Convolutional Neural Networks for the Detection of Diseased Hearts Using CT Images and Left Atrium Patches

• Type of Material: Article
• Authors: James D. Dormer, Emory University; Martin Halicek, Emory University; Ling Ma, Emory University; Carolyn Reilly, Emory University; Eduard Schreibmann, Emory University; Baowei Fei, Emory University
• Language: English
• Date: 2018-01-01
• Publisher: Society of Photo-optical Instrumentation Engineers (SPIE)
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2018 SPIE.
• Final Published Version (URL): http://dx.doi.org/10.1117/12.2293548
• Title of Journal or Parent Work: Proceedings of SPIE
• ISSN: 0277-786X
• Volume: 10575
• Grant/Funding Information: This research is supported in part by NIH grants (CA176684, CA156775, and CA204254) and by the National Cancer Institute (NCI) via NRG Oncology, a member of the NCI National Clinical Trials Network with Federal funds from the Department of Health and Human Services under Grant Number U10 CA37422.
• Keywords: GUIDELINES; Physical Sciences; FAILURE ASSOCIATION; Cardiovascular disease (CVD); ESC; EUROPEAN-SOCIETY; Computer-aided diagnosis; HFA; Optics; COLLABORATION; Science & Technology; 3D Computed tomography; TASK-FORCE; Deep learning; Convolutional neural networks; DIAGNOSIS; Radiology, Nuclear Medicine & Medical Imaging; Heart disease; Life Sciences & Biomedicine; Classification
• Research Categories: Health Sciences, Radiology

Abstract

Cardiovascular disease is a leading cause of death in the United States. The identification of cardiac diseases on conventional three-dimensional (3D) CT can have many clinical applications. An automated method that can distinguish between healthy and diseased hearts could improve diagnostic speed and accuracy when the only modality available is conventional 3D CT. In this work, we proposed and implemented convolutional neural networks (CNNs) to identify diseased hears on CT images. Six patients with healthy hearts and six with previous cardiovascular disease events received chest CT. After the left atrium for each heart was segmented, 2D and 3D patches were created. A subset of the patches were then used to train separate convolutional neural networks using leave-one-out cross-validation of patient pairs. The results of the two neural networks were compared, with 3D patches producing the higher testing accuracy. The full list of 3D patches from the left atrium was then classified using the optimal 3D CNN model, and the receiver operating curves (ROCs) were produced. The final average area under the curve (AUC) from the ROC curves was 0.840 ± 0.065 and the average accuracy was 78.9% ± 5.9%. This demonstrates that the CNN-based method is capable of distinguishing healthy hearts from those with previous cardiovascular disease.