Radiomics-Based Quality Control System for Automatic Cardiac Segmentation: A Feasibility Study
Purpose: In the past decade, there has been a rapid increase in the development of automatic cardiac segmentation methods. However, the automatic quality control (QC) of these segmentation methods has received less attention. This study aims to address this gap by developing an automatic pipeline th...
| Những tác giả chính: | , , , , , , |
|---|---|
| Định dạng: | Bài viết |
| Ngôn ngữ: | English |
| Được phát hành: |
MDPI AG
2023-07-01
|
| Loạt: | Bioengineering |
| Những chủ đề: | |
| Truy cập trực tuyến: | https://www.mdpi.com/2306-5354/10/7/791 |
| _version_ | 1827733906712952832 |
|---|---|
| author | Qiming Liu Qifan Lu Yezi Chai Zhengyu Tao Qizhen Wu Meng Jiang Jun Pu |
| author_facet | Qiming Liu Qifan Lu Yezi Chai Zhengyu Tao Qizhen Wu Meng Jiang Jun Pu |
| author_sort | Qiming Liu |
| collection | DOAJ |
| description | Purpose: In the past decade, there has been a rapid increase in the development of automatic cardiac segmentation methods. However, the automatic quality control (QC) of these segmentation methods has received less attention. This study aims to address this gap by developing an automatic pipeline that incorporates DL-based cardiac segmentation and radiomics-based quality control. Methods: In the DL-based localization and segmentation part, the entire heart was first located and cropped. Then, the cropped images were further utilized for the segmentation of the right ventricle cavity (RVC), myocardium (MYO), and left ventricle cavity (LVC). As for the radiomics-based QC part, a training radiomics dataset was created with segmentation tasks of various quality. This dataset was used for feature extraction, selection, and QC model development. The model performance was then evaluated using both internal and external testing datasets. Results: In the internal testing dataset, the segmentation model demonstrated a great performance with a dice similarity coefficient (DSC) of 0.954 for whole heart segmentations. Images were then appropriately cropped to 160 × 160 pixels. The models also performed well for cardiac substructure segmentations. The DSC values were 0.863, 0.872, and 0.940 for RVC, MYO, and LVC for 2D masks and 0.928, 0.886, and 0.962 for RVC, MYO, and LVC for 3D masks with an attention-UNet. After feature selection with the radiomics dataset, we developed a series of models to predict the automatic segmentation quality and its DSC value for the RVC, MYO, and LVC structures. The mean absolute values for our best prediction models were 0.060, 0.032, and 0.021 for 2D segmentations and 0.027, 0.017, and 0.011 for 3D segmentations, respectively. Additionally, the radiomics-based classification models demonstrated a high negative detection rate of >0.85 in all 2D groups. In the external dataset, models showed similar results. Conclusions: We developed a pipeline including cardiac substructure segmentation and QC at both the slice (2D) and subject (3D) levels. Our results demonstrate that the radiomics method possesses great potential for the automatic QC of cardiac segmentation. |
| first_indexed | 2024-03-11T01:18:07Z |
| format | Article |
| id | doaj.art-f1e14a00cd6e441bbeadc7b8fb79a01b |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-11T01:18:07Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-f1e14a00cd6e441bbeadc7b8fb79a01b2023-11-18T18:21:25ZengMDPI AGBioengineering2306-53542023-07-0110779110.3390/bioengineering10070791Radiomics-Based Quality Control System for Automatic Cardiac Segmentation: A Feasibility StudyQiming Liu0Qifan Lu1Yezi Chai2Zhengyu Tao3Qizhen Wu4Meng Jiang5Jun Pu6Department of Cardiology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200120, ChinaDepartment of Cardiology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200120, ChinaDepartment of Cardiology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200120, ChinaDepartment of Cardiology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200120, ChinaDepartment of Cardiology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200120, ChinaDepartment of Cardiology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200120, ChinaDepartment