1
|
Wu J, Xin J, Yang X, Matkovic LA, Zhao X, Zheng N, Li R. Segmentation of carotid artery vessel wall and diagnosis of carotid atherosclerosis on black blood magnetic resonance imaging with multi-task learning. Med Phys 2024; 51:1775-1797. [PMID: 37681965 DOI: 10.1002/mp.16728] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2023] [Revised: 07/04/2023] [Accepted: 07/29/2023] [Indexed: 09/09/2023] Open
Abstract
BACKGROUND Atherosclerotic cardiovascular disease is the leading cause of death worldwide. Early detection of carotid atherosclerosis can prevent the progression of cardiovascular disease. Many (semi-) automatic methods have been designed for the segmentation of carotid vessel wall and the diagnosis of carotid atherosclerosis (i.e., the lumen segmentation, the outer wall segmentation, and the carotid atherosclerosis diagnosis) on black blood magnetic resonance imaging (BB-MRI). However, most of these methods ignore the intrinsic correlation among different tasks on BB-MRI, leading to limited performance. PURPOSE Thus, we model the intrinsic correlation among the lumen segmentation, the outer wall segmentation, and the carotid atherosclerosis diagnosis tasks on BB-MRI by using the multi-task learning technique and propose a gated multi-task network (GMT-Net) to perform three related tasks in a neural network (i.e., carotid artery lumen segmentation, outer wall segmentation, and carotid atherosclerosis diagnosis). METHODS In the proposed method, the GMT-Net is composed of three modules, including the sharing module, the segmentation module, and the diagnosis module, which interact with each other to achieve better learning performance. At the same time, two new adaptive layers, namely, the gated exchange layer and the gated fusion layer, are presented to exchange and merge branch features. RESULTS The proposed method is applied to the CAREII dataset (i.e., 1057 scans) for the lumen segmentation, the outer wall segmentation, and the carotid atherosclerosis diagnosis. The proposed method can achieve promising segmentation performances (0.9677 Dice for the lumen and 0.9669 Dice for the outer wall) and better diagnosis accuracy of carotid atherosclerosis (0.9516 AUC and 0.9024 Accuracy) in the "CAREII test" dataset (i.e., 106 scans). The results show that the proposed method has statistically significant accuracy and efficiency. CONCLUSIONS Even without the intervention of reviewers required for the previous works, the proposed method automatically segments the lumen and outer wall together and diagnoses carotid atherosclerosis with high performance. The proposed method can be used in clinical trials to help radiologists get rid of tedious reading tasks, such as screening review to separate normal carotid arteries from atherosclerotic arteries and to outline vessel wall contours.
Collapse
Affiliation(s)
- Jiayi Wu
- National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University
| | - Jingmin Xin
- National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University
| | - Xiaofeng Yang
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA
| | - Luke A Matkovic
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA
| | - Xihai Zhao
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Nanning Zheng
- National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University
| | - Rui Li
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| |
Collapse
|
2
|
Huang X, Wang J, Li Z. 3D carotid artery segmentation using shape-constrained active contours. Comput Biol Med 2023; 153:106530. [PMID: 36610215 DOI: 10.1016/j.compbiomed.2022.106530] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2022] [Revised: 12/12/2022] [Accepted: 12/31/2022] [Indexed: 01/04/2023]
Abstract
Reconstruction of the carotid artery is demanded in the detection and characterization of atherosclerosis. This study proposes a shape-constrained active contour model for segmenting the carotid artery from MR images, which embeds the output of the deep learning network into the active contour. First the centerline of the carotid artery is localized and then modified active contour initialized from the centerline is used to extract the vessel lumen, finally the probability atlas generated by the deep learning network in polar representation domain is integrated into the active contour as a prior information to detect the outer wall. The results showed that the proposed active contour model was efficient and comparable to manual segmentation.
Collapse
Affiliation(s)
- Xianjue Huang
- School of Biological Science and Medical Engineering, Southeast University, Nanjing, 210096, China
| | - Jun Wang
- First Affiliated Hospital, Nanjing Medical University, Nanjing, 210029, China
| | - Zhiyong Li
- School of Biological Science and Medical Engineering, Southeast University, Nanjing, 210096, China; School of Mechanical, Medical and Process Engineering, Queensland University of Technology, Brisbane, 4000, Australia; Faculty of Sports Science, Ningbo University, Ningbo, 315211, China.
