Comparison of In-Vivo and Ex-Vivo Ascending Aorta Elastic Properties through Automatic Deep Learning Segmentation of Cine-MRI and Biomechanical Testing
Ascending aortic aneurysm is a pathology that is important to be supervised and treated. During the years the aorta dilates, it becomes stiff, and its elastic properties decrease. In some cases, the aortic wall can rupture leading to aortic dissection with a high mortality rate. The main reference s...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/12/2/402 |
| _version_ | 1797440736644300800 |
|---|---|
| author | Emmanouil Markodimitrakis Siyu Lin Emmanouil Koutoulakis Diana Marcela Marín-Castrillón Francisco Aarón Tovar Sáez Sarah Leclerc Chloé Bernard Arnaud Boucher Benoit Presles Olivier Bouchot Thomas Decourselle Marie-Catherine Morgant Alain Lalande |
| author_facet | Emmanouil Markodimitrakis Siyu Lin Emmanouil Koutoulakis Diana Marcela Marín-Castrillón Francisco Aarón Tovar Sáez Sarah Leclerc Chloé Bernard Arnaud Boucher Benoit Presles Olivier Bouchot Thomas Decourselle Marie-Catherine Morgant Alain Lalande |
| author_sort | Emmanouil Markodimitrakis |
| collection | DOAJ |
| description | Ascending aortic aneurysm is a pathology that is important to be supervised and treated. During the years the aorta dilates, it becomes stiff, and its elastic properties decrease. In some cases, the aortic wall can rupture leading to aortic dissection with a high mortality rate. The main reference standard to measure when the patient needs to undertake surgery is the aortic diameter. However, the aortic diameter was shown not to be sufficient to predict aortic dissection, implying other characteristics should be considered. Therefore, the main objective of this work is to assess in-vivo the elastic properties of four different quadrants of the ascending aorta and compare the results with equivalent properties obtained ex-vivo. The database consists of 73 cine-MRI sequences of thoracic aorta acquired in axial orientation at the level of the pulmonary trunk. All the patients have dilated aorta and surgery is required. The exams were acquired just prior to surgery, each consisting of 30 slices on average across the cardiac cycle. Multiple deep learning architectures have been explored with different hyperparameters and settings to automatically segment the contour of the aorta on each image and then automatically calculate the aortic compliance. A semantic segmentation U-Net network outperforms the rest explored networks with a Dice score of 98.09% (±0.96%) and a Hausdorff distance of 4.88 mm (±1.70 mm). Local aortic compliance and local aortic wall strain were calculated from the segmented surfaces for each quadrant and then compared with elastic properties obtained ex-vivo. Good agreement was observed between Young’s modulus and in-vivo strain. Our results suggest that the lateral and posterior quadrants are the stiffest. In contrast, the medial and anterior quadrants have the lowest aortic stiffness. The in-vivo stiffness tendency agrees with the values obtained ex-vivo. We can conclude that our automatic segmentation method is robust and compatible with clinical practice (thanks to a graphical user interface), while the in-vivo elastic properties are reliable and compatible with the ex-vivo ones. |
| first_indexed | 2024-03-09T12:13:38Z |
| format | Article |
| id | doaj.art-343ecbbb6d654904bc837b79e21a845b |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-09T12:13:38Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-343ecbbb6d654904bc837b79e21a845b2023-11-30T22:49:29ZengMDPI AGJournal of Clinical Medicine2077-03832023-01-0112240210.3390/jcm12020402Comparison of In-Vivo and Ex-Vivo Ascending Aorta Elastic Properties through Automatic Deep Learning Segmentation of Cine-MRI and Biomechanical TestingEmmanouil Markodimitrakis0Siyu Lin1Emmanouil Koutoulakis2Diana Marcela Marín-Castrillón3Francisco Aarón Tovar Sáez4Sarah Leclerc5Chloé Bernard6Arnaud Boucher7Benoit Presles8Olivier Bouchot9Thomas Decourselle10Marie-Catherine Morgant11Alain Lalande12ImViA Laboratory, EA 7535, University of Burgundy and Franche-Comte, 21000 Dijon, FranceImViA Laboratory, EA 7535, University of Burgundy and Franche-Comte, 21000 Dijon, FranceImViA Laboratory, EA 7535, University of Burgundy and Franche-Comte, 21000 Dijon, FranceImViA Laboratory, EA 7535, University of Burgundy and Franche-Comte, 21000 Dijon, FranceImViA Laboratory, EA 7535, University of Burgundy and Franche-Comte, 21000 Dijon, FranceImViA Laboratory, EA 7535, University of Burgundy and Franche-Comte, 21000 Dijon, FranceImViA Laboratory, EA 7535, University of Burgundy and Franche-Comte, 21000 Dijon, FranceImViA Laboratory, EA 7535, University of Burgundy and Franche-Comte, 21000 Dijon, FranceImViA Laboratory, EA 7535, University of Burgundy and Franche-Comte, 21000 Dijon, FranceImViA Laboratory, EA 7535, University of Burgundy and Franche-Comte, 21000 Dijon, FranceCASIS—CArdiac Simulation & Imaging Software SAS, 21800 Quetigny, FranceImViA Laboratory, EA 7535, University of Burgundy and Franche-Comte, 21000 Dijon, FranceImViA Laboratory, EA 7535, University