27 February 2018 Convolutional neural networks for the detection of diseased hearts using CT images and left atrium patches
Author Affiliations +
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.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
James D. Dormer, James D. Dormer, Martin Halicek, Martin Halicek, Ling Ma, Ling Ma, Carolyn M. Reilly, Carolyn M. Reilly, Eduard Schreibmann, Eduard Schreibmann, Baowei Fei, Baowei Fei, } "Convolutional neural networks for the detection of diseased hearts using CT images and left atrium patches", Proc. SPIE 10575, Medical Imaging 2018: Computer-Aided Diagnosis, 1057530 (27 February 2018); doi: 10.1117/12.2293548; https://doi.org/10.1117/12.2293548

Back to Top