| |
Collapse
|
3
|
Munir K, Frezza F, Rizzi A. Deep Learning Hybrid Techniques for Brain Tumor Segmentation. SENSORS (BASEL, SWITZERLAND) 2022; 22:8201. [PMID: 36365900 PMCID: PMC9658353 DOI: 10.3390/s22218201] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/05/2022] [Revised: 10/17/2022] [Accepted: 10/19/2022] [Indexed: 06/16/2023]
Abstract
Medical images play an important role in medical diagnosis and treatment. Oncologists analyze images to determine the different characteristics of deadly diseases, plan the therapy, and observe the evolution of the disease. The objective of this paper is to propose a method for the detection of brain tumors. Brain tumors are identified from Magnetic Resonance (MR) images by performing suitable segmentation procedures. The latest technical literature concerning radiographic images of the brain shows that deep learning methods can be implemented to extract specific features of brain tumors, aiding clinical diagnosis. For this reason, most data scientists and AI researchers work on Machine Learning methods for designing automatic screening procedures. Indeed, an automated method would result in quicker segmentation findings, providing a robust output with respect to possible differences in data sources, mostly due to different procedures in data recording and storing, resulting in a more consistent identification of brain tumors. To improve the performance of the segmentation procedure, new architectures are proposed and tested in this paper. We propose deep neural networks for the detection of brain tumors, trained on the MRI scans of patients' brains. The proposed architectures are based on convolutional neural networks and inception modules for brain tumor segmentation. A comparison of these proposed architectures with the baseline reference ones shows very interesting results. MI-Unet showed a performance increase in comparison to baseline Unet architecture by 7.5% in dice score, 23.91% insensitivity, and 7.09% in specificity. Depth-wise separable MI-Unet showed a performance increase by 10.83% in dice score, 2.97% in sensitivity, and 12.72% in specificity as compared to the baseline Unet architecture. Hybrid Unet architecture achieved performance improvement of 9.71% in dice score, 3.56% in sensitivity, and 12.6% in specificity. Whereas the depth-wise separable hybrid Unet architecture outperformed the baseline architecture by 15.45% in dice score, 20.56% in sensitivity, and 12.22% in specificity.
Collapse
|
4
|
Jain PK, Sharma N, Saba L, Paraskevas KI, Kalra MK, Johri A, Laird JR, Nicolaides AN, Suri JS. Unseen Artificial Intelligence-Deep Learning Paradigm for Segmentation of Low Atherosclerotic Plaque in Carotid Ultrasound: A Multicenter Cardiovascular Study. Diagnostics (Basel) 2021; 11:2257. [PMID: 34943494 PMCID: PMC8699942 DOI: 10.3390/diagnostics11122257] [Citation(s) in RCA: 24] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2021] [Revised: 11/27/2021] [Accepted: 11/30/2021] [Indexed: 12/12/2022] Open
Abstract
BACKGROUND The early detection of carotid wall plaque is recommended in the prevention of cardiovascular disease (CVD) in moderate-risk patients. Previous techniques for B-mode carotid atherosclerotic wall plaque segmentation used artificial intelligence (AI) methods on monoethnic databases, where training and testing are from the "same" ethnic group ("Seen AI"). Therefore, the versatility of the system is questionable. This is the first study of its kind that uses the "Unseen AI" paradigm where training and testing are from "different" ethnic groups. We hypothesized that deep learning (DL) models should perform in 10% proximity between "Unseen AI" and "Seen AI". METHODOLOGY Two cohorts from multi-ethnic groups (330 Japanese and 300 Hong Kong (HK)) were used for the validation of our hypothesis. We used a four-layered UNet architecture for the segmentation of the atherosclerotic wall with low plaque. "Unseen AI" (training: Japanese, testing: HK or vice versa) and "Seen AI" experiments (single ethnicity or mixed ethnicity) were performed. Evaluation was conducted by measuring the wall plaque area. Statistical tests were conducted for its stability and reliability. RESULTS When using the UNet DL architecture, the "Unseen AI" pair one (Training: 330 Japanese and Testing: 300 HK), the mean accuracy, dice-similarity, and correlation-coefficient were 98.55, 78.38, and 0.80 (p < 0.0001), respectively, while for "Unseen AI" pair two (Training: 300 HK and Testing: 330 Japanese), these were 98.67, 82.49, and 0.87 (p < 0.0001), respectively. Using "Seen AI", the same parameters were 99.01, 86.89 and 0.92 (p < 0.0001), respectively. CONCLUSION We demonstrated that "Unseen AI" was in close proximity (<10%) to "Seen AI", validating our DL model for low atherosclerotic wall plaque segmentation. The online system runs < 1 s.
Collapse
Affiliation(s)
- Pankaj K. Jain
- School of Biomedical Engineering, IIT (BHU), Varanasi 221005, India; (P.K.J.); (N.S.)
| | - Neeraj Sharma
- School of Biomedical Engineering, IIT (BHU), Varanasi 221005, India; (P.K.J.); (N.S.)
