Deep Learning–based Method for Fully Automatic Quantification of Left Ventricle Function from Cine MR Images: A Multivendor, Multicenter Study

Abstract

To develop a deep learning-based method for fully automated quantification of left ventricular (LV) function from shortaxis cine MR images and to evaluate its performance in a multivendor and multicenter setting. Materials and Methods: This retrospective study included cine MRI data sets obtained from three major MRI vendors in four medical centers from 2008 to 2016. Three convolutional neural networks (CNNs) with the U-NET architecture were trained on data sets of increasing variability: (a) a single-vendor, single-center, homogeneous cohort of 100 patients (CNN1); (b) a single-vendor, multicenter, heterogeneous cohort of 200 patients (CNN2); and (c) a multivendor, multicenter, heterogeneous cohort of 400 patients (CNN3). All CNNs were tested on an independent multivendor, multicenter data set of 196 patients. CNN performance was evaluated with respect to the manual annotations from three experienced observers in terms of (a) LV detection accuracy, (b) LV segmentation accuracy, and (c) LV functional parameter accuracy. Automatic and manual results were compared with the paired Wilcoxon test, Pearson correlation, and Bland-Altman analysis. Results: CNN3 achieved the highest performance on the independent testing data set. The average perpendicular distance compared with manual analysis was 1.1 mm 6 0.3 for CNN3, compared with 1.5 mm 6 1.0 for CNN1 (P , .05) and 1.3 mm 6 0.6 for CNN2 (P , .05). The LV function parameters derived from CNN3 showed a high correlation (r 2  0.98) and agreement with those obtained by experts for data sets from different vendors and centers. Conclusion: A deep learning-based method trained on a data set with high variability can achieve fully automated and accurate cine MRI analysis on multivendor, multicenter cine MRI data.

Deep Learning for Cardiac Image Segmentation: A Review

“…This limitation prevents models to be deployed in the real world and therefore diminishes their impact for improving clinical workflows. To improve the model performance across MR images acquired from multiple vendors and multiple scanners, Tao et al (2019) collected a large multivendor, multi-center, heterogeneous labeled training set from patients with cardiovascular diseases. However, this approach may not scale to the real world, as it implies the collection of a vastly large dataset covering all possible cases.…”

Convolutional Neural Network for Automated FLAIR Lesion Segmentation on Clinical Brain MR Imaging

“…Deep learning-based approaches have recently demonstrated success with a variety of other image-segmentation tasks, including intracranial hemorrhage segmentation on CT, 19 structural neuroanatomy classification on brain MR imaging, 20 cartilage segmentation on knee MR imaging, 21 and left ventricular volume on cardiac MR imaging. 22 The winner of the 20th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2017 challenge for white matter hyperintensity segmentation 23 was based on a U-Net. 24 Therefore, we adopted a deep learning approach, adapting a U-Net convolutional neural network (CNN) architecture for 3D imaging for the task of disease-invariant FLAIR lesion segmentation.…”

Deep learning‐based quantification of PET/CT prostate gland uptake: association with overall survival

“…In recent years, deep-learning (DL) has become the method of choice for automated image analysis (Lakhani et al, 2018). Radiology studies have reported on application of deep learning in different organs (Lehman et al, 2018;Nam et al, 2018;Tao et al, 2019). Still, the prognostic role of that application remains undefined and further investigation is needed.…”