Octree Representation Improves Data Fidelity of Cardiac CT Images and Convolutional Neural Network Semantic Segmentation of Left Atrial and Ventricular Chambers

• Published in: Radiology. Artificial intelligence 2021-11, Vol.3 (6), p.e210036
• Main Authors: Gupta, Kunal, Sekhar, Nitesh, Vigneault, Davis M, Scott, Anderson R, Colvert, Brendan, Craine, Amanda, Raghavan, Adhithi, Contijoch, Francisco J
• Format: Article
• Language: English
• Subjects: Technical Development
• ISSN: 2638-6100; 2638-6100
• DOI: 10.1148/ryai.2021210036

To assess whether octree representation and octree-based convolutional neural networks (CNNs) improve segmentation accuracy of three-dimensional images. Cardiac CT angiographic examinations from 100 patients (mean age, 67 years ± 17 [standard deviation]; 60 men) performed between June 2012 and June 2018 with semantic segmentations of the left ventricular (LV) and left atrial (LA) blood pools at the end-diastolic and end-systolic cardiac phases were retrospectively evaluated. Image quality (root mean square error [RMSE]) and segmentation fidelity (global Dice and border Dice coefficients) metrics of the octree representation were compared with spatial downsampling for a range of memory footprints. Fivefold cross-validation was used to train an octree-based CNN and CNNs with spatial downsampling at four levels of image compression or spatial downsampling. The semantic segmentation performance of octree-based CNN (OctNet) was compared with the performance of U-Nets with spatial downsampling. Octrees provided high image and segmentation fidelity (median RMSE, 1.34 HU; LV Dice coefficient, 0.970; LV border Dice coefficient, 0.843) with a reduced memory footprint (87.5% reduction). Spatial downsampling to the same memory footprint had lower data fidelity (median RMSE, 12.96 HU; LV Dice coefficient, 0.852; LV border Dice coefficient, 0.310). OctNet segmentation improved the border segmentation Dice coefficient (LV, 0.612; LA, 0.636) compared with the highest performance among U-Nets with spatial downsampling (Dice coefficients: LV, 0.579; LA, 0.592). Octree-based representations can reduce the memory footprint and improve segmentation border accuracy. CT, Cardiac, Segmentation, Supervised Learning, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms© RSNA, 2021.