Deep Learning‐Based Analysis of Aortic Morphology From Three‐Dimensional MRI
- 12 January 2024
- journal article
- research article
- Published by Wiley in Journal of Magnetic Resonance Imaging
- Vol. 60 (4) , 1565-1576
Abstract
Background: Quantification of aortic morphology plays an important role in the evaluation and follow‐up assessment of patients with aortic diseases, but often requires labor‐intensive and operator‐dependent measurements. Automatic solutions would help enhance their quality and reproducibility.Purpose: To design a deep learning (DL)‐based automated approach for aortic landmarks and lumen detection derived from three‐dimensional (3D) MRI.Study Type: Retrospective.Population: Three hundred ninety‐one individuals (female: 47%, age = 51.9 ± 18.4) from three sites, including healthy subjects and patients (hypertension, aortic dilation, Turner syndrome), randomly divided into training/validation/test datasets (N = 236/77/78). Twenty‐five subjects were randomly selected and analyzed by three operators with different levels of expertise.Field Strength/Sequence: 1.5‐T and 3‐T, 3D spoiled gradient‐recalled or steady‐state free precession sequences.Assessment: Reinforcement learning and a two‐stage network trained using reference landmarks and segmentation from an existing semi‐automatic software were used for aortic landmark detection and segmentation from sinotubular junction to coeliac trunk. Aortic segments were defined using the detected landmarks while the aortic centerline was extracted from the segmentation and morphological indices (length, aortic diameter, and volume) were computed for both the reference and the proposed segmentations.Statistical Tests: Segmentation: Dice similarity coefficient (DSC), Hausdorff distance (HD), average symmetrical surface distance (ASSD); landmark detection: Euclidian distance (ED); model robustness: Spearman correlation, Bland–Altman analysis, Kruskal–Wallis test for comparisons between reference and DL‐derived aortic indices; inter‐observer study: Williams index (WI). A WI 95% confidence interval (CI) lower bound >1 indicates that the method is within the inter‐observer variability. A P‐value 0.95, mean bias <7%). Our segmentation and landmark detection performances were within the inter‐observer variability except the sinotubular junction landmark (CI = 0.96;1.04).Data Conclusion: A DL‐based aortic segmentation and anatomical landmark detection approach was developed and applied to 3D MRI data for achieve aortic morphology evaluation.Evidence Level: 3Technical Efficacy: Stage 2Keywords
Funding Information
- China Scholarship Council (202008070119)
- EIT Health (220636)
- Fondation pour la Recherche Médicale (ING20150532487)
This publication has 34 references indexed in Scilit:
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Automatic extraction of three‐dimensional thoracic aorta geometric model from phase contrast MRI for morphometric and hemodynamic characterizationMagnetic Resonance in Medicine, 2015
- Proximal Aortic Distensibility Is an Independent Predictor of All-Cause Mortality and Incident CV EventsJACC, 2014
- 2014 ESC Guidelines on the diagnosis and treatment of aortic diseasesEuropean Heart Journal, 2014
- Determinants and normal values of ascending aortic diameter by age, gender, and race/ethnicity in the Multi‐Ethnic Study of Atherosclerosis (MESA)Journal of Magnetic Resonance Imaging, 2013
- Acute aortic dissection type ABritish Journal of Surgery, 2012
- Automated segmentation of blood-flow regions in large thoracic arteries using 3D-cine PC-MRI measurementsInternational Journal of Computer Assisted Radiology and Surgery, 2011
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Aortic Aneurysm Diameter and Risk of Cardiovascular MortalityArteriosclerosis, Thrombosis, and Vascular Biology, 2001
- A methodology for evaluation of boundary detection algorithms on medical imagesIEEE Transactions on Medical Imaging, 1997