1
|
Ding J, Zhou R, Fang X, Wang F, Wang J, Gan H, Fenster A. An image registration-based self-supervised Su-Net for carotid plaque ultrasound image segmentation. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 244:107957. [PMID: 38061113 DOI: 10.1016/j.cmpb.2023.107957] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/12/2022] [Revised: 11/17/2023] [Accepted: 11/27/2023] [Indexed: 01/26/2024]
Abstract
BACKGROUND AND OBJECTIVES Total Plaque Area (TPA) measurement is critical for early diagnosis and intervention of carotid atherosclerosis in individuals with high risk for stroke. The delineation of the carotid plaques is necessary for TPA measurement, and deep learning methods can automatically segment the plaque and measure TPA from carotid ultrasound images. A large number of labeled images is essential for training a good deep learning model, but it is very difficult to collect such large labeled datasets for carotid image segmentation in clinical practice. Self-supervised learning can provide a possible solution to improve the deep-learning models on small labeled training datasets by designing a pretext task to pre-train the models without using the segmentation masks. However, the existing self-supervised learning methods do not consider the feature presentations of object contours. METHODS In this paper, we propose an image registration-based self-supervised learning method and a stacked U-Net (SSL-SU-Net) for carotid plaque ultrasound image segmentation, which can better exploit the semantic features of carotid plaque contours in self-supervised task training. RESULTS Our network was trained on different numbers of labeled images (n = 10, 33, 50 and 100 subjects) and tested on 44 subjects from the SPARC dataset (n = 144, London, Canada). The network trained on the entire SPARC dataset was then directly applied to an independent dataset collected in Zhongnan hospital (n = 497, Wuhan, China). For the 44 subjects tested on the SPARC dataset, our method yielded a DSC of 80.25-89.18% and the produced TPA measurements, which were strongly correlated with manual segmentation (r = 0.965-0.995, ρ< 0.0001). For the Zhongnan dataset, the DSC was 90.3% and algorithm TPAs were strongly correlated with manual TPAs (r = 0.985, ρ< 0.0001). CONCLUSIONS The results demonstrate that our proposed method yielded excellent performance and good generalization ability when trained on a small labeled dataset, facilitating the use of deep learning in carotid ultrasound image analysis and clinical practice. The code of our algorithm is available https://github.com/a610lab/Registration-SSL.
Collapse
Affiliation(s)
- Jing Ding
- School of Computer Science, Hubei University of Technology, Wuhan, Hubei 430068, China
| | - Ran Zhou
- School of Computer Science, Hubei University of Technology, Wuhan, Hubei 430068, China.
| | - Xiaoyue Fang
- School of Computer Science, Hubei University of Technology, Wuhan, Hubei 430068, China
| | - Furong Wang
- Liyuan Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
| | - Ji Wang
- School of Computer Science, Hubei University of Technology, Wuhan, Hubei 430068, China
| | - Haitao Gan
- School of Computer Science, Hubei University of Technology, Wuhan, Hubei 430068, China.
| | - Aaron Fenster
- Imaging Research Laboratories, Robarts Research Institute, Western University, London N6A 5K8, Ontario, Canada
| |
Collapse
|
2
|
Kiernan MJ, Al Mukaddim R, Mitchell CC, Maybock J, Wilbrand SM, Dempsey RJ, Varghese T. Lumen segmentation using a Mask R-CNN in carotid arteries with stenotic atherosclerotic plaque. ULTRASONICS 2024; 137:107193. [PMID: 37952384 PMCID: PMC10841729 DOI: 10.1016/j.ultras.2023.107193] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/20/2023] [Revised: 09/19/2023] [Accepted: 10/29/2023] [Indexed: 11/14/2023]
Abstract
In patients at high risk for ischemic stroke, clinical carotid ultrasound is often used to grade stenosis, determine plaque burden and assess stroke risk. Analysis currently requires a trained sonographer to manually identify vessel and plaque regions, which is time and labor intensive. We present a method for automatically determining bounding boxes and lumen segmentation using a Mask R-CNN network trained on sonographer assisted ground-truth carotid lumen segmentations. Automatic lumen segmentation also lays the groundwork for developing methods for accurate plaque segmentation, and wall thickness measurements in cases with no plaque. Different training schemes are used to identify the Mask R-CNN model with the highest accuracy. Utilizing a single-channel B-mode training input, our model produces a mean bounding box intersection over union (IoU) of 0.81 and a mean lumen segmentation IoU of 0.75. However, we encountered errors in prediction when the jugular vein is the most prominently visualized vessel in the B-mode image. This was due to the fact that our dataset has limited instances of B-mode images with both the jugular vein and carotid artery where the vein is dominantly visualized. Additional training datasets are anticipated to mitigate this issue.
Collapse
Affiliation(s)
- Maxwell J Kiernan
- Department of Medical Physics, University of Wisconsin School of Medicine and Public Health (UW-SMPH), United States.
| | - Rashid Al Mukaddim
- Department of Medical Physics, University of Wisconsin School of Medicine and Public Health (UW-SMPH), United States
| | | | - Jenna Maybock
- Department of Neurological Surgery, UW-SMPH. Madison, WI, United States
| | | | - Robert J Dempsey
- Department of Neurological Surgery, UW-SMPH. Madison, WI, United States
| | - Tomy Varghese
- Department of Medical Physics, University of Wisconsin School of Medicine and Public Health (UW-SMPH), United States.
