Fully automated 3D segmentation of MR-imaged calf muscle compartments: Neighborhood relationship enhanced fully convolutional network

Zhihui Guo; Honghai Zhang; Zhi Chen; Ellen van der Plas; Laurie Gutmann; Daniel Thedens; Peggy Nopoulos; Milan Sonka

doi:10.1016/j.compmedimag.2020.101835

Back

Fully automated 3D segmentation of MR-imaged calf muscle compartments: Neighborhood relationship enhanced fully convolutional network

Journal article

Open access

Peer reviewed

Fully automated 3D segmentation of MR-imaged calf muscle compartments: Neighborhood relationship enhanced fully convolutional network

Zhihui Guo, Honghai Zhang, Zhi Chen, Ellen van der Plas, Laurie Gutmann, Daniel Thedens, Peggy Nopoulos and Milan Sonka

Computerized medical imaging and graphics, Vol.87, pp.101835-101835

01/2021

DOI: 10.1016/j.compmedimag.2020.101835

PMCID: PMC7855601

PMID: 33373972

Files and links (1)

url

https://www.ncbi.nlm.nih.gov/pmc/articles/7855601View

Open Access

Abstract

Automated segmentation of individual calf muscle compartments from 3D magnetic resonance (MR) images is essential for developing quantitative biomarkers for muscular disease progression and its prediction. Achieving clinically acceptable results is a challenging task due to large variations in muscle shape and MR appearance. In this paper, we present a novel fully convolutional network (FCN) that utilizes contextual information in a large neighborhood and embeds edge-aware constraints for individual calf muscle compartment segmentations. An encoder-decoder architecture is used to systematically enlarge convolution receptive field and preserve information at all resolutions. Edge positions derived from the FCN output muscle probability maps are explicitly regularized using kernel-based edge detection in an end-to-end optimization framework. Our method was evaluated on 40 T1-weighted MR images of 10 healthy and 30 diseased subjects by fourfold cross-validation. Mean DICE coefficients of 88.00-91.29% and mean absolute surface positioning errors of 1.04-1.66 mm were achieved for the five 3D muscle compartments.

Edge constraint

Fully convolutional network

Calf muscle compartment segmentation

Magnetic resonance image

Details

Title: Subtitle: Fully automated 3D segmentation of MR-imaged calf muscle compartments: Neighborhood relationship enhanced fully convolutional network
Creators: Zhihui Guo - Iowa Institute for Biomedical Imaging, University of Iowa, Iowa City, IA 52242, USA. Electronic address: zhihui-guo@uiowa.edu
Honghai Zhang - Iowa Institute for Biomedical Imaging, University of Iowa, Iowa City, IA 52242, USA
Zhi Chen - Iowa Institute for Biomedical Imaging, University of Iowa, Iowa City, IA 52242, USA
Ellen van der Plas - Department of Psychiatry, University of Iowa, Iowa City, IA 52242, USA
Laurie Gutmann - Department of Neurology, University of Iowa, Iowa City, IA 52242, USA
Daniel Thedens - Department of Psychiatry, University of Iowa, Iowa City, IA 52242, USA
Peggy Nopoulos - Department of Psychiatry, University of Iowa, Iowa City, IA 52242, USA
Milan Sonka - Iowa Institute for Biomedical Imaging, University of Iowa, Iowa City, IA 52242, USA
Resource Type: Journal article
Publication Details: Computerized medical imaging and graphics, Vol.87, pp.101835-101835
DOI: 10.1016/j.compmedimag.2020.101835
PMID: 33373972
PMCID: PMC7855601
NLM abbreviation: Comput Med Imaging Graph
ISSN: 0895-6111
eISSN: 1879-0771
Publisher: United States
Grant note: R01 EB004640 / NIBIB NIH HHS R01 NS094387 / NINDS NIH HHS
Language: English
Date published: 01/2021
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Neurology; Radiology; Electrical and Computer Engineering; Psychiatry; Stead Family Department of Pediatrics; Iowa Neuroscience Institute; Radiation Oncology; The Iowa Institute for Biomedical Imaging; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Ophthalmology and Visual Sciences
Record Identifier: 9984070122902771

Metrics

23 Record Views

19 Times Cited - Web of Science