1
|
Tayebi Arasteh S, Romanowicz J, Pace DF, Golland P, Powell AJ, Maier AK, Truhn D, Brosch T, Weese J, Lotfinia M, van der Geest RJ, Moghari MH. Automated segmentation of 3D cine cardiovascular magnetic resonance imaging. Front Cardiovasc Med 2023; 10:1167500. [PMID: 37904806 PMCID: PMC10613522 DOI: 10.3389/fcvm.2023.1167500] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2023] [Accepted: 09/18/2023] [Indexed: 11/01/2023] Open
Abstract
Introduction As the life expectancy of children with congenital heart disease (CHD) is rapidly increasing and the adult population with CHD is growing, there is an unmet need to improve clinical workflow and efficiency of analysis. Cardiovascular magnetic resonance (CMR) is a noninvasive imaging modality for monitoring patients with CHD. CMR exam is based on multiple breath-hold 2-dimensional (2D) cine acquisitions that should be precisely prescribed and is expert and institution dependent. Moreover, 2D cine images have relatively thick slices, which does not allow for isotropic delineation of ventricular structures. Thus, development of an isotropic 3D cine acquisition and automatic segmentation method is worthwhile to make CMR workflow straightforward and efficient, as the present work aims to establish. Methods Ninety-nine patients with many types of CHD were imaged using a non-angulated 3D cine CMR sequence covering the whole-heart and great vessels. Automatic supervised and semi-supervised deep-learning-based methods were developed for whole-heart segmentation of 3D cine images to separately delineate the cardiac structures, including both atria, both ventricles, aorta, pulmonary arteries, and superior and inferior vena cavae. The segmentation results derived from the two methods were compared with the manual segmentation in terms of Dice score, a degree of overlap agreement, and atrial and ventricular volume measurements. Results The semi-supervised method resulted in a better overlap agreement with the manual segmentation than the supervised method for all 8 structures (Dice score 83.23 ± 16.76% vs. 77.98 ± 19.64%; P-value ≤0.001). The mean difference error in atrial and ventricular volumetric measurements between manual segmentation and semi-supervised method was lower (bias ≤ 5.2 ml) than the supervised method (bias ≤ 10.1 ml). Discussion The proposed semi-supervised method is capable of cardiac segmentation and chamber volume quantification in a CHD population with wide anatomical variability. It accurately delineates the heart chambers and great vessels and can be used to accurately calculate ventricular and atrial volumes throughout the cardiac cycle. Such a segmentation method can reduce inter- and intra- observer variability and make CMR exams more standardized and efficient.
Collapse
Affiliation(s)
- Soroosh Tayebi Arasteh
- Department of Cardiology, Boston Children’s Hospital, and Department of Pediatrics, Harvard Medical School, Boston, MA, United States
- Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
- Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany
| | - Jennifer Romanowicz
- Department of Cardiology, Boston Children’s Hospital, and Department of Pediatrics, Harvard Medical School, Boston, MA, United States
- Department of Cardiology, Children’s Hospital Colorado, and School of Medicine, University of Colorado, Aurora, CO, United States
| | - Danielle F. Pace
- Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA, United States
- Computer Science & Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA, United States
| | - Polina Golland
- Computer Science & Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA, United States
| | - Andrew J. Powell
- Department of Cardiology, Boston Children’s Hospital, and Department of Pediatrics, Harvard Medical School, Boston, MA, United States
| | - Andreas K. Maier
- Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Daniel Truhn
- Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany
| | - Tom Brosch
- Philips Research Laboratories, Hamburg, Germany
| | | | - Mahshad Lotfinia
- Institute of Heat and Mass Transfer, RWTH Aachen University, Aachen, Germany
| | | | - Mehdi H. Moghari
- Department of Radiology, Children’s Hospital Colorado, and School of Medicine, University of Colorado, Aurora, CO, United States
| |
Collapse
|
2
|
Turenne AD, Szewczyk J, Eugene F, Bras AL, Blanc R, Haigron P. Statistical shape model of vessel centerline for endovascular paths comparison in mechanical thrombectomy. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021; 2021:1765-1769. [PMID: 34891629 DOI: 10.1109/embc46164.2021.9630921] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Endovascular interventions are experiencing an important development. Despite many advantages of this type of intervention, catheter navigation is still a cause of difficulties or failure. Mechanical thrombectomy is one of these interventions where navigation difficulties are related to the ability to navigate the aortic arch and access the carotid. These difficulties are due to the selection of adequate catheters and guides for a specific anatomy and to the technical gesture to operate. The objective of this work is to propose a method to find similar endovascular navigation paths from pre-existing patients to support intervention in mechanical thrombectomy. For each patient, iso-centerlines of the aortic arch and supra-aortic trunks are extracted from pre-operative magnetic resonance angiography volume. A statistical shape model is computed from these vascular structure iso-centerlines. Euclidean distance between vectors of statistical shape model modes is used to compare endovascular navigation paths. A set of 6 patient cases was used to compute the statistical shape model. For validation, an additional set of 5 patient cases was considered to generate new iso-centerlines.Retrieval of closest iso-centerlines were correct in more than 95% of cases with the proposed method while this percentage goes down to 43% with Euclidean distance between 3D points of iso-centerlines.Clinical relevance-The presented method allows physicians to retrieve past navigation paths similar to a new one. Used in planning, this could allow to anticipate navigation difficulties in mechanical thrombectomy.