of Burgundy and Franche-Comte, 21000 Dijon, FranceAscending aortic aneurysm is a pathology that is important to be supervised and treated. During the years the aorta dilates, it becomes stiff, and its elastic properties decrease. In some cases, the aortic wall can rupture leading to aortic dissection with a high mortality rate. The main reference standard to measure when the patient needs to undertake surgery is the aortic diameter. However, the aortic diameter was shown not to be sufficient to predict aortic dissection, implying other characteristics should be considered. Therefore, the main objective of this work is to assess in-vivo the elastic properties of four different quadrants of the ascending aorta and compare the results with equivalent properties obtained ex-vivo. The database consists of 73 cine-MRI sequences of thoracic aorta acquired in axial orientation at the level of the pulmonary trunk. All the patients have dilated aorta and surgery is required. The exams were acquired just prior to surgery, each consisting of 30 slices on average across the cardiac cycle. Multiple deep learning architectures have been explored with different hyperparameters and settings to automatically segment the contour of the aorta on each image and then automatically calculate the aortic compliance. A semantic segmentation U-Net network outperforms the rest explored networks with a Dice score of 98.09% (±0.96%) and a Hausdorff distance of 4.88 mm (±1.70 mm). Local aortic compliance and local aortic wall strain were calculated from the segmented surfaces for each quadrant and then compared with elastic properties obtained ex-vivo. Good agreement was observed between Young’s modulus and in-vivo strain. Our results suggest that the lateral and posterior quadrants are the stiffest. In contrast, the medial and anterior quadrants have the lowest aortic stiffness. The in-vivo stiffness tendency agrees with the values obtained ex-vivo. We can conclude that our automatic segmentation method is robust and compatible with clinical practice (thanks to a graphical user interface), while the in-vivo elastic properties are reliable and compatible with the ex-vivo ones.https://www.mdpi.com/2077-0383/12/2/402cine-MRIdeep learning segmentationascending aortic elasticityyoung modulus |
| spellingShingle | Emmanouil Markodimitrakis Siyu Lin Emmanouil Koutoulakis Diana Marcela Marín-Castrillón Francisco Aarón Tovar Sáez Sarah Leclerc Chloé Bernard Arnaud Boucher Benoit Presles Olivier Bouchot Thomas Decourselle Marie-Catherine Morgant Alain Lalande Comparison of In-Vivo and Ex-Vivo Ascending Aorta Elastic Properties through Automatic Deep Learning Segmentation of Cine-MRI and Biomechanical Testing Journal of Clinical Medicine cine-MRI deep learning segmentation ascending aortic elasticity young modulus |
| title | Comparison of In-Vivo and Ex-Vivo Ascending Aorta Elastic Properties through Automatic Deep Learning Segmentation of Cine-MRI and Biomechanical Testing |
| title_full | Comparison of In-Vivo and Ex-Vivo Ascending Aorta Elastic Properties through Automatic Deep Learning Segmentation of Cine-MRI and Biomechanical Testing |
| title_fullStr | Comparison of In-Vivo and Ex-Vivo Ascending Aorta Elastic Properties through Automatic Deep Learning Segmentation of Cine-MRI and Biomechanical Testing |
| title_full_unstemmed | Comparison of In-Vivo and Ex-Vivo Ascending Aorta Elastic Properties through Automatic Deep Learning Segmentation of Cine-MRI and Biomechanical Testing |
| title_short | Comparison of In-Vivo and Ex-Vivo Ascending Aorta Elastic Properties through Automatic Deep Learning Segmentation of Cine-MRI and Biomechanical Testing |
| title_sort | comparison of in vivo and ex vivo ascending aorta elastic properties through automatic deep learning segmentation of cine mri and biomechanical testing |
| topic | cine-MRI deep learning segmentation ascending aortic elasticity young modulus |
| url | https://www.mdpi.com/2077-0383/12/2/402 |
| work_keys_str_mv | AT emmanouilmarkodimitrakis comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting AT siyulin comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting AT emmanouilkoutoulakis comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting AT dianamarcelamarincastrillon comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting AT franciscoaarontovarsaez comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting AT sarahleclerc comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting AT chloebernard comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting AT arnaudboucher comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting AT benoitpresles comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting AT olivierbouchot comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting AT thomasdecourselle comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting AT mariecatherinemorgant comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting AT alainlalande comparisonofinvivoandexvivoascendingaortaelasticpropertiesthroughautomaticdeeplearningsegmentationofcinemriandbiomechanicaltesting |