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 10015 Cagliari, Italy;
| | | | - Mandeep K. Kalra
- Department of Radiology, Massachusetts General Hospital, 55 Fruit Street, Boston, MA 02114, USA;
| | - Amer Johri
- Division of Cardiology, Queen’s University, Kingston, ON K7L 3N6, Canada;
| | - John R. Laird
- Heart and Vascular Institute, Adventist Health St. Helena, St. Helena, CA 94574, USA;
| | - Andrew N. Nicolaides
- Vascular Screening and Diagnostic Centre, University of Nicosia, Nicosia 1700, Cyprus;
| | - Jasjit S. Suri
- Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA
| |
Collapse
|
5
|
Sanagala SS, Nicolaides A, Gupta SK, Koppula VK, Saba L, Agarwal S, Johri AM, Kalra MS, Suri JS. Ten Fast Transfer Learning Models for Carotid Ultrasound Plaque Tissue Characterization in Augmentation Framework Embedded with Heatmaps for Stroke Risk Stratification. Diagnostics (Basel) 2021; 11:2109. [PMID: 34829456 PMCID: PMC8622690 DOI: 10.3390/diagnostics11112109] [Citation(s) in RCA: 23] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2021] [Revised: 11/03/2021] [Accepted: 11/09/2021] [Indexed: 12/24/2022] Open
Abstract
Background and Purpose: Only 1-2% of the internal carotid artery asymptomatic plaques are unstable as a result of >80% stenosis. Thus, unnecessary efforts can be saved if these plaques can be characterized and classified into symptomatic and asymptomatic using non-invasive B-mode ultrasound. Earlier plaque tissue characterization (PTC) methods were machine learning (ML)-based, which used hand-crafted features that yielded lower accuracy and unreliability. The proposed study shows the role of transfer learning (TL)-based deep learning models for PTC. Methods: As pertained weights were used in the supercomputer framework, we hypothesize that transfer learning (TL) provides improved performance compared with deep learning. We applied 11 kinds of artificial intelligence (AI) models, 10 of them were augmented and optimized using TL approaches-a class of Atheromatic™ 2.0 TL (AtheroPoint™, Roseville, CA, USA) that consisted of (i-ii) Visual Geometric Group-16, 19 (VGG16, 19); (iii) Inception V3 (IV3); (iv-v) DenseNet121, 169; (vi) XceptionNet; (vii) ResNet50; (viii) MobileNet; (ix) AlexNet; (x) SqueezeNet; and one DL-based (xi) SuriNet-derived from UNet. We benchmark 11 AI models against our earlier deep convolutional neural network (DCNN) model. Results: The best performing TL was MobileNet, with accuracy and area-under-the-curve (AUC) pairs of 96.10 ± 3% and 0.961 (p < 0.0001), respectively. In DL, DCNN was comparable to SuriNet, with an accuracy of 95.66% and 92.7 ± 5.66%, and an AUC of 0.956 (p < 0.0001) and 0.927 (p < 0.0001), respectively. We validated the performance of the AI architectures with established biomarkers such as greyscale median (GSM), fractal dimension (FD), higher-order spectra (HOS), and visual heatmaps. We benchmarked against previously developed Atheromatic™ 1.0 ML and showed an improvement of 12.9%. Conclusions: TL is a powerful AI tool for PTC into symptomatic and asymptomatic plaques.
Collapse
Affiliation(s)
- Skandha S. Sanagala
- CSE Department, CMR College of Engineering & Technology, Hyderabad 501401, TS, India; (S.S.S.); (V.K.K.)
- CSE Department, Bennett University, Greater Noida 203206, UP, India;
| | - Andrew Nicolaides
- Vascular Screening and Diagnostic Centre, University of Nicosia, Nicosia 1700, Cyprus;
| | - Suneet K. Gupta
- CSE Department, Bennett University, Greater Noida 203206, UP, India;
| | - Vijaya K. Koppula
- CSE Department, CMR College of Engineering & Technology, Hyderabad 501401, TS, India; (S.S.S.); (V.K.K.)
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 10015 Cagliari, Italy;
| | | | - Amer M. Johri
- Division of Cardiology, Queen’s University, Kingston, ON K7L 3N6, Canada;
| | - Manudeep S. Kalra
- Department of Radiology, Massachusetts General Hospital, 55 Fruit Street, Boston, MA 02114, USA;
| | - Jasjit S. Suri
- Stroke Diagnostic and Monitoring Division, AtheroPoint™ LLC, Roseville, CA 95661, USA
| |
Collapse
|
6
|
Murgia A, Balestrieri A, Francone M, Lucatelli P, Scapin E, Buckler A, Micheletti G, Faa G, Conti M, Suri JS, Guglielmi G, Carriero A, Saba L. Plaque imaging volume analysis: technique and application. Cardiovasc Diagn Ther 2020; 10:1032-1047. [PMID: 32968659 PMCID: PMC7487381 DOI: 10.21037/cdt.2020.03.01] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2019] [Accepted: 02/15/2020] [Indexed: 12/12/2022]
Abstract
The prevention and management of atherosclerosis poses a tough challenge to public health organizations worldwide. Together with myocardial infarction, stroke represents its main manifestation, with up to 25% of all ischemic strokes being caused by thromboembolism arising from the carotid arteries. Therefore, a vast number of publications have focused on the characterization of the culprit lesion, the atherosclerotic plaque. A paradigm shift appears to be taking place at the current state of research, as the attention is gradually moving from the classically defined degree of stenosis to the identification of features of plaque vulnerability, which appear to be more reliable predictors of recurrent cerebrovascular events. The present review will offer a perspective on the present state of research in the field of carotid atherosclerotic disease, focusing on the imaging modalities currently used in the study of the carotid plaque and the impact that such diagnostic means are having in the clinical setting.