Collapse
|
3
|
Thamsen B, Yevtushenko P, Gundelwein L, Setio AAA, Lamecker H, Kelm M, Schafstedde M, Heimann T, Kuehne T, Goubergrits L. Synthetic Database of Aortic Morphometry and Hemodynamics: Overcoming Medical Imaging Data Availability. IEEE TRANSACTIONS ON MEDICAL IMAGING 2021; 40:1438-1449. [PMID: 33544670 DOI: 10.1109/tmi.2021.3057496] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
Modeling of hemodynamics and artificial intelligence have great potential to support clinical diagnosis and decision making. While hemodynamics modeling is extremely time- and resource-consuming, machine learning (ML) typically requires large training data that are often unavailable. The aim of this study was to develop and evaluate a novel methodology generating a large database of synthetic cases with characteristics similar to clinical cohorts of patients with coarctation of the aorta (CoA), a congenital heart disease associated with abnormal hemodynamics. Synthetic data allows use of ML approaches to investigate aortic morphometric pathology and its influence on hemodynamics. Magnetic resonance imaging data (154 patients as well as of healthy subjects) of aortic shape and flow were used to statistically characterize the clinical cohort. The methodology generating the synthetic cohort combined statistical shape modeling of aortic morphometry and aorta inlet flow fields and numerical flow simulations. Hierarchical clustering and non-linear regression analysis were successfully used to investigate the relationship between morphometry and hemodynamics and to demonstrate credibility of the synthetic cohort by comparison with a clinical cohort. A database of 2652 synthetic cases with realistic shape and hemodynamic properties was generated. Three shape clusters and respective differences in hemodynamics were identified. The novel model predicts the CoA pressure gradient with a root mean square error of 4.6 mmHg. In conclusion, synthetic data for anatomy and hemodynamics is a suitable means to address the lack of large datasets and provide a powerful basis for ML to gain new insights into cardiovascular diseases.
Collapse
|
5
|
Rodriguez-Florez N, Bruse JL, Borghi A, Vercruysse H, Ong J, James G, Pennec X, Dunaway DJ, Jeelani NUO, Schievano S. Statistical shape modelling to aid surgical planning: associations between surgical parameters and head shapes following spring-assisted cranioplasty. Int J Comput Assist Radiol Surg 2017; 12:1739-1749. [PMID: 28550406 PMCID: PMC5608871 DOI: 10.1007/s11548-017-1614-5] [Citation(s) in RCA: 15] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2017] [Accepted: 05/16/2017] [Indexed: 12/04/2022]
Abstract
PURPOSE Spring-assisted cranioplasty is performed to correct the long and narrow head shape of children with sagittal synostosis. Such corrective surgery involves osteotomies and the placement of spring-like distractors, which gradually expand to widen the skull until removal about 4 months later. Due to its dynamic nature, associations between surgical parameters and post-operative 3D head shape features are difficult to comprehend. The current study aimed at applying population-based statistical shape modelling to gain insight into how the choice of surgical parameters such as craniotomy size and spring positioning affects post-surgical head shape. METHODS Twenty consecutive patients with sagittal synostosis who underwent spring-assisted cranioplasty at Great Ormond Street Hospital for Children (London, UK) were prospectively recruited. Using a nonparametric statistical modelling technique based on mathematical currents, a 3D head shape template was computed from surface head scans of sagittal patients after spring removal. Partial least squares (PLS) regression was employed to quantify and visualise trends of localised head shape changes associated with the surgical parameters recorded during spring insertion: anterior-posterior and lateral craniotomy dimensions, anterior spring position and distance between anterior and posterior springs. RESULTS Bivariate correlations between surgical parameters and corresponding PLS shape vectors demonstrated that anterior-posterior (Pearson's [Formula: see text]) and lateral craniotomy dimensions (Spearman's [Formula: see text]), as well as the position of the anterior spring ([Formula: see text]) and the distance between both springs ([Formula: see text]) on average had significant effects on head shapes at the time of spring removal. Such effects were visualised on 3D models. CONCLUSIONS Population-based analysis of 3D post-operative medical images via computational statistical modelling tools allowed for detection of novel associations between surgical parameters and head shape features achieved following spring-assisted cranioplasty. The techniques described here could be extended to other cranio-maxillofacial procedures in order to assess post-operative outcomes and ultimately facilitate surgical decision making.
