DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics
<jats:p>Myocardial strain analysis from cinematic magnetic resonance imaging (cine-MRI) data provides a more thorough characterization of cardiac mechanics than volumetric parameters such as left-ventricular ejection fraction, but sources of variation including segmentation and motion estimati...
| Main Authors: | , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media SA
2022
|
| Online Access: | https://hdl.handle.net/1721.1/143900 |
| _version_ | 1811069135912697856 |
|---|---|
| author | Morales, Manuel A van den Boomen, Maaike Nguyen, Christopher Kalpathy-Cramer, Jayashree Rosen, Bruce R Stultz, Collin M Izquierdo-Garcia, David Catana, Ciprian |
| author2 | Harvard University--MIT Division of Health Sciences and Technology |
| author_facet | Harvard University--MIT Division of Health Sciences and Technology Morales, Manuel A van den Boomen, Maaike Nguyen, Christopher Kalpathy-Cramer, Jayashree Rosen, Bruce R Stultz, Collin M Izquierdo-Garcia, David Catana, Ciprian |
| author_sort | Morales, Manuel A |
| collection | MIT |
| description | <jats:p>Myocardial strain analysis from cinematic magnetic resonance imaging (cine-MRI) data provides a more thorough characterization of cardiac mechanics than volumetric parameters such as left-ventricular ejection fraction, but sources of variation including segmentation and motion estimation have limited its wider clinical use. We designed and validated a fast, fully-automatic deep learning (DL) workflow to generate both volumetric parameters and strain measures from cine-MRI data consisting of segmentation and motion estimation convolutional neural networks. The final motion network design, loss function, and associated hyperparameters are the result of a thorough <jats:italic>ad hoc</jats:italic> implementation that we carefully planned specific for strain quantification, tested, and compared to other potential alternatives. The optimal configuration was trained using healthy and cardiovascular disease (CVD) subjects (<jats:italic>n</jats:italic> = 150). DL-based volumetric parameters were correlated (&gt;0.98) and without significant bias relative to parameters derived from manual segmentations in 50 healthy and CVD test subjects. Compared to landmarks manually-tracked on tagging-MRI images from 15 healthy subjects, landmark deformation using DL-based motion estimates from paired cine-MRI data resulted in an end-point-error of 2.9 ± 1.5 mm. Measures of end-systolic global strain from these cine-MRI data showed no significant biases relative to a tagging-MRI reference method. On 10 healthy subjects, intraclass correlation coefficient for intra-scanner repeatability was good to excellent (&gt;0.75) for all global measures and most polar map segments. In conclusion, we developed and evaluated the first end-to-end learning-based workflow for automated strain analysis from cine-MRI data to quantitatively characterize cardiac mechanics of healthy and CVD subjects.</jats:p> |
| first_indexed | 2024-09-23T08:06:17Z |
| format | Article |
| id | mit-1721.1/143900 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T08:06:17Z |
| publishDate | 2022 |
| publisher | Frontiers Media SA |
| record_format | dspace |
| spelling | mit-1721.1/1439002023-04-18T15:15:49Z DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics Morales, Manuel A van den Boomen, Maaike Nguyen, Christopher Kalpathy-Cramer, Jayashree Rosen, Bruce R Stultz, Collin M Izquierdo-Garcia, David Catana, Ciprian Harvard University--MIT Division of Health Sciences and Technology Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science <jats:p>Myocardial strain analysis from cinematic magnetic resonance imaging (cine-MRI) data provides a more thorough characterization of cardiac mechanics than volumetric parameters such as left-ventricular ejection fraction, but sources of variation including segmentation and motion estimation have limited its wider clinical use. We designed and validated a fast, fully-automatic deep learning (DL) workflow to generate both volumetric parameters and strain measures from cine-MRI data consisting of segmentation and motion estimation convolutional neural networks. The final motion network design, loss function, and associated hyperparameters are the result of a thorough <jats:italic>ad hoc</jats:italic> implementation that we carefully planned specific for strain quantification, tested, and compared to other potential alternatives. The optimal configuration was trained using healthy and cardiovascular disease (CVD) subjects (<jats:italic>n</jats:italic> = 150). DL-based volumetric parameters were correlated (&gt;0.98) and without significant bias relative to parameters derived from manual segmentations in 50 healthy and CVD test subjects. Compared to landmarks manually-tracked on tagging-MRI images from 15 healthy subjects, landmark deformation using DL-based motion estimates from paired cine-MRI data resulted in an end-point-error of 2.9 ± 1.5 mm. Measures of end-systolic global strain from these cine-MRI data showed no significant biases relative to a tagging-MRI reference method. On 10 healthy subjects, intraclass correlation coefficient for intra-scanner repeatability was good to excellent (&gt;0.75) for all global measures and most polar map segments. In conclusion, we developed and evaluated the first end-to-end learning-based workflow for automated strain analysis from cine-MRI data to quantitatively characterize cardiac mechanics of healthy and CVD subjects.</jats:p> 2022-07-20T17:04:00Z 2022-07-20T17:04:00Z 2021 2022-07-20T17:00:10Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/143900 Morales, Manuel A, van den Boomen, Maaike, Nguyen, Christopher, Kalpathy-Cramer, Jayashree, Rosen, Bruce R et al. 2021. "DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics." Frontiers in Cardiovascular Medicine, 8. en 10.3389/FCVM.2021.730316 Frontiers in Cardiovascular Medicine Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf Frontiers Media SA Frontiers |
| spellingShingle | Morales, Manuel A van den Boomen, Maaike Nguyen, Christopher Kalpathy-Cramer, Jayashree Rosen, Bruce R Stultz, Collin M Izquierdo-Garcia, David Catana, Ciprian DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics |
| title | DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics |
| title_full | DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics |
| title_fullStr | DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics |
| title_full_unstemmed | DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics |
| title_short | DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics |
| title_sort | deepstrain a deep learning workflow for the automated characterization of cardiac mechanics |
| url | https://hdl.handle.net/1721.1/143900 |
| work_keys_str_mv | AT moralesmanuela deepstrainadeeplearningworkflowfortheautomatedcharacterizationofcardiacmechanics AT vandenboomenmaaike deepstrainadeeplearningworkflowfortheautomatedcharacterizationofcardiacmechanics AT nguyenchristopher deepstrainadeeplearningworkflowfortheautomatedcharacterizationofcardiacmechanics AT kalpathycramerjayashree deepstrainadeeplearningworkflowfortheautomatedcharacterizationofcardiacmechanics AT rosenbrucer deepstrainadeeplearningworkflowfortheautomatedcharacterizationofcardiacmechanics AT stultzcollinm deepstrainadeeplearningworkflowfortheautomatedcharacterizationofcardiacmechanics AT izquierdogarciadavid deepstrainadeeplearningworkflowfortheautomatedcharacterizationofcardiacmechanics AT catanaciprian deepstrainadeeplearningworkflowfortheautomatedcharacterizationofcardiacmechanics |