1
|
Li G, Zheng C, Cui Y, Si J, Yang Y, Li J, Lu J. Diagnostic efficacy of complexity metrics from cardiac MRI myocardial segmental motion curves in detecting late gadolinium enhancement in myocardial infarction patients. Heliyon 2024; 10:e31889. [PMID: 38912500 PMCID: PMC11190533 DOI: 10.1016/j.heliyon.2024.e31889] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2024] [Revised: 05/23/2024] [Accepted: 05/23/2024] [Indexed: 06/25/2024] Open
Abstract
Background Myocardial segmental motion is associated with cardiovascular pathology, often assessed through myocardial strain features. The stability of the motion can be influenced by myocardial fibrosis. This research aimed to explore the complexity metrics (CM) of myocardial segmental motion curves, observe their correlation with late gadolinium enhancement (LGE) transmural extension (TE), and assess diagnostic efficacy combined with segmental strains in different TE segments. Methods We included 42 myocardial infarction patients, dividing images into 672 myocardial segments (208 remote, 384 viable, and 80 unviable segments based on TE). Radial and circumferential segmental strain, along with CM for motion curves, were extracted. Correlation between CM and LGE, as well as the potential distinguishing role of CM, was evaluated using Pearson correlation, univariate linear regression (F-test), multivariate regression analysis (T-test), area under curve (AUC), machine learning models, and DeLong test. Results All CMs showed significant linear correlation with TE (P < 0.001). Six CMs were correlated with TE (r > 0.3), with radial frequency drift (FD) displayed the strongest correlation (r = 0.496, P < 0.001). Radial and circumferential FD significantly differed in higher TE myocardium than in remote segments (P < 0.05). Radial FD had practical diagnostic efficacy (remote vs. unviable AUC = 0.89, viable vs. unviable AUC = 0.77, remote vs. viable AUC = 0.65). Combining CM with segmental strain features boosted diagnostic efficacy than models using only segmental strain features (DeLong test, P < 0.05). Conclusions The CM of myocardial motion curves has been associated with LGE infarction, and combining CM with strain features improves the diagnosis of different myocardial LGE infarction degrees.
Collapse
Affiliation(s)
- Geng Li
- Department of Radiology and Nuclear Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China
- Beijing Key Laboratory of Magnetic Resonance Imaging and Brain Informatics, Beijing, China
| | - Chong Zheng
- Department of Radiology and Nuclear Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China
- Beijing Key Laboratory of Magnetic Resonance Imaging and Brain Informatics, Beijing, China
| | - Yadong Cui
- Department of Radiology and Nuclear Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China
- Beijing Key Laboratory of Magnetic Resonance Imaging and Brain Informatics, Beijing, China
| | - Jin Si
- Department of Geriatrics, Xuanwu Hospital, Capital Medical University, National Clinical Research Center for Geriatric Diseases, Beijing, China
| | - Yang Yang
- Beijing United Imaging Research Institute of Intelligent Imaging, Beijing, China
| | - Jing Li
- Department of Geriatrics, Xuanwu Hospital, Capital Medical University, National Clinical Research Center for Geriatric Diseases, Beijing, China
| | - Jie Lu
- Department of Radiology and Nuclear Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China
- Beijing Key Laboratory of Magnetic Resonance Imaging and Brain Informatics, Beijing, China
| |
Collapse
|
2
|
Ribeiro MAO, Nunes FLS. Left ventricle segmentation combining deep learning and deformable models with anatomical constraints. J Biomed Inform 2023; 142:104366. [PMID: 37086958 DOI: 10.1016/j.jbi.2023.104366] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2022] [Revised: 03/19/2023] [Accepted: 04/17/2023] [Indexed: 04/24/2023]
Abstract
Segmentation of the left ventricle is a key approach in Cardiac Magnetic Resonance Imaging for calculating biomarkers in diagnosis. Since there is substantial effort required from the expert, many automatic segmentation methods have been proposed, in which deep learning networks have obtained remarkable performance. However, one of the main limitations of these approaches is the production of segmentations that contain anatomical errors. To avoid this limitation, we propose a new fully-automatic left ventricle segmentation method combining deep learning and deformable models. We propose a new level set energy formulation that includes exam-specific information estimated from the deep learning segmentation and shape constraints. The method is part of a pipeline containing pre-processing steps and a failure correction post-processing step. Experiments were conducted with the Sunnybrook and ACDC public datasets, and a private dataset. Results suggest that the method is competitive, that it can produce anatomically consistent segmentations, has good generalization ability, and is often able to estimate biomarkers close to the expert.