Collapse
Affiliation(s)
- Naiara Rodriguez-Florez
- UCL Great Ormond Street Institute of Child Health, 30 Guilford Street, London, WC1N 1EH, UK.
- Craniofacial Unit, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK.
| | - Jan L Bruse
- Craniofacial Unit, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK
- Centre for Cardiovascular Imaging, UCL Institute of Cardiovascular Science, London, UK
| | - Alessandro Borghi
- UCL Great Ormond Street Institute of Child Health, 30 Guilford Street, London, WC1N 1EH, UK
- Craniofacial Unit, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK
| | - Herman Vercruysse
- Craniofacial Unit, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK
| | - Juling Ong
- Craniofacial Unit, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK
| | - Greg James
- UCL Great Ormond Street Institute of Child Health, 30 Guilford Street, London, WC1N 1EH, UK
- Craniofacial Unit, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK
| | | | - David J Dunaway
- UCL Great Ormond Street Institute of Child Health, 30 Guilford Street, London, WC1N 1EH, UK
- Craniofacial Unit, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK
| | - N U Owase Jeelani
- UCL Great Ormond Street Institute of Child Health, 30 Guilford Street, London, WC1N 1EH, UK
- Craniofacial Unit, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK
| | - Silvia Schievano
- UCL Great Ormond Street Institute of Child Health, 30 Guilford Street, London, WC1N 1EH, UK
- Craniofacial Unit, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK
- Centre for Cardiovascular Imaging, UCL Institute of Cardiovascular Science, London, UK
| |
Collapse
|
6
|
Bruse JL, Zuluaga MA, Khushnood A, McLeod K, Ntsinjana HN, Hsia TY, Sermesant M, Pennec X, Taylor AM, Schievano S. Detecting Clinically Meaningful Shape Clusters in Medical Image Data: Metrics Analysis for Hierarchical Clustering Applied to Healthy and Pathological Aortic Arches. IEEE Trans Biomed Eng 2017; 64:2373-2383. [PMID: 28221991 DOI: 10.1109/tbme.2017.2655364] [Citation(s) in RCA: 31] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
OBJECTIVE Today's growing medical image databases call for novel processing tools to structure the bulk of data and extract clinically relevant information. Unsupervised hierarchical clustering may reveal clusters within anatomical shape data of patient populations as required for modern precision medicine strategies. Few studies have applied hierarchical clustering techniques to three-dimensional patient shape data and results depend heavily on the chosen clustering distance metrics and linkage functions. In this study, we sought to assess clustering classification performance of various distance/linkage combinations and of different types of input data to obtain clinically meaningful shape clusters. METHODS We present a processing pipeline combining automatic segmentation, statistical shape modeling, and agglomerative hierarchical clustering to automatically subdivide a set of 60 aortic arch anatomical models into healthy controls, two groups affected by congenital heart disease, and their respective subgroups as defined by clinical diagnosis. Results were compared with traditional morphometrics and principal component analysis of shape features. RESULTS Our pipeline achieved automatic division of input shape data according to primary clinical diagnosis with high F-score (0.902 ± 0.042) and Matthews correlation coefficient (0.851 ± 0.064) using the correlation/weighted distance/linkage combination. Meaningful subgroups within the three patient groups were obtained and benchmark scores for automatic segmentation and classification performance are reported. CONCLUSION Clustering results vary depending on the distance/linkage combination used to divide the data. Yet, clinically relevant shape clusters and subgroups could be found with high specificity and low misclassification rates. SIGNIFICANCE Detecting disease-specific clusters within medical image data could improve image-based risk assessment, treatment planning, and medical device development in complex disease.
Collapse
|