TY - JOUR
T1 - Deep‐Learning‐Based Preprocessing for Quantitative Myocardial Perfusion MRI
AU - Scannell, Cian M.
AU - Veta, Mitko
AU - Villa, Adriana D.M.
AU - Sammut, Eva C.
AU - Lee, Jack
AU - Breeuwer, Marcel
AU - Chiribiri, Amedeo
PY - 2020/6/1
Y1 - 2020/6/1
N2 - Background: Quantitative myocardial perfusion cardiac MRI can provide a fast and robust assessment of myocardial perfusion status for the noninvasive diagnosis of myocardial ischemia while being more objective than visual assessment. However, it currently has limited use in clinical practice due to the challenging postprocessing required, particularly the segmentation. Purpose: To evaluate the efficacy of an automated deep learning (DL) pipeline for image processing prior to quantitative analysis. Study Type: Retrospective. Population: In all, 175 (350 MRI scans; 1050 image series) clinical patients under both rest and stress conditions (135/10/30 training/validation/test). Field Strength/Sequence: 3.0T/2D multislice saturation recovery T
1-weighted gradient echo sequence. Assessment: Accuracy was assessed, as compared to the manual operator, through the mean square error of the distance between landmarks and the Dice similarity coefficient of the segmentation and bounding box detection. Quantitative perfusion maps obtained using the automated DL-based processing were compared to the results obtained with the manually processed images. Statistical Tests: Bland–Altman plots and intraclass correlation coefficient (ICC) were used to assess the myocardial blood flow (MBF) obtained using the automated DL pipeline, as compared to values obtained by a manual operator. Results: The mean (SD) error in the detection of the time of peak signal enhancement in the left ventricle was 1.49 (1.4) timeframes. The mean (SD) Dice similarity coefficients for the bounding box and myocardial segmentation were 0.93 (0.03) and 0.80 (0.06), respectively. The mean (SD) error in the RV insertion point was 2.8 (1.8) mm. The Bland–Altman plots showed a bias of 2.6% of the mean MBF between the automated and manually processed MBF values on a per-myocardial segment basis. The ICC was 0.89, 95% confidence interval = [0.87, 0.90]. Data Conclusion: We showed high accuracy, compared to manual processing, for the DL-based processing of myocardial perfusion data leading to quantitative values that are similar to those achieved with manual processing. Level of Evidence: 3. Technical Efficacy Stage: 1. J. Magn. Reson. Imaging 2020;51:1689–1696.
AB - Background: Quantitative myocardial perfusion cardiac MRI can provide a fast and robust assessment of myocardial perfusion status for the noninvasive diagnosis of myocardial ischemia while being more objective than visual assessment. However, it currently has limited use in clinical practice due to the challenging postprocessing required, particularly the segmentation. Purpose: To evaluate the efficacy of an automated deep learning (DL) pipeline for image processing prior to quantitative analysis. Study Type: Retrospective. Population: In all, 175 (350 MRI scans; 1050 image series) clinical patients under both rest and stress conditions (135/10/30 training/validation/test). Field Strength/Sequence: 3.0T/2D multislice saturation recovery T
1-weighted gradient echo sequence. Assessment: Accuracy was assessed, as compared to the manual operator, through the mean square error of the distance between landmarks and the Dice similarity coefficient of the segmentation and bounding box detection. Quantitative perfusion maps obtained using the automated DL-based processing were compared to the results obtained with the manually processed images. Statistical Tests: Bland–Altman plots and intraclass correlation coefficient (ICC) were used to assess the myocardial blood flow (MBF) obtained using the automated DL pipeline, as compared to values obtained by a manual operator. Results: The mean (SD) error in the detection of the time of peak signal enhancement in the left ventricle was 1.49 (1.4) timeframes. The mean (SD) Dice similarity coefficients for the bounding box and myocardial segmentation were 0.93 (0.03) and 0.80 (0.06), respectively. The mean (SD) error in the RV insertion point was 2.8 (1.8) mm. The Bland–Altman plots showed a bias of 2.6% of the mean MBF between the automated and manually processed MBF values on a per-myocardial segment basis. The ICC was 0.89, 95% confidence interval = [0.87, 0.90]. Data Conclusion: We showed high accuracy, compared to manual processing, for the DL-based processing of myocardial perfusion data leading to quantitative values that are similar to those achieved with manual processing. Level of Evidence: 3. Technical Efficacy Stage: 1. J. Magn. Reson. Imaging 2020;51:1689–1696.
KW - automated image analysis
KW - convolutional neural networks
KW - machine learning
KW - quantitative myocardial perfusion
UR - http://www.scopus.com/inward/record.url?scp=85075028311&partnerID=8YFLogxK
U2 - 10.1002/jmri.26983
DO - 10.1002/jmri.26983
M3 - Article
C2 - 31710769
AN - SCOPUS:85075028311
SN - 1522-2586
VL - 51
SP - 1689
EP - 1696
JO - Journal of Magnetic Resonance Imaging
JF - Journal of Magnetic Resonance Imaging
IS - 6
ER -