Collapse
Affiliation(s)
- Matheus A O Ribeiro
- University of São Paulo, Rua Arlindo Bettio, 1000, Vila Guaraciaba, São Paulo, 01000-000, São Paulo, Brazil.
| | - Fátima L S Nunes
- University of São Paulo, Rua Arlindo Bettio, 1000, Vila Guaraciaba, São Paulo, 01000-000, São Paulo, Brazil.
| |
Collapse
|
3
|
Non-contrast Cine Cardiac Magnetic Resonance image radiomics features and machine learning algorithms for myocardial infarction detection. Comput Biol Med 2021; 141:105145. [PMID: 34929466 DOI: 10.1016/j.compbiomed.2021.105145] [Citation(s) in RCA: 24] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2021] [Accepted: 12/13/2021] [Indexed: 12/22/2022]
Abstract
OBJECTIVE Robust differentiation between infarcted and normal tissue is important for clinical diagnosis and precision medicine. The aim of this work is to investigate the radiomic features and to develop a machine learning algorithm for the differentiation of myocardial infarction (MI) and viable tissues/normal cases in the left ventricular myocardium on non-contrast Cine Cardiac Magnetic Resonance (Cine-CMR) images. METHODS Seventy-two patients (52 with MI and 20 healthy control patients) were enrolled in this study. MR imaging was performed on a 1.5 T MRI using the following parameters: TR = 43.35 ms, TE = 1.22 ms, flip angle = 65°, temporal resolution of 30-40 ms. N4 bias field correction algorithm was applied to correct the inhomogeneity of images. All images were segmented and verified simultaneously by two cardiac imaging experts in consensus. Subsequently, features extraction was performed within the whole left ventricular myocardium (3D volume) in end-diastolic volume phase. Re-sampling to 1 × 1 × 1 mm3 voxels was performed for MR images. All intensities within the VOI of MR images were discretized to 64 bins. Radiomic features were normalized to obtain Z-scores, followed by Student's t-test statistical analysis for comparison. A p-value < 0.05 was used as a threshold for statistically significant differences and false discovery rate (FDR) correction performed to report q-value (FDR adjusted p-value). The extracted features were ranked using the MSVM-RFE algorithm, then Spearman correlation between features was performed to eliminate highly correlated features (R2 > 0.80). Ten different machine learning algorithms were used for classification and different metrics used for evaluation and various parameters used for models' evaluation. RESULTS In univariate analysis, the highest area under the curve (AUC) of receiver operating characteristic (ROC) value was achieved for the Maximum 2D diameter slice (M2DS) shape feature (AUC = 0.88, q-value = 1.02E-7), while the average of univariate AUCs was 0.62 ± 0.08. In multivariate analysis, Logistic Regression (AUC = 0.93 ± 0.03, Accuracy = 0.86 ± 0.05, Recall = 0.87 ± 0.1, Precision = 0.93 ± 0.03 and F1 Score = 0.90 ± 0.04) and SVM (AUC = 0.92 ± 0.05, Accuracy = 0.85 ± 0.04, Recall = 0.92 ± 0.01, Precision = 0.88 ± 0.04 and F1 Score = 0.90 ± 0.02) yielded optimal performance as the best machine learning algorithm for this radiomics analysis. CONCLUSION This study demonstrated that using radiomics analysis on non-contrast Cine-CMR images enables to accurately detect MI, which could potentially be used as an alternative diagnostic method for Late Gadolinium Enhancement Cardiac Magnetic Resonance (LGE-CMR).
