and consists of an unsupervised reconstruction network (R), a supervised segmentation network (S), and a transfer block (T). The reconstruction network extracts the robust features from reconstructing pseudo unlabeled samples, which is the auxiliary branch of the segmentation network. The segmentation network is used to segment the target lesions under the limited labeled samples and the auxiliary of the reconstruction network. The transfer block is used to co-optimization the feature maps between the bottlenecks of the reconstruction network and segmentation network. We propose a mix loss function to optimize COL-Net. COL-Net is verified on the public ischemic penumbra segmentation challenge (SPES) with two dozen labeled samples. Results demonstrate that COL-Net has high predictive accuracy and generalization with the Dice coefficient of 0.79. The extended experiment also shows COL-Net outperforms most supervised segmentation methods. COL-Net is a meaningful attempt to alleviate the limited labeled sample problem in medical image segmentation. Frontiers Media S.A. 2021-12-16 /pmc/articles/PMC8717777/ /pubmed/34975444 http://dx.doi.org/10.3389/fninf.2021.782262 Text en Copyright © 2021 Liu, Zhang, Wang, Xiong and Zhang. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Liu, Liangliang
Zhang, Jing
Wang, Jin-xiang
Xiong, Shufeng
Zhang, Hui
Co-optimization Learning Network for MRI Segmentation of Ischemic Penumbra Tissues
title Co-optimization Learning Network for MRI Segmentation of Ischemic Penumbra Tissues
title_full Co-optimization Learning Network for MRI Segmentation of Ischemic Penumbra Tissues
title_fullStr Co-optimization Learning Network for MRI Segmentation of Ischemic Penumbra Tissues
title_full_unstemmed Co-optimization Learning Network for MRI Segmentation of Ischemic Penumbra Tissues
title_short Co-optimization Learning Network for MRI Segmentation of Ischemic Penumbra Tissues
title_sort co-optimization learning network for mri segmentation of ischemic penumbra tissues
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8717777/
https://www.ncbi.nlm.nih.gov/pubmed/34975444
http://dx.doi.org/10.3389/fninf.2021.782262
work_keys_str_mv AT liuliangliang cooptimizationlearningnetworkformrisegmentationofischemicpenumbratissues
AT zhangjing cooptimizationlearningnetworkformrisegmentationofischemicpenumbratissues
AT wangjinxiang cooptimizationlearningnetworkformrisegmentationofischemicpenumbratissues
AT xiongshufeng cooptimizationlearningnetworkformrisegmentationofischemicpenumbratissues
AT zhanghui cooptimizationlearningnetworkformrisegmentationofischemicpenumbratissues