Key result
Automated deep-learning CMR segmentation matches expert accuracy with a mean Dice score of ~0.84.
Why the study?
Automated segmentation and analysis of joint cardiac MRI T1 and T2 mapping lacked an AI solution integrated for inline use on MRI scanners.
Does an AI-based convolutional neural network provide accurate automated myocardial segmentation of joint T1 and T2 mapping compared to expert cardiologists?
Observational (n=807)
Yes
Does an AI-based convolutional neural network provide accurate automated myocardial segmentation of joint T1 and T2 mapping compared to expert cardiologists?
An AI-based deep learning model can accurately perform automated inline myocardial segmentation of joint T1 and T2 mapping with performance equivalent to human experts.
Supports feasibility of automated joint T1/T2 mapping segmentation; leaves open prospective validation before clinical use.
Purpose To develop an artificial intelligence (AI) solution for automated segmentation and analysis of joint cardiac MRI short-axis T1 and T2 mapping. Materials and Methods In this retrospective study, a joint T1 and T2 mapping sequence was used to acquire 4240 maps from 807 patients across two hospitals between March and November 2020. Five hundred nine maps from 94 consecutive patients were assigned to a holdout testing set. A convolutional neural network was trained to segment the endocardial and epicardial contours with use of an edge probability estimation approach. Training labels were segmented by an expert cardiologist. Predicted contours were processed to yield mapping values for each of the 16 American Heart Association segments. Network segmentation performance and segment-wise measurements on the testing set were compared with those of two experts on the holdout testing set. The AI model was fully integrated using open-source software to run on MRI scanners. Results A total of 3899 maps (92%) were deemed artifact-free and suitable for human segmentation. AI segmentation closely matched that of each expert (mean Dice coefficient, 0.82 ± 0.07 [SD] vs expert 1 and 0.86 ± 0.06 vs expert 2) and compared favorably with interexpert agreement (Dice coefficient, 0.84 ± 0.06 for expert 1 vs expert 2). AI-derived segment-wise values for native T1, postcontrast T1, and T2 mapping correlated with expert-derived values (R2 = 0.96, 0.98, and 0.87, respectively, vs expert 1, and 0.97, 0.99, and 0.92 vs expert 2) and fell within the range of interexpert reproducibility (R2 = 0.97, 0.99, and 0.90, respectively). The AI model has since been deployed at two hospitals, enabling automated inline analysis. Conclusion Automated inline analysis of joint T1 and T2 mapping allows accurate segment-wise tissue characterization, with performance equivalent to that of human experts. Keywords: MRI, Neural Networks, Cardiac, Heart Supplemental material is available for this article.
No takes yet. Share an insight, caveat, or question.
Howard et al. (2022) conducted an observational in Cardiac MRI (n=807). Automated inline myocardial segmentation using deep learning vs. Expert cardiologist segmentation was evaluated on Segmentation performance (Dice coefficient) and segment-wise measurements (R2). Automated inline myocardial segmentation of joint T1 and T2 mapping using deep learning achieved accuracy equivalent to human experts (mean Dice coefficient 0.82-0.86).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: