1
|
Cheng H, Zhang J, Gong Y, Pu Z, Jiang J, Chu Y, Xia L. Semantic segmentation method for myocardial contrast echocardiogram based on DeepLabV3+ deep learning architecture. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2023; 20:2081-2093. [PMID: 36899523 DOI: 10.3934/mbe.2023096] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/18/2023]
Abstract
Myocardial contrast echocardiography (MCE) has been proposed as a method to assess myocardial perfusion for the detection of coronary artery diseases in a non-invasive way. As a critical step of automatic MCE perfusion quantification, myocardium segmentation from the MCE frames faces many challenges due to the low image quality and complex myocardial structure. In this paper, a deep learning semantic segmentation method is proposed based on a modified DeepLabV3+ structure with an atrous convolution and atrous spatial pyramid pooling module. The model was trained separately on three chamber views (apical two-chamber view, apical three-chamber view, and apical four-chamber view) on 100 patients' MCE sequences, divided by a proportion of 7:3 into training and testing datasets. The results evaluated by using the dice coefficient (0.84, 0.84, and 0.86 for three chamber views respectively) and Intersection over Union(0.74, 0.72 and 0.75 for three chamber views respectively) demonstrated the better performance of the proposed method compared to other state-of-the-art methods, including the original DeepLabV3+, PSPnet, and U-net. In addition, we conducted a trade-off comparison between model performance and complexity in different depths of the backbone convolution network, which illustrated model application feasibility.
Collapse
Affiliation(s)
- Huan Cheng
- Key Laboratory for Biomedical Engineering of Ministry of Education, Institute of Biomedical Engineering, Zhejiang University, Hangzhou 310027, China
| | - Jucheng Zhang
- Department of Clinical Engineering, School of Medicine, The Second Affiliated Hospital, Zhejiang University, Hangzhou 310009, China
| | - Yinglan Gong
- Institute of Wenzhou, Zhejiang University, Wenzhou 325036, China
| | - Zhaoxia Pu
- Department of Cardiology, School of Medicine, The Second Affiliated Hospital, Zhejiang University, Hangzhou 310009, China
| | - Jun Jiang
- Department of Cardiology, School of Medicine, The Second Affiliated Hospital, Zhejiang University, Hangzhou 310009, China
| | - Yonghua Chu
- Department of Clinical Engineering, School of Medicine, The Second Affiliated Hospital, Zhejiang University, Hangzhou 310009, China
| | - Ling Xia
- Key Laboratory for Biomedical Engineering of Ministry of Education, Institute of Biomedical Engineering, Zhejiang University, Hangzhou 310027, China
| |
Collapse
|
2
|
Chen Y, Xie W, Zhang J, Qiu H, Zeng D, Shi Y, Yuan H, Zhuang J, Jia Q, Zhang Y, Dong Y, Huang M, Xu X. Myocardial Segmentation of Cardiac MRI Sequences With Temporal Consistency for Coronary Artery Disease Diagnosis. Front Cardiovasc Med 2022; 9:804442. [PMID: 35282363 PMCID: PMC8914019 DOI: 10.3389/fcvm.2022.804442] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/02/2021] [Accepted: 01/07/2022] [Indexed: 11/13/2022] Open
Abstract
Coronary artery disease (CAD) is the most common cause of death globally, and its diagnosis is usually based on manual myocardial (MYO) segmentation of MRI sequences. As manual segmentation is tedious, time-consuming, and with low replicability, automatic MYO segmentation using machine learning techniques has been widely explored recently. However, almost all the existing methods treat the input MRI sequences independently, which fails to capture the temporal information between sequences, e.g., the shape and location information of the myocardium in sequences along time. In this article, we propose a MYO segmentation framework for sequence of cardiac MRI (CMR) scanning images of the left ventricular (LV) cavity, right ventricular (RV) cavity, and myocardium. Specifically, we propose to combine conventional neural networks and recurrent neural networks to incorporate temporal information between sequences to ensure temporal consistency. We evaluated our framework on the automated cardiac diagnosis challenge (ACDC) dataset. The experiment results demonstrate that our framework can improve the segmentation accuracy by up to 2% in the Dice coefficient.