Collapse
|
4
|
Liu L, Wolterink JM, Brune C, Veldhuis RNJ. Anatomy-aided deep learning for medical image segmentation: a review. Phys Med Biol 2021; 66. [PMID: 33906186 DOI: 10.1088/1361-6560/abfbf4] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2021] [Accepted: 04/27/2021] [Indexed: 01/17/2023]
Abstract
Deep learning (DL) has become widely used for medical image segmentation in recent years. However, despite these advances, there are still problems for which DL-based segmentation fails. Recently, some DL approaches had a breakthrough by using anatomical information which is the crucial cue for manual segmentation. In this paper, we provide a review of anatomy-aided DL for medical image segmentation which covers systematically summarized anatomical information categories and corresponding representation methods. We address known and potentially solvable challenges in anatomy-aided DL and present a categorized methodology overview on using anatomical information with DL from over 70 papers. Finally, we discuss the strengths and limitations of the current anatomy-aided DL approaches and suggest potential future work.
Collapse
Affiliation(s)
- Lu Liu
- Applied Analysis, Department of Applied Mathematics, Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Drienerlolaan 5, 7522 NB, Enschede, The Netherlands.,Data Management and Biometrics, Department of Computer Science, Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Drienerlolaan 5, 7522 NB, Enschede, The Netherlands
| | - Jelmer M Wolterink
- Applied Analysis, Department of Applied Mathematics, Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Drienerlolaan 5, 7522 NB, Enschede, The Netherlands
| | - Christoph Brune
- Applied Analysis, Department of Applied Mathematics, Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Drienerlolaan 5, 7522 NB, Enschede, The Netherlands
| | - Raymond N J Veldhuis
- Data Management and Biometrics, Department of Computer Science, Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Drienerlolaan 5, 7522 NB, Enschede, The Netherlands
| |
Collapse
|
5
|
Xiong J, Po LM, Cheung KW, Xian P, Zhao Y, Rehman YAU, Zhang Y. Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning. SENSORS (BASEL, SWITZERLAND) 2021; 21:2375. [PMID: 33805558 PMCID: PMC8037138 DOI: 10.3390/s21072375] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/21/2021] [Revised: 03/25/2021] [Accepted: 03/26/2021] [Indexed: 12/18/2022]
Abstract
Deep reinforcement learning (DRL) has been utilized in numerous computer vision tasks, such as object detection, autonomous driving, etc. However, relatively few DRL methods have been proposed in the area of image segmentation, particularly in left ventricle segmentation. Reinforcement learning-based methods in earlier works often rely on learning proper thresholds to perform segmentation, and the segmentation results are inaccurate due to the sensitivity of the threshold. To tackle this problem, a novel DRL agent is designed to imitate the human process to perform LV segmentation. For this purpose, we formulate the segmentation problem as a Markov decision process and innovatively optimize it through DRL. The proposed DRL agent consists of two neural networks, i.e., First-P-Net and Next-P-Net. The First-P-Net locates the initial edge point, and the Next-P-Net locates the remaining edge points successively and ultimately obtains a closed segmentation result. The experimental results show that the proposed model has outperformed the previous reinforcement learning methods and achieved comparable performances compared with deep learning baselines on two widely used LV endocardium segmentation datasets, namely Automated Cardiac Diagnosis Challenge (ACDC) 2017 dataset, and Sunnybrook 2009 dataset. Moreover, the proposed model achieves higher F-measure accuracy compared with deep learning methods when training with a very limited number of samples.
Collapse
Affiliation(s)
- Jingjing Xiong
- Department of Electrical Engineering, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong Kong, China; (L.-M.P.); (P.X.); (Y.Z.); (Y.Z.)
| | - Lai-Man Po
- Department of Electrical Engineering, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong Kong, China; (L.-M.P.); (P.X.); (Y.Z.); (Y.Z.)
| | - Kwok Wai Cheung
- School of Communication, The Hang Seng University of Hong Kong, Hang Shin Link, Siu Lek Yuen, Shatin, Hong Kong, China;
| | - Pengfei Xian
- Department of Electrical Engineering, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong Kong, China; (L.-M.P.); (P.X.); (Y.Z.); (Y.Z.)
| | - Yuzhi Zhao
- Department of Electrical Engineering, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong Kong, China; (L.-M.P.); (P.X.); (Y.Z.); (Y.Z.)
| | - Yasar Abbas Ur Rehman
- TCL Corporate Research (HK) Co., Ltd., 22 Science Park East Avenue, Shatin, Hong Kong, China;
| | - Yujia Zhang
- Department of Electrical Engineering, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong Kong, China; (L.-M.P.); (P.X.); (Y.Z.); (Y.Z.)
| |
Collapse
|