Share Email Print

Proceedings Paper

Deep learning angiography (DLA): three-dimensional C-arm cone beam CT angiography generated from deep learning method using a convolutional neural network
Author(s): Juan C. Montoya; Yinsheng Li; Charles Strother; Guang-Hong Chen
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Current clinical 3D-DSA requires the acquisition of two image volumes, before and after the injection of contrast media (i.e. mask and fill scans). Deep learning angiography (DLA) is a recently developed technique that enables the generation of mask-free 3D angiography using convolutional neural networks (CNN). In this work, the quantitative performance of DLA as a function of the number of layers in the deep neural network and the DLA inference computation time are investigated. Clinically indicated rotational angiography exams of 105 patients scanned with a C-arm conebeam CT system using a standard 3D-DSA imaging protocol for the assessment of cerebrovascular abnormalities were retrospectively collected. More than 185 million labeled voxels from contrast-enhanced images of 43 subjects were used as training and testing dataset. Multiple deep CNNs were trained to perform DLA. The trained DLA models were then applied in a validation cohort consisting of the remaining image volumes from 62 subjects and accuracy, sensitivity, precision and F1-scores were calculated for vasculature classification in relevant anatomy. The implementation of the best performing model was optimized for accelerated DLA inference and the computation time was measured under multiple hardware configurations.

Vasculature classification accuracy and 95% CI in the validation dataset were 98.7% ([98.3, 99.1] %) for the best performing model. DLA inference user time was 17 seconds for a throughput of 23 images/s. In conclusion, a 30-layer DLA model outperformed shallower networks and DLA inference computation time was demonstrated not be a limiting factor for current clinical practice.

Paper Details

Date Published: 9 March 2018
PDF: 9 pages
Proc. SPIE 10573, Medical Imaging 2018: Physics of Medical Imaging, 105731N (9 March 2018); doi: 10.1117/12.2293985
Show Author Affiliations
Juan C. Montoya, Univ. of Wisconsin School of Medicine and Public Health (United States)
Yinsheng Li, Univ. of Wisconsin School of Medicine and Public Health (United States)
Charles Strother, Univ. of Wisconsin School of Medicine and Public Health (United States)
Guang-Hong Chen, Univ. of Wisconsin School of Medicine and Public Health (United States)

Published in SPIE Proceedings Vol. 10573:
Medical Imaging 2018: Physics of Medical Imaging
Joseph Y. Lo; Taly Gilat Schmidt; Guang-Hong Chen, Editor(s)

© SPIE. Terms of Use
Back to Top