1
|
Liu J, Zeng B, Chen X. Heart and great vessels segmentation in congenital heart disease via CNN and conditioned energy function postprocessing. Int J Comput Assist Radiol Surg 2024:10.1007/s11548-024-03182-3. [PMID: 38814529 DOI: 10.1007/s11548-024-03182-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2024] [Accepted: 05/08/2024] [Indexed: 05/31/2024]
Abstract
PURPOSE The segmentation of the heart and great vessels in CT images of congenital heart disease (CHD) is critical for the clinical assessment of cardiac anomalies and the diagnosis of CHD. However, the diverse types and abnormalities inherent in CHD present significant challenges to comprehensive heart segmentation. METHODS We proposed a novel two-stage segmentation approach, integrating a Convolutional Neural Network (CNN) with a postprocessing method with conditioned energy function for pulmonary and aorta. The initial stage employs a CNN enhanced by a gated self-attention mechanism for the segmentation of five primary heart structures and two major vessels. Subsequently, the second stage utilizes a conditioned energy function specifically tailored to refine the segmentation of the pulmonary artery and aorta, ensuring vascular continuity. RESULTS Our method was evaluated on a public dataset including 110 3D CT volumes, encompassing 16 CHD variants. Compared to prevailing segmentation techniques (U-Net, V-Net, Unetr, dynUnet), our approach demonstrated improvements of 1.02, 1.04, and 1.41% in Dice Coefficient (DSC), Intersection over Union (IOU), and the 95th percentile Hausdorff Distance (HD95), respectively, for heart structure segmentation. For the two great vessels, the enhancements were 1.05, 1.07, and 1.42% in these metrics. CONCLUSION The outcomes on the public dataset affirm the efficacy of our proposed segmentation method. Precise segmentation of the entire heart and great vessels can significantly aid in the diagnosis and treatment of CHD, underscoring the clinical relevance of our findings.
Collapse
Affiliation(s)
- Jiaxuan Liu
- Institute of Biomedical Manufacturing and Life Quality Engineering, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Bolun Zeng
- Institute of Biomedical Manufacturing and Life Quality Engineering, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Xiaojun Chen
- Institute of Biomedical Manufacturing and Life Quality Engineering, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China.
- Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, 200240, China.
| |
Collapse
|
2
|
ImageCHD: A 3D Computed Tomography Image Dataset for Classification of Congenital Heart Disease. MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION – MICCAI 2020 2020. [DOI: 10.1007/978-3-030-59719-1_8] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/01/2023]
|
3
|
Gupta-Malhotra M, Schaaf W, Kutty S. A Primer on Multimodal Imaging and Cardiology-Radiology Congenital Heart Interface. CHILDREN-BASEL 2019; 6:children6040061. [PMID: 31018523 PMCID: PMC6517999 DOI: 10.3390/children6040061] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/04/2019] [Revised: 04/12/2019] [Accepted: 04/17/2019] [Indexed: 12/29/2022]
Abstract
Pediatric cardiology imaging laboratories in the present day have several modalities for imaging of congenital and acquired cardiovascular disease. These modalities include echocardiography, cardiovascular magnetic resonance imaging, cardiac computed tomography and nuclear imaging. The utility and limitations of multimodal imaging is described herein along with a framework for establishing a cardiology-radiology interface.
Collapse
Affiliation(s)
- Monesha Gupta-Malhotra
- Department of Pediatric Cardiology, Johns Hopkins All Children's Hospital, Johns Hopkins University, Saint Petersburg, FL 33701, USA.
| | - William Schaaf
- Department of Pediatric Radiology, Johns Hopkins All Children's Hospital, St. Petersburg, FL 33701, USA.
| | - Shelby Kutty
- Department of Pediatric Cardiology, Johns Hopkins Children's Center, Baltimore, MD 21205, USA.
| |
Collapse
|
4
|
Malahfji M, Chamsi-Pasha MA. Advanced Cardiac Imaging for Complex Adult Congenital Heart Diseases. Methodist Debakey Cardiovasc J 2019; 15:99-104. [PMID: 31384372 DOI: 10.14797/mdcj-15-2-99] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/23/2023] Open
Abstract
The population of patients with adult congenital heart disease has grown and is currently estimated to include approximately 1 million people in the United States. Cardiologists and imagers frequently encounter complex patients who have undergone multiple prior operations and interventions. A myriad of imaging tests are currently available, including echocardiography, cardiovascular magnetic resonance imaging, and computed tomography, all of which collectively provide invaluable information on cardiac anatomy and hemodynamics. Advanced imaging plays a role in diagnosis and preprocedural planning and also determines the need and frequency of follow-up. This article provides a contemporary review of the current role of cardiac imaging in patients with complex congenital heart disease.