| |
Collapse
|
3
|
Wang Q, Lai MW, Bin G, Ding Q, Wu S, Zhou Z, Tsui PH. MBR-Net: A multi-branch residual network based on ultrasound backscattered signals for characterizing pediatric hepatic steatosis. ULTRASONICS 2023; 135:107093. [PMID: 37482038 DOI: 10.1016/j.ultras.2023.107093] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/13/2023] [Revised: 05/18/2023] [Accepted: 06/23/2023] [Indexed: 07/25/2023]
Abstract
The evaluation of pediatric hepatic steatosis and early detection of fatty liver in children are of critical importance. In this paper, a deep learning model based on the convolutional neural network (CNN) of ultrasound backscattered signals, multi-branch residual network (MBR-Net), was proposed for characterizing pediatric hepatic steatosis. The MBR-Net was composed of three convolutional branches. Each branch used different sizes of convolution blocks to enhance the capability of local feature acquisition, and leveraged the residual mechanism with skip connections to guide the network to effectively capture features. A total of 393 frames of ultrasound backscattered signals collected from 131 children were included in the experiments. The hepatic steatosis index was used as the reference standard for diagnosing the steatosis grade, G0-G3. The ultrasound backscattered signals within the liver region of interests (ROIs) were normalized and augmented using a sliding gate method. The gated ROI signals were randomly divided into training, validation, and test sets with the ratio of 8:1:1. The area under the operating characteristic curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE) were used as the evaluation metrics. Experimental results showed that the MBR-Net yields AUCs for diagnosing pediatric hepatic steatosis grade ≥G1, ≥G2, and ≥G3 of 0.94 (ACC: 93.65%; SEN: 89.79%; SPE: 84.48%), 0.93 (ACC: 90.48%; SEN: 87.75%; SPE: 82.65%), and 0.93 (ACC: 87.76%; SEN: 84.84%; SPE: 86.55%), respectively, which were superior to the conventional one-branch CNNs without residual mechanisms. The proposed MBR-Net can be used as a new deep learning method for ultrasound backscattered signal analysis to characterize pediatric hepatic steatosis.
Collapse
Affiliation(s)
- Qian Wang
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing, China
| | - Ming-Wei Lai
- Division of Pediatric Gastroenterology, Department of Pediatrics, Chang Gung Children's Medical Center, Chang Gung Memorial Hospital, Linkou, College of Medicine, Chang Gung University, Taoyuan, Taiwan; Liver Research Center, Chang Gung Memorial Hospital, Linkou, Taoyuan, Taiwan
| | - Guangyu Bin
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing, China
| | - Qiying Ding
- Department of Ultrasound, BJUT Hospital, Beijing University of Technology, Beijing, China
| | - Shuicai Wu
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing, China
| | - Zhuhuang Zhou
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing, China.
| | - Po-Hsiang Tsui
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan; Institute for Radiological Research, Chang Gung University, Taoyuan, Taiwan; Division of Pediatric Gastroenterology, Department of Pediatrics, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan.
| |
Collapse
|
4
|
Chen YF, Chen ZJ, Lin YY, Lin ZQ, Chen CN, Yang ML, Zhang JY, Li YZ, Wang Y, Huang YH. Stroke risk study based on deep learning-based magnetic resonance imaging carotid plaque automatic segmentation algorithm. Front Cardiovasc Med 2023; 10:1101765. [PMID: 36910524 PMCID: PMC9998982 DOI: 10.3389/fcvm.2023.1101765] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2022] [Accepted: 01/10/2023] [Indexed: 02/26/2023] Open
Abstract
Introduction The primary factor for cardiovascular disease and upcoming cardiovascular events is atherosclerosis. Recently, carotid plaque texture, as observed on ultrasonography, is varied and difficult to classify with the human eye due to substantial inter-observer variability. High-resolution magnetic resonance (MR) plaque imaging offers naturally superior soft tissue contrasts to computed tomography (CT) and ultrasonography, and combining different contrast weightings may provide more useful information. Radiation freeness and operator independence are two additional benefits of M RI. However, other than preliminary research on MR texture analysis of basilar artery plaque, there is currently no information addressing MR radiomics on the carotid plaque. Methods For the automatic segmentation of MRI scans to detect carotid plaque for stroke risk assessment, there is a need for a computer-aided autonomous framework to classify MRI scans automatically. We used to detect carotid plaque from MRI scans for stroke risk assessment pre-trained models, fine-tuned them, and adjusted hyperparameters according to our problem. Results Our trained YOLO V3 model achieved 94.81% accuracy, RCNN achieved 92.53% accuracy, and MobileNet achieved 90.23% in identifying carotid plaque from MRI scans for stroke risk assessment. Our approach will prevent incorrect diagnoses brought on by poor image quality and personal experience. Conclusion The evaluations in this work have demonstrated that this methodology produces acceptable results for classifying magnetic resonance imaging (MRI) data.
Collapse
Affiliation(s)
- Ya-Fang Chen
- Department of Neurology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, China
| | - Zhen-Jie Chen
- Department of Neurology, Anxi County Hospital, Quanzhou, Fujian, China
| | - You-Yu Lin
- Department of Neurology, Jinjiang Municipal Hospital, Shanghai Sixth People’s Hospital Fujian Campus, Quanzhou, Fujian, China
| | - Zhi-Qiang Lin
- Department of Neurology, Jinjiang Municipal Hospital, Shanghai Sixth People’s Hospital Fujian Campus, Quanzhou, Fujian, China
| | - Chun-Nuan Chen
- Department of Neurology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, China
| | - Mei-Li Yang
- Department of Neurology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, China
| | - Jin-Yin Zhang
- Department of Neurology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, China
| | - Yuan-zhe Li
- Department of CT/MRI, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, China
| | - Yi Wang
- Department of CT/MRI, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, China
| | - Yin-Hui Huang
- Department of Neurology, Jinjiang Municipal Hospital, Shanghai Sixth People’s Hospital Fujian Campus, Quanzhou, Fujian, China
| |
Collapse
|