Collapse
Affiliation(s)
- Alessandro Murgia
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari – Polo di Monserrato, s.s. 554 Monserrato (Cagliari) 09045, Italy
| | - Antonella Balestrieri
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari – Polo di Monserrato, s.s. 554 Monserrato (Cagliari) 09045, Italy
| | - Marco Francone
- Department of Radiological, Oncological and Anatomopathological Sciences-Radiology, ‘Sapienza’ University of Rome, Rome, Italy
| | - Pierleone Lucatelli
- Department of Radiological, Oncological and Anatomopathological Sciences-Radiology, ‘Sapienza’ University of Rome, Rome, Italy
| | - Elisa Scapin
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari – Polo di Monserrato, s.s. 554 Monserrato (Cagliari) 09045, Italy
| | | | - Giulio Micheletti
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari – Polo di Monserrato, s.s. 554 Monserrato (Cagliari) 09045, Italy
| | - Gavino Faa
- Department of Pathology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari – Polo San Giovanni di Dio, Cagliari (Cagliari) 09045, Italy
| | - Maurizio Conti
- Diagnostic and Monitoring Division, AtheroPoint™ LLC, Roseville, CA, USA
- Department of Electrical Engineering, U of Idaho (Affl.), Idaho, USA
| | - Jasjit S. Suri
- Diagnostic and Monitoring Division, AtheroPoint™ LLC, Roseville, CA, USA
- Department of Electrical Engineering, U of Idaho (Affl.), Idaho, USA
| | | | - Alessandro Carriero
- Department of Radiology, Maggiore della Carità Hospital, Università del Piemonte Orientale, Novara, Italy
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari – Polo di Monserrato, s.s. 554 Monserrato (Cagliari) 09045, Italy
| |
Collapse
|
7
|
Tsakanikas VD, Siogkas PK, Mantzaris MD, Potsika VT, Kigka VI, Exarchos TP, Koncar IB, Jovanovic M, Vujcic A, Ducic S, Pelisek J, Fotiadis DI. A deep learning oriented method for automated 3D reconstruction of carotid arterial trees from MR imaging. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2020; 2020:2408-2411. [PMID: 33018492 DOI: 10.1109/embc44109.2020.9176532] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
The scope of this paper is to present a new carotid vessel segmentation algorithm implementing the U-net based convolutional neural network architecture. With carotid atherosclerosis being the major cause of stroke in Europe, new methods that can provide more accurate image segmentation of the carotid arterial tree and plaque tissue can help improve early diagnosis, prevention and treatment of carotid disease. Herein, we present a novel methodology combining the U-net model and morphological active contours in an iterative framework that accurately segments the carotid lumen and outer wall. The method automatically produces a 3D meshed model of the carotid bifurcation and smaller branches, using multispectral MR image series obtained from two clinical centres of the TAXINOMISIS study. As indicated by a validation study, the algorithm succeeds high accuracy (99.1% for lumen area and 92.6% for the perimeter) for lumen segmentation. The proposed algorithm will be used in the TAXINOMISIS study to obtain more accurate 3D vessel models for improved computational fluid dynamics simulations and the development of models of atherosclerotic plaque progression.
Collapse
|
8
|
Jodas DS, da Costa MFM, Parreira TAA, Pereira AS, Tavares JMRS. Using a distance map and an active contour model to segment the carotid artery boundary from the lumen contour in proton density weighted magnetic resonance images. Comput Biol Med 2020; 123:103901. [PMID: 32658794 DOI: 10.1016/j.compbiomed.2020.103901] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2020] [Revised: 06/20/2020] [Accepted: 06/28/2020] [Indexed: 10/23/2022]
Abstract
Segmentation methods have assumed an important role in image-based diagnosis of several cardiovascular diseases. Particularly, the segmentation of the boundary of the carotid artery is demanded in the detection and characterization of atherosclerosis and assessment of the disease progression. In this article, a fully automatic approach for the segmentation of the carotid artery boundary in Proton Density Weighted Magnetic Resonance Images is presented. The approach relies on the expansion of the lumen contour based on a distance map built using the gray-weighted distance relative to the center of the identified lumen region in the image under analysis. Then, a Snake model with a modified weighted external energy based on the combination of a balloon force along with a Gradient Vector Flow-based external energy is applied to the expanded contour towards the correct boundary of the carotid artery. The average values of the Dice coefficient, Polyline distance, mean contour distance and centroid distance found in the segmentation of 139 carotid arteries were 0.83 ± 0.11, 2.70 ± 1.69 pixels, 2.79 ± 1.89 pixels and 3.44 ± 2.82 pixels, respectively. The segmentation results of the proposed approach were also compared against the ones obtained by related approaches found in the literature, which confirmed the outstanding performance of the new approach. Additionally, the proposed weighted external energy for the Snake model was shown to be also robust to carotid arteries with large thickness and weak boundary image edges.
