1
|
Aly AH, Khandelwal P, Aly AH, Kawashima T, Mori K, Saito Y, Hung J, Gorman JH, Pouch AM, Gorman RC, Yushkevich PA. Fully Automated 3D Segmentation and Diffeomorphic Medial Modeling of the Left Ventricle Mitral Valve Complex in Ischemic Mitral Regurgitation. Med Image Anal 2022; 80:102513. [PMID: 35772323 DOI: 10.1016/j.media.2022.102513] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2021] [Revised: 05/30/2022] [Accepted: 06/10/2022] [Indexed: 10/18/2022]
Abstract
There is an urgent unmet need to develop a fully-automated image-based left ventricle mitral valve analysis tool to support surgical decision making for ischemic mitral regurgitation patients. This requires an automated tool for segmentation and modeling of the left ventricle and mitral valve from immediate pre-operative 3D transesophageal echocardiography. Previous works have presented methods for semi-automatically segmenting and modeling the mitral valve, but do not include the left ventricle and do not avoid self-intersection of the mitral valve leaflets during shape modeling. In this study, we develop and validate a fully automated algorithm for segmentation and shape modeling of the left ventricular mitral valve complex from pre-operative 3D transesophageal echocardiography. We performed a 3-fold nested cross validation study on two datasets from separate institutions to evaluate automated segmentations generated by nnU-net with the expert manual segmentation which yielded average overall Dice scores of 0.82±0.03 (set A), 0.87±0.08 (set B) respectively. A deformable medial template was subsequently fitted to the segmentation to generate shape models. Comparison of shape models to the manual and automatically generated segmentations resulted in an average Dice score of 0.93-0.94 and 0.75-0.81 for the left ventricle and mitral valve, respectively. This is a substantial step towards automatically analyzing the left ventricle mitral valve complex in the operating room.
Collapse
Affiliation(s)
- Ahmed H Aly
- Division of Cardiothoracic Surgery, The Ohio State University, Columbus, OH, USA; Department of Bioengineering, School of Engineering and Applied Sciences, University of Pennsylvania, Philadelphia, PA, USA; Gorman Cardiovascular Research Group, University of Pennsylvania, Philadelphia, PA, USA.
| | - Pulkit Khandelwal
- Department of Bioengineering, School of Engineering and Applied Sciences, University of Pennsylvania, Philadelphia, PA, USA
| | - Abdullah H Aly
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA; The Ohio State College of Medicine, Columbus, OH, USA
| | - Takayuki Kawashima
- Gorman Cardiovascular Research Group, University of Pennsylvania, Philadelphia, PA, USA
| | - Kazuki Mori
- Gorman Cardiovascular Research Group, University of Pennsylvania, Philadelphia, PA, USA
| | - Yoshiaki Saito
- Gorman Cardiovascular Research Group, University of Pennsylvania, Philadelphia, PA, USA
| | - Judy Hung
- Department of Cardiology at Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Joseph H Gorman
- Gorman Cardiovascular Research Group, University of Pennsylvania, Philadelphia, PA, USA; Department of Surgery, University of Pennsylvania, Philadelphia, PA, USA
| | - Alison M Pouch
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Robert C Gorman
- Gorman Cardiovascular Research Group, University of Pennsylvania, Philadelphia, PA, USA; Department of Surgery, University of Pennsylvania, Philadelphia, PA, USA
| | - Paul A Yushkevich
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
| |
Collapse
|
2
|
Rodell CB, Zhang ZL, Dusaj NN, Oquendo Y, Lee ME, Bouma W, Gorman JH, Burdick JA, Gorman RC. Injectable Shear-Thinning Hydrogels Prevent Ischemic Mitral Regurgitation and Normalize Ventricular Flow Dynamics. Semin Thorac Cardiovasc Surg 2019; 32:445-453. [PMID: 31682905 PMCID: PMC7195238 DOI: 10.1053/j.semtcvs.2019.10.015] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2019] [Accepted: 10/23/2019] [Indexed: 11/11/2022]
Abstract
Injectable hydrogels are known to attenuate left-ventricular (LV) remodeling following myocardial infarction (MI), dependent on material mechanical properties. The effect of hydrogel injection on ischemic mitral regurgitation (IMR) resultant from LV remodeling remains relatively unexplored. This study uses multiple imaging methods to evaluate the efficacy of injectable hydrogels with tunable modulus to prevent post-MI development of IMR. Posterolateral MI was induced in 20 sheep with subsequent epicardial injection of saline (control (MI); n = 7), soft hydrogel (guest-host crosslinking, modulus <1 kPa, n = 7), or stiff hydrogel (dual-crosslinking, modulus = 41.4 ± 4.3 kPa, n = 6) within the infarct region and 8-week follow-up. IMR and valve geometry were assessed by echocardiography. LV geometry (long-axis dimension, posterior chordae length) and ventricular flow dynamics were assessed by magnetic resonance imaging. IMR developed in MI controls at 8 weeks and was attenuated with hydrogel treatment (IMR grade for MI: 1.86 ± 0.69; guest-host crosslinking: 1.29 ± 1.11; dual-crosslinking: 0.50 ± 0.55, P = 0.02 vs MI). Tethering of the posterior leaflet increased in MI controls, but not with stiff hydrogel treatment. Across cohorts, IMR was correlated with changes in the long-axis dimension (Spearman R = 0.77) and posterior chordae length (Spearman R = 0.64). Intraventricular flow dynamics were highly disturbed in MI controls, but stiff hydrogel treatment normalized flow patterns and reduced the prevalence of large (≥2+ MR, >5 mL) regurgitant volumes. Injectable hydrogels attenuated subvalvular remodeling and leaflet tethering, preventing IMR development and normalizing LV flow dynamics. Hydrogels with a supraphysiological modulus yielded best outcomes.
Collapse
Affiliation(s)
- Christopher B. Rodell
- Department of Bioengineering, University of Pennsylvania, Philadelphia, Pennsylvania 19104
- Current affiliation: School of Biomedical Engineering, Science and Health Systems, Drexel University, Philadelphia, Pennsylvania 19104
| | - Zhang L. Zhang
- Gorman Cardiovascular Research Group, Department of Surgery, University of Pennsylvania, Philadelphia, Pennsylvania 19104
| | - Neville N. Dusaj
- Department of Bioengineering, University of Pennsylvania, Philadelphia, Pennsylvania 19104
| | - Yousi Oquendo
- Gorman Cardiovascular Research Group, Department of Surgery, University of Pennsylvania, Philadelphia, Pennsylvania 19104
| | - Madonna E. Lee
- Gorman Cardiovascular Research Group, Department of Surgery, University of Pennsylvania, Philadelphia, Pennsylvania 19104
| | - Wobbe Bouma
- Gorman Cardiovascular Research Group, Department of Surgery, University of Pennsylvania, Philadelphia, Pennsylvania 19104
| | - Joseph H. Gorman
- Gorman Cardiovascular Research Group, Department of Surgery, University of Pennsylvania, Philadelphia, Pennsylvania 19104
| | - Jason A. Burdick
- Department of Bioengineering, University of Pennsylvania, Philadelphia, Pennsylvania 19104
| | - Robert C. Gorman
- Gorman Cardiovascular Research Group, Department of Surgery, University of Pennsylvania, Philadelphia, Pennsylvania 19104
| |
Collapse
|
3
|
Midterm results of mitral valve repair done on patients with ischemic mitral regurgitation and nonischemic mitral regurgitation. COR ET VASA 2011. [DOI: 10.33678/cor.2011.117] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|