Collapse
Affiliation(s)
- Maan Malahfji
- HOUSTON METHODIST DEBAKEY HEART & VASCULAR CENTER, HOUSTON METHODIST HOSPITAL, HOUSTON, TEXAS
| | - Mohammed A Chamsi-Pasha
- HOUSTON METHODIST DEBAKEY HEART & VASCULAR CENTER, HOUSTON METHODIST HOSPITAL, HOUSTON, TEXAS
| |
Collapse
|
5
|
Shirota G, Maeda E, Namiki Y, Bari R, Ino K, Torigoe R, Abe O. Pediatric 320-row cardiac computed tomography using electrocardiogram-gated model-based full iterative reconstruction. Pediatr Radiol 2017; 47:1463-1470. [PMID: 28667349 PMCID: PMC5608791 DOI: 10.1007/s00247-017-3901-2] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/27/2017] [Revised: 04/05/2017] [Accepted: 05/09/2017] [Indexed: 12/03/2022]
Abstract
BACKGROUND Full iterative reconstruction algorithm is available, but its diagnostic quality in pediatric cardiac CT is unknown. OBJECTIVE To compare the imaging quality of two algorithms, full and hybrid iterative reconstruction, in pediatric cardiac CT. MATERIALS AND METHODS We included 49 children with congenital cardiac anomalies who underwent cardiac CT. We compared quality of images reconstructed using the two algorithms (full and hybrid iterative reconstruction) based on a 3-point scale for the delineation of the following anatomical structures: atrial septum, ventricular septum, right atrium, right ventricle, left atrium, left ventricle, main pulmonary artery, ascending aorta, aortic arch including the patent ductus arteriosus, descending aorta, right coronary artery and left main trunk. We evaluated beam-hardening artifacts from contrast-enhancement material using a 3-point scale, and we evaluated the overall image quality using a 5-point scale. We also compared image noise, signal-to-noise ratio and contrast-to-noise ratio between the algorithms. RESULTS The overall image quality was significantly higher with full iterative reconstruction than with hybrid iterative reconstruction (3.67±0.79 vs. 3.31±0.89, P=0.0072). The evaluation scores for most of the gross structures were higher with full iterative reconstruction than with hybrid iterative reconstruction. There was no significant difference between full and hybrid iterative reconstruction for the presence of beam-hardening artifacts. Image noise was significantly lower in full iterative reconstruction, while signal-to-noise ratio and contrast-to-noise ratio were significantly higher in full iterative reconstruction. CONCLUSION The diagnostic quality was superior in images with cardiac CT reconstructed with electrocardiogram-gated full iterative reconstruction.
Collapse
Affiliation(s)
- Go Shirota
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan.
| | - Eriko Maeda
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655 Japan
| | - Yoko Namiki
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655 Japan
| | - Razibul Bari
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655 Japan
| | - Kenji Ino
- Imaging Center, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655 Japan
| | - Rumiko Torigoe
- Toshiba Medical Systems, 2-1-6, Tsukuda, Chuo-ku, Tokyo, 104-0051 Japan
| | - Osamu Abe
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655 Japan
| |
Collapse
|
6
|
Bhat V, Belaval V, Gadabanahalli K, Raj V, Shah S. Illustrated Imaging Essay on Congenital Heart Diseases: Multimodality Approach Part II: Acyanotic Congenital Heart Disease and Extracardiac Abnormalities. J Clin Diagn Res 2016; 10:TE01-6. [PMID: 27504381 DOI: 10.7860/jcdr/2016/21442.8040] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2015] [Accepted: 04/02/2016] [Indexed: 11/24/2022]
Abstract
Acyanotic heart disease constitutes a significant majority of patient who may present with non-cardiac symptoms. Either they are detected incidentally or present with respiratory complaints. Equipped with knowledge of anatomy by echocardiography and radiographic methods described in previous part of this presentation, diagnosis may be confidently attempted. On plain radiography acyanotic congenital heart diseases have variable appearance depending upon severity of disease. Cardiac size, chamber enlargement and pulmonary vascular pattern are key elements. Typically left to right shunts with large volume flow are associated with pulmonary plethora. Plain radiography has an important role in detecting manifestation of pulmonary arterial hypertension. Severe stenosis of pulmonary valve is associated with pulmonary oligemia. Small intra-cardiac shunts and anomalies of coronary arteries generally present with normal cardiac size and pulmonary arterial pattern. Disease spectrum presented in this illustration demands thorough scrutiny of pulmonary, osseous and abdominal abnormalities. This section illustrates some commonly encountered spectrum of acyanotic cardiac disease.