Collapse
Affiliation(s)
- Danilo Samuel Jodas
- CAPES Foundation, Ministry of Education of Brazil, Brasília - DF, 70040-020, Brazil; Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Faculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, s/n, 4200-465, Porto, Portugal.
| | - Maria Francisca Monteiro da Costa
- IFE Neurorradiologia, Serviço de Neurorradiologia, Centro Hospitalar São João, Alameda Professor Hernâni Monteiro, 4200-319 Porto, Portugal.
| | - Tiago A A Parreira
- AH Neurorradiologia, Serviço de Neurorradiologia, Centro Hospitalar São João, Alameda Professor Hernâni Monteiro, 4200-319 Porto, Portugal.
| | - Aledir Silveira Pereira
- Universidade Estadual Paulista Júlio de Mesquita Filho, Rua Cristóvão Colombo, 2265, 15054-000, S. J. do Rio Preto, Brazil.
| | - João Manuel R S Tavares
- Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Faculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, s/n, 4200-465, Porto, Portugal.
| |
Collapse
|
9
|
Puvvula A, Jamthikar AD, Gupta D, Khanna NN, Porcu M, Saba L, Viskovic K, Ajuluchukwu JNA, Gupta A, Mavrogeni S, Turk M, Laird JR, Pareek G, Miner M, Sfikakis PP, Protogerou A, Kitas GD, Nicolaides A, Viswanathan V, Suri JS. Morphological Carotid Plaque Area Is Associated With Glomerular Filtration Rate: A Study of South Asian Indian Patients With Diabetes and Chronic Kidney Disease. Angiology 2020; 71:520-535. [PMID: 32180436 DOI: 10.1177/0003319720910660] [Citation(s) in RCA: 18] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/11/2022]
Abstract
We evaluated the association between automatically measured carotid total plaque area (TPA) and the estimated glomerular filtration rate (eGFR), a biomarker of chronic kidney disease (CKD). Automated average carotid intima-media thickness (cIMTave) and TPA measurements in carotid ultrasound (CUS) were performed using AtheroEdge (AtheroPoint). Pearson correlation coefficient (CC) was then computed between the TPA and eGFR for (1) males versus females, (2) diabetic versus nondiabetic patients, and (3) between the left and right carotid artery. Overall, 339 South Asian Indian patients with either type 2 diabetes mellitus (T2DM) or CKD, or hypertension (stage 1 or stage 2) were retrospectively analyzed by acquiring cIMTave and TPA measurements of their left and right common carotid arteries (CCA; total CUS: 678, mean age: 54.2 ± 9.8 years; 75.2% males; 93.5% with T2DM). The CC between TPA and eGFR for different scenarios were (1) for males and females -0.25 (P < .001) and -0.35 (P < .001), respectively; (2) for T2DM and non-T2DM -0.26 (P < .001) and -0.49 (P = .02), respectively, and (3) for left and right CCA -0.25 (P < .001) and -0.23 (P < .001), respectively. Automated TPA is an equally reliable biomarker compared with cIMTave for patients with CKD (with or without T2DM) with subclinical atherosclerosis.
Collapse
Affiliation(s)
- Anudeep Puvvula
- Annu's Hospitals for Skin and Diabetes, Nellore, Andhra Pradesh, India
| | - Ankush D Jamthikar
- Department of Electronics and Communications Engineering, Visvesvaraya National Institute of Technology, Nagpur, Maharashtra, India
| | - Deep Gupta
- Department of Electronics and Communications Engineering, Visvesvaraya National Institute of Technology, Nagpur, Maharashtra, India
| | - Narendra N Khanna
- Department of Cardiology, Indraprastha Apollo Hospitals, New Delhi, Delhi, India
| | - Michele Porcu
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), Cagliari, Italy
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), Cagliari, Italy
| | - Klaudija Viskovic
- Department of Radiology and Ultrasound, University Hospital for Infectious Diseases, Zagreb, Croatia
| | | | - Ajay Gupta
- Department of Radiology, Weill Cornell Medicine, New York City, NY, USA
| | - Sophie Mavrogeni
- Cardiology Clinic, Onassis Cardiac Surgery Center, Athens, Greece
| | - Monika Turk
- Department of Neurology, University Medical Centre Maribor, Slovenia
| | - John R Laird
- Heart and Vascular Institute, Adventist Health St Helena, St Helena, CA, USA
| | - Gyan Pareek
- Minimally Invasive Urology Institute, Brown University, Providence, RI, USA
| | - Martin Miner
- Men's Health Center, Miriam Hospital, Providence, RI, USA
| | - Petros P Sfikakis
- Rheumatology Unit, National Kapodistrian University of Athens, Greece
| | - Athanasios Protogerou
- Department of Cardiovascular Prevention and Research Unit Clinic and Laboratory of Pathophysiology, National and Kapodistrian University of Athens, Greece
| | - George D Kitas
- R & D Academic Affairs, Dudley Group NHS Foundation Trust, Dudley, United Kingdom
| | - Andrew Nicolaides
- Vascular Screening and Diagnostic Centre and University of Nicosia Medical School, Cyprus
| | - Vijay Viswanathan
- M. V. Hospital for Diabetes and Professor M. Viswanathan Diabetes Research Centre, Chennai, Tamil Nadu, India
| | - Jasjit S Suri
- Stroke Monitoring and Diagnostic Division, AtheroPoint, Roseville, CA, USA
| |
Collapse
|
10
|
Wu J, Xin J, Yang X, Sun J, Xu D, Zheng N, Yuan C. Deep morphology aided diagnosis network for segmentation of carotid artery vessel wall and diagnosis of carotid atherosclerosis on black-blood vessel wall MRI. Med Phys 2019; 46:5544-5561. [PMID: 31356693 DOI: 10.1002/mp.13739] [Citation(s) in RCA: 20] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/12/2019] [Revised: 06/14/2019] [Accepted: 07/11/2019] [Indexed: 12/21/2022] Open
Abstract
