Abstract
PurposeTo develop a deep neural network–based computational workflow for inline myocardial perfusion analysis that automatically delineates the myocardium, which improves the clinical workflow and offers a “one-click” solution.Materials and MethodsIn this retrospective study, consecutive adenosine stress and rest perfusion scans were acquired from three hospitals between October 1, 2018 and February 27, 2019. The training and validation set included 1825 perfusion series from 1034 patients (mean age, 60.6 years ± 14.2 [standard deviation]). The independent test set included 200 scans from 105 patients (mean age, 59.1 years ± 12.5). A convolutional neural network (CNN) model was trained to segment the left ventricular cavity, myocardium, and right ventricle by processing an incoming time series of perfusion images. Model outputs were compared with manual ground truth for accuracy of segmentation and flow measures derived on a global and per-sector basis with t test performed for statistical significance. The trained models were integrated onto MR scanners for effective inference.ResultsThe mean Dice ratio of automatic and manual segmentation was 0.93 ± 0.04. The CNN performed similarly to manual segmentation and flow measures for mean stress myocardial blood flow (MBF; 2.25 mL/min/g ± 0.59 vs 2.24 mL/min/g ± 0.59, P = .94) and mean rest MBF (1.08 mL/min/g ± 0.23 vs 1.07 mL/min/g ± 0.23, P = .83). The per-sector MBF values showed no difference between the CNN and manual assessment (P = .92). A central processing unit–based model inference on the MR scanner took less than 1 second for a typical perfusion scan of three slices.ConclusionThe described CNN was capable of cardiac perfusion mapping and integrated an automated inline implementation on the MR scanner, enabling one-click analysis and reporting in a manner comparable to manual assessment.Published under a CC BY 4.0 license.Supplemental material is available for this article.
Highlights
Materials and MethodsConsecutive adenosine stress and rest perfusion scans were acquired from three hospitals between October 1, 2018 and February 27, 2019
A one-click solution to acquire free-breathing perfusion images, perform pixelwise flow mapping, and conduct automated analysis with a 16-segment AHA report generated on the MR scanner was demonstrated
The collected datasets were previously included in a recent study [9] that developed a left ventricular (LV) blood pool detection solution for arterial input function images, whereas this study used the datasets for perfusion myocardium segmentation
Summary
The datasets consisted of adenosine stress and rest perfusion scans which were acquired at three hospitals (Barts Heart Centre, BHC; Royal Free Hospital, RFH; Leeds Teaching Hospitals, LTH) between October 1, 2018 and February 27, 2019. A total of 1825 perfusion scans from 1034 patients (mean age, 60.6 years 6 14.2; 692 men) were assembled and split into training and validation sets used for CNN model training. An independent hold-out consecutive test set was assembled, consisting of 200 perfusion scans from 105 patients (mean age, 59.1 years 6 12.5; 76 men). A screenshot (Fig 3) illustrates the perfusion mapping with overlaid CNN-based segmentation and AHA report applied to a patient with reduced regional perfusion This is a oneclick solution for automated analysis of quantitative perfusion flow mapping. A false-positive error was defined as the percentage area of the segmented mask in the CNN result that was not labeled in the manual one. A false-negative error was defined as the percentage area of segmented mask in the manual that was not labeled in the automated result. 2radiology-ai.rsna.org n Radiology: Artificial Intelligence Volume 2: Number 6—2020
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
