Feasibility study of deep neural networks to classify intracranial aneurysms using angiographic parametric imaging

2019 ◽  
Author(s):  
Mohammad Mahdi Shiraz Bhurwani ◽  
Alexander R. Podgorsak ◽  
Anusha Ramesh Chandra ◽  
Ryan A. Rava ◽  
Kenneth V. Snyder ◽  
...  
Keyword(s):  
Neural Networks ◽  
Feasibility Study ◽  
Intracranial Aneurysms ◽  
Deep Neural Networks ◽  
Parametric Imaging

Feasibility study for use of angiographic parametric imaging and deep neural networks for intracranial aneurysm occlusion prediction

2019 ◽  
Vol 12 (7) ◽  
pp. 714-719 ◽  
Author(s):  
Mohammad Mahdi Shiraz Bhurwani ◽  
Muhammad Waqas ◽  
Alexander R Podgorsak ◽  
Kyle A Williams ◽  
Jason M Davies ◽  
...  
Keyword(s):  
Neural Networks ◽  
Network Performance ◽  
Deep Neural Networks ◽  
Characteristic Curve ◽  
Quantitative Imaging ◽  
Parametric Imaging ◽  
Post Intervention ◽  
Imaging Tool ◽  
Flow Parameters ◽  
Occlusion Prediction

BackgroundAngiographic parametric imaging (API), based on digital subtraction angiography (DSA), is a quantitative imaging tool that may be used to extract contrast flow parameters related to hemodynamic conditions in abnormal pathologies such as intracranial aneurysms (IAs).ObjectiveTo investigate the feasibility of using deep neural networks (DNNs) and API to predict IA occlusion using pre- and post-intervention DSAs.MethodsWe analyzed DSA images of IAs pre- and post-treatment to extract API parameters in the IA dome and the corresponding main artery (un-normalized data). We implemented a two-step correction to account for injection variability (normalized data) and projection foreshortening (relative data). A DNN was trained to predict a binary IA occlusion outcome: occluded/unoccluded. Network performance was assessed with area under the receiver operating characteristic curve (AUROC) and classification accuracy. To evaluate the effect of the proposed corrections, prediction accuracy analysis was performed after each normalization step.ResultsThe study included 190 IAs. The mean and median duration between treatment and follow-up was 9.8 and 8.0 months, respectively. For the un-normalized, normalized, and relative subgroups, the DNN average prediction accuracies for IA occlusion were 62.5% (95% CI 60.5% to 64.4%), 70.8% (95% CI 68.2% to 73.4%), and 77.9% (95% CI 76.2% to 79.6%). The average AUROCs for the same subgroups were 0.48 (0.44–0.52), 0.67 (0.61–0.73), and 0.77 (0.74–0.80).ConclusionsThe study demonstrated the feasibility of using API and DNNs to predict IA occlusion using only pre- and post-intervention angiographic information.

Deep neural networks trained with heavier data augmentation learn features closer to representations in hIT

2018 ◽  
Author(s):  
Alex Hernández-García ◽  
Johannes Mehrer ◽  
Nikolaus Kriegeskorte ◽  
Peter König ◽  
Tim C. Kietzmann
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation

Representation of adversarial images in deep neural networks and the human brain

2018 ◽  
Author(s):  
Chi Zhang ◽  
Xiaohan Duan ◽  
Ruyuan Zhang ◽  
Li Tong
Keyword(s):  
Neural Networks ◽  
Human Brain ◽  
Deep Neural Networks
Sign in / Sign up

Export Citation Format

Share Document