PURPOSE Early detection of carotid atherosclerosis on the vessel wall (VW) magnetic resonance imaging (MRI) (VW-MRI) images can prevent the progression of cardiovascular disease. However, the manual inspection process of the VW-MRI images is cumbersome and has low reproducibility. Therefore in this paper, by using the convolutional neural networks (CNNs), we develop a deep morphology aided diagnosis (DeepMAD) network for automated segmentation of the VW of carotid artery and for automated diagnosis of the carotid atherosclerosis with the black-blood (BB) VW-MRI (i.e., the T1-weighted MRI) in a slice-by-slice manner. METHODS The proposed DeepMAD network consists of a segmentation subnetwork and a diagnosis subnetwork for performing the segmentation and diagnosis tasks on the BB-VW-MRI images, where the manual labeled lumen area, the manual labeled outer wall area and the manual labeled lesion Types based on the modified American Heart Association (AHA) criteria are used as the ground-truth. Specifically, a deep U-shape CNN with a weighted fusion layer is designed as the segmentation subnetwork, where the lumen area and the outer wall area can be simultaneously segmented under the supervision of the triple Dice loss to provide the vessel wall map as morphological information. Then, the image stream from the BB-VWMRI image and the morphology stream from the obtained vessel wall map are extracted from two deep CNNs and combined to obtain the diagnosis results of atherosclerosis in the diagnosis subnetwork. In addition, the triple input set is formed by three carotid regions of interest (ROIs) from three consecutive slices of the MRI sequence and input to the DeepMAD network, where the first and last slices used as additional adjacent slices to provide 2.5D spatial information along the carotid artery centerline for the intermediate slice, which is the target slice for segmentation and diagnosis in the study. RESULTS Compared to other existing methods, the DeepMAD network can achieve promising segmentation performances (0.9594 Dice for the lumen and 0.9657 Dice for the outer wall) and better diagnosis Accuracy of the carotid atherosclerosis (0.9503 AUC and 0.8916 Accuracy) in the test dataset (including invisible subjects) from same source as the training dataset. In addition, the trained DeepMAD model can be successfully transferred to another test dataset for segmentation and diagnosis tasks with remarkable performance (0.9475 Dice for the lumen and 0.9542 Dice for the outer wall, 0. 9227 AUC and 0.8679 Accuracy for diagnosis). CONCLUSIONS Even without the intervention of reviewers required for previous works, the proposed DeepMAD network automatically segments the lumen and the outer wall together and diagnoses the carotid atherosclerosis with high performances. The DeepMAD network can be used in clinical trials to help radiologists get rid of tedious reading tasks, such as screening review to separate the normal carotid from the atherosclerotic arteries and outlining the vessel wall contours.
Collapse
Affiliation(s)
- Jiayi Wu
- Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, 710049, China
| | - Jingmin Xin
- Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, 710049, China
| | - Xiaofeng Yang
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Jie Sun
- Department of Radiology, University of Washington, Seattle, WA, USA
| | - Dongxiang Xu
- Department of Radiology, University of Washington, Seattle, WA, USA
| | - Nanning Zheng
- Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, 710049, China
| | - Chun Yuan
- Department of Radiology, University of Washington, Seattle, WA, USA
| |
Collapse
|
11
|
Xue W, Vegunta S, Zwart CM, Aguilar MI, Patel AC, Hoxworth JM, Demaerschalk BM, Mitchell JR. Retrospective Validation of a Computer-Assisted Quantification Model of Intracerebral Hemorrhage Volume on Accuracy, Precision, and Acquisition Time, Compared with Standard ABC/2 Manual Volume Calculation. AJNR Am J Neuroradiol 2017; 38:1536-1542. [PMID: 28596188 DOI: 10.3174/ajnr.a5256] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/06/2016] [Accepted: 04/09/2017] [Indexed: 12/30/2022]
Abstract
BACKGROUND AND PURPOSE Intracerebral hemorrhage accounts for 6.5%-19.6% of all acute strokes. Initial intracerebral hemorrhage volume and expansion are both independent predictors of clinical outcomes and mortality. Therefore, a rapid, unbiased, and precise measurement of intracerebral hemorrhage volume is a key component of clinical management. The most commonly used method, ABC/2, results in overestimation. We developed an interactive segmentation program, SegTool, using a novel graphic processing unit, level set algorithm. Until now, the speed, bias, and precision of SegTool had not been validated. MATERIALS AND METHODS In a single stroke academic center, 2 vascular neurologists and 2 neuroradiologists independently performed a test-retest experiment that involved repeat measurements of static, unchanging intracerebral hemorrhage volumes on CT from 76 intracerebral hemorrhage cases. Measurements were made with SegTool and ABC/2. True intracerebral hemorrhage volumes were estimated from a consensus of repeat manual tracings by 2 operators. These data allowed us to estimate measurement bias, precision, and speed. RESULTS The measurements with SegTool were not significantly different from the true intracerebral hemorrhage volumes, while ABC/2 overestimated volume by 45%. The interrater measurement variability with SegTool was 50% less than that with ABC/2. The average measurement times for ABC/2 and SegTool were 35.7 and 44.6 seconds, respectively. CONCLUSIONS SegTool appears to have attributes superior to ABC/2 in terms of accuracy and interrater reliability with a 9-second delay in measurement time (on average); hence, it could be useful in clinical trials and practice.