of Cardiology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200120, ChinaPurpose: In the past decade, there has been a rapid increase in the development of automatic cardiac segmentation methods. However, the automatic quality control (QC) of these segmentation methods has received less attention. This study aims to address this gap by developing an automatic pipeline that incorporates DL-based cardiac segmentation and radiomics-based quality control. Methods: In the DL-based localization and segmentation part, the entire heart was first located and cropped. Then, the cropped images were further utilized for the segmentation of the right ventricle cavity (RVC), myocardium (MYO), and left ventricle cavity (LVC). As for the radiomics-based QC part, a training radiomics dataset was created with segmentation tasks of various quality. This dataset was used for feature extraction, selection, and QC model development. The model performance was then evaluated using both internal and external testing datasets. Results: In the internal testing dataset, the segmentation model demonstrated a great performance with a dice similarity coefficient (DSC) of 0.954 for whole heart segmentations. Images were then appropriately cropped to 160 × 160 pixels. The models also performed well for cardiac substructure segmentations. The DSC values were 0.863, 0.872, and 0.940 for RVC, MYO, and LVC for 2D masks and 0.928, 0.886, and 0.962 for RVC, MYO, and LVC for 3D masks with an attention-UNet. After feature selection with the radiomics dataset, we developed a series of models to predict the automatic segmentation quality and its DSC value for the RVC, MYO, and LVC structures. The mean absolute values for our best prediction models were 0.060, 0.032, and 0.021 for 2D segmentations and 0.027, 0.017, and 0.011 for 3D segmentations, respectively. Additionally, the radiomics-based classification models demonstrated a high negative detection rate of >0.85 in all 2D groups. In the external dataset, models showed similar results. Conclusions: We developed a pipeline including cardiac substructure segmentation and QC at both the slice (2D) and subject (3D) levels. Our results demonstrate that the radiomics method possesses great potential for the automatic QC of cardiac segmentation.https://www.mdpi.com/2306-5354/10/7/791radiomicsdeep learningquality controlcardiac magnetic resonance |
| spellingShingle | Qiming Liu Qifan Lu Yezi Chai Zhengyu Tao Qizhen Wu Meng Jiang Jun Pu Radiomics-Based Quality Control System for Automatic Cardiac Segmentation: A Feasibility Study Bioengineering radiomics deep learning quality control cardiac magnetic resonance |
| title | Radiomics-Based Quality Control System for Automatic Cardiac Segmentation: A Feasibility Study |
| title_full | Radiomics-Based Quality Control System for Automatic Cardiac Segmentation: A Feasibility Study |
| title_fullStr | Radiomics-Based Quality Control System for Automatic Cardiac Segmentation: A Feasibility Study |
| title_full_unstemmed | Radiomics-Based Quality Control System for Automatic Cardiac Segmentation: A Feasibility Study |
| title_short | Radiomics-Based Quality Control System for Automatic Cardiac Segmentation: A Feasibility Study |
| title_sort | radiomics based quality control system for automatic cardiac segmentation a feasibility study |
| topic | radiomics deep learning quality control cardiac magnetic resonance |
| url | https://www.mdpi.com/2306-5354/10/7/791 |
| work_keys_str_mv | AT qimingliu radiomicsbasedqualitycontrolsystemforautomaticcardiacsegmentationafeasibilitystudy AT qifanlu radiomicsbasedqualitycontrolsystemforautomaticcardiacsegmentationafeasibilitystudy AT yezichai radiomicsbasedqualitycontrolsystemforautomaticcardiacsegmentationafeasibilitystudy AT zhengyutao radiomicsbasedqualitycontrolsystemforautomaticcardiacsegmentationafeasibilitystudy AT qizhenwu radiomicsbasedqualitycontrolsystemforautomaticcardiacsegmentationafeasibilitystudy AT mengjiang radiomicsbasedqualitycontrolsystemforautomaticcardiacsegmentationafeasibilitystudy AT junpu radiomicsbasedqualitycontrolsystemforautomaticcardiacsegmentationafeasibilitystudy |