An accurate and time-efficient deep learning-based system for automated segmentation and reporting of cardiac magnetic resonance-detected ischemic scar. (February 2023)

• Record Type: Journal Article
• Authors: Papetti, Daniele M; Van Abeelen, Kirsten; Davies, Rhodri; Menè, Roberto; Heilbron, Francesca; Perelli, Francesco P; Artico, Jessica; Seraphim, Andreas; Moon, James C; Parati, Gianfranco; Xue, Hui; Kellman, Peter; Badano, Luigi P; Besozzi, Daniela; Nobile, Marco S; Torlasco, Camilla
• Is Part Of: Computer methods and programs in biomedicine. Volume 229(2023)
• Publication Date: 2023-02
• Subjects: Deep learning -- Cardiovascular imaging -- Cardiac magnetic resonance -- Myocardial ischemic scar -- Image processing; BB bright-blood -- BB-LGE bright-blood late gadolinium enhancement -- b-SSFP balanced-steady-state free precession -- CNN convolution neural network -- CMR cardiovascular magnetic resonance -- CV cross validation -- DB-LGE dark-blood late gadolinium enhancement -- DL deep learning -- ICC intra class correlation -- IOU intersection over union -- LV left ventricle -- MIS myocardial infraction scar -- n-SD n-standard deviation -- PSIR phase-sensitive inversion recovery -- ReLU rectified linear unit -- RIM relative infracted mass -- ROI region of interest -- TI inversion time; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.107321
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Cardiac ischemic scar can be accurately assessed on dark blood late enhancement imaging. The developed model accurately segments ischemic scar (IoU: 0.85 on test dataset). The developed model reduces computational time 5-fold compared to manual segmentation. The developed system automatically generates a quantitative clinical report. Abstract: Background and objectives: Myocardial infarction scar (MIS) assessment by cardiac magnetic resonance provides prognostic information and guides patients' clinical management. However, MIS segmentation is time-consuming and not performed routinely. This study presents a deep-learning-based computational workflow for the segmentation of left ventricular (LV) MIS, for the first time performed on state-of-the-art dark-blood late gadolinium enhancement (DB-LGE) images, and the computation of MIS transmurality and extent. Methods: DB-LGE short-axis images of consecutive patients with myocardial infarction were acquired at 1.5T in two centres between Jan 1, 2019, and June 1, 2021. Two convolutional neural network (CNN) models based on the U-Net architecture were trained to sequentially segment the LV and MIS, by processing an incoming series of DB-LGE images. A 5-fold cross-validation was performed to assess the performance of the models. Model outputs were compared respectively with manual (LV endo- and epicardial border) and semi-automated (MIS, 4-Standard Deviation technique) ground truth to assess the accuracy of the segmentation. An automated post-processing and reporting tool was developed, computing MIS extent (expressed as relative infarcted mass) and transmurality. Results: The dataset included 1355 DB-LGE short-axis images from 144 patients (MIS in 942 images). High performance (> 0.85) as measured by the Intersection over Union metric was obtained for both the LV and MIS segmentations on the training sets. The performance for both LV and MIS segmentations was 0.83 on the test sets. Compared to the 4-Standard Deviation segmentation technique, our system was five times quicker (<1 min versus 7 ± 3 min), and required minimal user interaction. Conclusions: Our solution successfully addresses different issues related to automatic MIS segmentation, including accuracy, time-effectiveness, and the automatic generation of a clinical report.