Collapse
Affiliation(s)
- W Xue
- From the Department of Biomedical Informatics (W.X., J.R.M.), Arizona State University, Scottsdale, Arizona
| | - S Vegunta
- Moran Eye Center (S.V.), University of Utah, Salt Lake City, Utah
| | - C M Zwart
- Departments of Radiology (C.M.Z., A.C.P., J.M.H.)
| | | | - A C Patel
- Departments of Radiology (C.M.Z., A.C.P., J.M.H.)
| | - J M Hoxworth
- Departments of Radiology (C.M.Z., A.C.P., J.M.H.)
| | | | - J R Mitchell
- From the Department of Biomedical Informatics (W.X., J.R.M.), Arizona State University, Scottsdale, Arizona.,Research (J.R.M.), Mayo Clinic, Scottsdale, Arizona
| |
Collapse
|
12
|
Kaur T, Saini BS, Gupta S. A joint intensity and edge magnitude-based multilevel thresholding algorithm for the automatic segmentation of pathological MR brain images. Neural Comput Appl 2016. [DOI: 10.1007/s00521-016-2751-4] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
13
|
Jodas DS, Pereira AS, R.S. Tavares JM. Lumen segmentation in magnetic resonance images of the carotid artery. Comput Biol Med 2016; 79:233-242. [DOI: 10.1016/j.compbiomed.2016.10.021] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2016] [Revised: 10/24/2016] [Accepted: 10/24/2016] [Indexed: 11/15/2022]
|
14
|
Chen Z, Liu AF, Chen H, Yuan C, He L, Zhu Y, Guan M, Jiang WJ, Zhao X. Evaluation of basilar artery atherosclerotic plaque distribution by 3D MR vessel wall imaging. J Magn Reson Imaging 2016; 44:1592-1599. [PMID: 27249041 DOI: 10.1002/jmri.25296] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2016] [Revised: 04/13/2016] [Accepted: 04/13/2016] [Indexed: 11/07/2022] Open
Abstract
PURPOSE Basilar artery (BA) atherosclerosis is an important cause of perforator stroke in the brainstem due to plaque involvement of the perforator ostia in BA dorsal or lateral walls. Therefore, to acquire information on plaque distribution is important to better understand and prevent the perforator stroke. This study aimed to comprehensively evaluate BA plaque distribution with 3D magnetic resonance imaging (MRI) vessel wall imaging. MATERIALS AND METHODS Consecutive patients with cerebrovascular symptoms and stenosis or irregular luminal surface of BA were recruited and underwent BA 3D proton density-weighted volume isotropic turbo spin echo acquisition (VISTA) imaging at 3T. The cross-sectional and longitudinal distribution of BA plaque were analyzed with a custom-developed tool. RESULTS In all, 85 BA plaques were detected in 61 recruited patients. For cross-sectional distribution, the prevalence of plaque involvement in the ventral, left, dorsal, and right quadrant of BA wall was 74.1%, 70.6%, 67.1%, and 62.4%, respectively. Of the 85 plaques, 17.7% involved one quadrant and 82.3% involved two or more quadrants. The most severe plaque region was more commonly situated at lateral walls (66.1%) as compared to ventral (23.2%, P < 0.001) and dorsal walls (10.6%, P < 0.001). Longitudinally, plaques were more frequently found to occur at BA segment distal than proximal to anterior inferior cerebellar artery (AICA) (63.5% vs. 36.5%). CONCLUSION Taking advantage of 3D MR vessel wall imaging, BA plaques were found to more likely affect lateral walls and form in BA distal to AICA, where most perforators originate, suggesting that it might be useful to characterize BA plaque distribution before aggressive treatment for prevention of perforator stroke. J. Magn. Reson. Imaging 2016;44:1592-1599.