Collapse
Affiliation(s)
- Venkatraman Bhat
- Director of Imaging Services, Head of Radiology, Department of Radiology and Imaging services, Narayana Health, Narayana Hrudayalaya, Multispeciality Hospital-Shaw Mazumdar Medical Centre , Bengaluru, India
| | - Vinay Belaval
- Junior Consultant, Department of Radiology and Imaging services, Narayana Health, Narayana Hrudayalaya, Multispeciality Hospital-Shaw Mazumdar Medical Centre , Bengaluru, India
| | - Karthik Gadabanahalli
- Consultant Radiology, Department of Radiology and Imaging services, Narayana Health, Narayana Hrudayalaya, Multispeciality Hospital-Shaw Mazumdar Medical Centre , Bengaluru, India
| | - Vimal Raj
- Consultant Radiology, Department of Radiology and Imaging services, Narayana Health, Narayana Hrudayalaya, Multispeciality Hospital-Shaw Mazumdar Medical Centre , Bengaluru, India
| | - Sejal Shah
- Senior Consultant Paediatric Cardiology, Department of Pediatric cardiology, Narayana Health, Narayana Hrudayalaya , Bengaluru, India
| |
Collapse
|
7
|
Bhat V, Belaval V, Gadabanahalli K, Raj V, Shah S. Illustrated Imaging Essay on Congenital Heart Diseases: Multimodality Approach Part III: Cyanotic Heart Diseases and Complex Congenital Anomalies. J Clin Diagn Res 2016; 10:TE01-10. [PMID: 27630924 DOI: 10.7860/jcdr/2016/21443.8210] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2015] [Accepted: 04/02/2016] [Indexed: 11/24/2022]
Abstract
From the stand point of radiographic analysis most of the complex cyanotic congenital heart diseases (CHD), can be divided into those associated with decreased or increased pulmonary vascularity. Combination of a specific cardiac configuration and status of lung vasculature in a clinical context allows plain film diagnosis to be predicted in some CHD. Correlation of the position of the cardiac apex in relation to the visceral situs is an important information that can be obtained from the plain film. This information helps in gathering information about the atrio-ventricular, ventricular arterial concordance or discordance. Categorization of the cyanotic heart disease based on vascularity is presented below. Thorough understanding of cardiac anatomy by different imaging methods is essential in understanding and interpreting complex cardiac disease. Basic anatomical details and background for interpretation are provided in the previous parts of this presentation.
Collapse
Affiliation(s)
- Venkatraman Bhat
- Director and Head, Department of Radiology and Imaging Services, Narayana Health, Narayana Hrudayalaya, Multispeciality Hospital-Shaw Mazumdar Medical Centre , Bengaluru, Karnataka, India
| | - Vinay Belaval
- Junior Consultant, Department of Radiology and Imaging Services, Narayana Health, Narayana Hrudayalaya, Multispeciality Hospital-Shaw Mazumdar Medical Centre , Bengaluru, Karnataka, India
| | - Karthik Gadabanahalli
- Consultant, Department of Radiology and Imaging Services, Narayana Health, Narayana Hrudayalaya, Multispeciality Hospital-Shaw Mazumdar Medical Centre , Bengaluru, Karnataka, India
| | - Vimal Raj
- Consultant, Department of Radiology and Imaging Services, Narayana Health, Narayana Hrudayalaya, Multispeciality Hospital-Shaw Mazumdar Medical Centre , Bengaluru, Karnataka, India
| | - Sejal Shah
- Senior Consultant, Department of Pediatric Cardiology, Narayana Health, Narayana Hrudayalaya , Bengaluru, Karnataka, India
| |
Collapse
|