Collapse
Affiliation(s)
- Yutian Chen
- Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Guangdong Provincial Key Laboratory of South China Structural Heart Disease, Guangdong Cardiovascular Institute, Guangzhou, China
- Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA, United States
| | - Wen Xie
- Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Guangdong Provincial Key Laboratory of South China Structural Heart Disease, Guangdong Cardiovascular Institute, Guangzhou, China
| | - Jiawei Zhang
- Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Guangdong Provincial Key Laboratory of South China Structural Heart Disease, Guangdong Cardiovascular Institute, Guangzhou, China
- Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China
- Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China
| | - Hailong Qiu
- Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Guangdong Provincial Key Laboratory of South China Structural Heart Disease, Guangdong Cardiovascular Institute, Guangzhou, China
| | - Dewen Zeng
- Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, United States
| | - Yiyu Shi
- Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, United States
| | - Haiyun Yuan
- Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Guangdong Provincial Key Laboratory of South China Structural Heart Disease, Guangdong Cardiovascular Institute, Guangzhou, China
| | - Jian Zhuang
- Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Guangdong Provincial Key Laboratory of South China Structural Heart Disease, Guangdong Cardiovascular Institute, Guangzhou, China
| | - Qianjun Jia
- Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Department of Catheterization Lab, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
| | - Yanchun Zhang
- Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China
| | - Yuhao Dong
- Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Guangdong Provincial Key Laboratory of South China Structural Heart Disease, Guangdong Cardiovascular Institute, Guangzhou, China
- Department of Catheterization Lab, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- *Correspondence: Yuhao Dong
| | - Meiping Huang
- Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Guangdong Provincial Key Laboratory of South China Structural Heart Disease, Guangdong Cardiovascular Institute, Guangzhou, China
- Department of Catheterization Lab, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Meiping Huang
| | - Xiaowei Xu
- Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Guangdong Provincial Key Laboratory of South China Structural Heart Disease, Guangdong Cardiovascular Institute, Guangzhou, China
- Xiaowei Xu
| |
Collapse
|
3
|
Mamalakis M, Garg P, Nelson T, Lee J, Wild JM, Clayton RH. MA-SOCRATIS: An automatic pipeline for robust segmentation of the left ventricle and scar. Comput Med Imaging Graph 2021; 93:101982. [PMID: 34481237 DOI: 10.1016/j.compmedimag.2021.101982] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2021] [Revised: 08/19/2021] [Accepted: 08/23/2021] [Indexed: 11/18/2022]
Abstract
Multi-atlas segmentation of cardiac regions and total infarct scar (MA-SOCRATIS) is an unsupervised automatic pipeline to segment left ventricular myocardium and scar from late gadolinium enhanced MR images (LGE-MRI) of the heart. We implement two different pipelines for myocardial and scar segmentation from short axis LGE-MRI. Myocardial segmentation has two steps; initial segmentation and re-estimation. The initial segmentation step makes a first estimate of myocardium boundaries by using multi-atlas segmentation techniques. The re-estimation step refines the myocardial segmentation by a combination of k-means clustering and a geometric median shape variation technique. An active contour technique determines the unhealthy and healthy myocardial wall. The scar segmentation pipeline is a combination of a Rician-Gaussian mixture model and full width at half maximum (FWHM) thresholding, to determine the intensity pixels in scar regions. Following this step a watershed method with an automatic seed-points framework segments the final scar region. MA-SOCRATIS was evaluated using two different datasets. In both datasets ground truths were based on manual segmentation of short axis images from LGE-MRI scans. The first dataset included 40 patients from the MS-CMRSeg 2019 challenge dataset (STACOM at MICCAI 2019). The second is a collection of 20 patients with scar regions that are challenging to segment. MA-SOCRATIS achieved robust and accurate performance in automatic segmentation of myocardium and scar regions without the need of training or tuning in both cohorts, compared with state-of-the-art techniques (intra-observer and inter observer myocardium segmentation: 81.9% and 70% average Dice value, and scar (intra-observer and inter observer segmentation: 70.5% and 70.5% average Dice value).
Collapse
Affiliation(s)
- Michail Mamalakis
- Insigneo Institute for In-Silico Medicine, University of Sheffield, Sheffield, UK; Department of Computer Science, University of Sheffield, Regent Court, Sheffield S1 4DP, UK.
| | - Pankaj Garg
- Department of Cardiology, Sheffield Teaching Hospitals NHS Trust, Sheffield S5 7AU, UK
| | - Tom Nelson
- Department of Cardiology, Sheffield Teaching Hospitals NHS Trust, Sheffield S5 7AU, UK
| | - Justin Lee
- Department of Cardiology, Sheffield Teaching Hospitals NHS Trust, Sheffield S5 7AU, UK
| | - Jim M Wild
- Insigneo Institute for In-Silico Medicine, University of Sheffield, Sheffield, UK; Polaris, Imaging Sciences, Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Richard H Clayton
- Insigneo Institute for In-Silico Medicine, University of Sheffield, Sheffield, UK; Department of Computer Science, University of Sheffield, Regent Court, Sheffield S1 4DP, UK
| |
Collapse
|