Collapse
Affiliation(s)
- Zhensen Chen
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University School of Medicine, Beijing, China
| | - Ao-Fei Liu
- New Era Stroke Care and Research Institute, General Hospital of the PLA Rocket Force, Beijing, China
| | - Huijun Chen
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University School of Medicine, Beijing, China
| | - Chun Yuan
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University School of Medicine, Beijing, China.,Department of Radiology, University of Washington, Seattle, Washington, USA
| | - Le He
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University School of Medicine, Beijing, China
| | - Yandong Zhu
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University School of Medicine, Beijing, China
| | - Maobin Guan
- Department of Radiology, Yangzhou First People's Hospital, Yangzhou, China
| | - Wei-Jian Jiang
- New Era Stroke Care and Research Institute, General Hospital of the PLA Rocket Force, Beijing, China
| | - Xihai Zhao
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University School of Medicine, Beijing, China
| |
Collapse
|
15
|
Saba L, Araki T, Kumar PK, Rajan J, Lavra F, Ikeda N, Sharma AM, Shafique S, Nicolaides A, Laird JR, Gupta A, Suri JS. Carotid inter-adventitial diameter is more strongly related to plaque score than lumen diameter: An automated tool for stroke analysis. JOURNAL OF CLINICAL ULTRASOUND : JCU 2016; 44:210-220. [PMID: 26887355 DOI: 10.1002/jcu.22334] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/29/2015] [Revised: 11/27/2015] [Accepted: 12/31/2015] [Indexed: 06/05/2023]
Abstract
PURPOSE To compare the strength of correlation between automatically measured carotid lumen diameter (LD) and interadventitial diameter (IAD) with plaque score (PS). METHODS Retrospective study on a database of 404 common carotid artery B-mode sonographic images from 202 diabetic patients. LD and IAD were computed automatically using an advanced computerized edge detection method and compared with two distinct manual measurements. PS was computed by adding the maximal thickness in millimeters of plaques in segments taken from the internal carotid artery, bulb, and common carotid artery on both sides. RESULTS The coefficient of correlation was 0.19 (p < 0.007) between LD and PS, and 0.25 (p < 0.0006) between IAD and PS. After excluding 10 outliers, coefficient of correlation was 0.25 (p < 0.0001) between LD and PS, and 0.38 (p < 0.0001) between IAD and PS. The precision of merit of automated versus the two manual measurements was 96.6% and 97.2% for LD, and 97.7% and 98.1%, for IAD, respectively. CONCLUSIONS Our automated measurement system gave satisfying results in comparison with manual measurements. Carotid IAD was more strongly correlated to PS than carotid LD in this population sample of Japanese diabetic patients.
Collapse
Affiliation(s)
- Luca Saba
- Department of Radiology, University of Cagliari, Italy
| | - Tadashi Araki
- Division of Cardiovascular Medicine, Toho University, Ohashi Medical Center, Tokyo, Japan
| | - P Krishna Kumar
- Department of Computer Science and Engineering, National Institute of Technology, Karnataka, India
- Point-of-Care Devices, Global Biomedical Technologies, Inc, Roseville, CA
| | - Jeny Rajan
- Department of Computer Science and Engineering, National Institute of Technology, Karnataka, India
- Point-of-Care Devices, Global Biomedical Technologies, Inc, Roseville, CA
| | | | - Nobutaka Ikeda
- Cardiovascular Medicine, National Center for Global Health and Medicine, Tokyo, Japan
| | - Aditya M Sharma
- Division of Cardiovascular Medicine, Department of Medicine, University of Virginia, VA
| | | | | | - John R Laird
- UC Davis Vascular Center, University of California, Davis, CA
| | - Ajay Gupta
- Radiology Department, Brain and Mind Research Institute, Weill Cornell Medical College, NY
| | - Jasjit S Suri
- Point-of-Care Devices, Global Biomedical Technologies, Inc, Roseville, CA
- Monitoring and Diagnostic Division, AtheroPoint, Roseville, CA
- Department of Electrical Engineering, University of Idaho (Affl.), ID
| |
Collapse
|
16
|
Wang Y, Zhang Y, Navarro L, Eker OF, Corredor Jerez RA, Chen Y, Zhu Y, Courbebaisse G. Multilevel segmentation of intracranial aneurysms in CT angiography images. Med Phys 2016; 43:1777. [DOI: 10.1118/1.4943375] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/02/2023] Open
|
17
|
Shinohara Y, Sakamoto M, Kuya K, Kishimoto J, Iwata N, Ohta Y, Fujii S, Watanabe T, Ogawa T. Assessment of carotid plaque composition using fast-kV switching dual-energy CT with gemstone detector: comparison with extracorporeal and virtual histology-intravascular ultrasound. Neuroradiology 2015; 57:889-95. [DOI: 10.1007/s00234-015-1541-5] [Citation(s) in RCA: 18] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2015] [Accepted: 05/07/2015] [Indexed: 11/30/2022]
|