Learning physical properties in complex visual scenes: An intelligent machine for perceiving blood flow dynamics from static CT angiography imaging. (March 2020)

• Record Type: Journal Article
• Authors: Gao, Zhifan; Wang, Xin; Sun, Shanhui; Wu, Dan; Bai, Junjie; Yin, Youbing; Liu, Xin; Zhang, Heye; de Albuquerque, Victor Hugo C.
• Is Part Of: Neural networks. Volume 123(2020)
• Page Start: 82
• Page End: 93
• Publication Date: 2020-03
• Subjects: Learning physical properties -- Tree-structured RNN -- LSTM -- Fractional flow reserve -- CT angiography; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2019.11.017
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Humans perceive physical properties such as motion and elastic force by observing objects in visual scenes. Recent research has proven that computers are capable of inferring physical properties from camera images like humans. However, few studies perceive the physical properties in more complex environment, i.e. humans have difficulty estimating physical quantities directly from the visual observation, or encounter difficulty visualizing the physical process in mind according to their daily experiences. As an appropriate example, fractional flow reserve (FFR), which measures the blood pressure difference across the vessel stenosis, becomes an important physical quantitative value determining the likelihood of myocardial ischemia in clinical coronary intervention procedure. In this study, we propose a novel deep neural network solution (TreeVes-Net) that allows machines to perceive FFR values directly from static coronary CT angiography images. Our framework fully utilizes a tree-structured recurrent neural network (RNN) with a coronary representation encoder. The encoder captures coronary geometric information providing the blood fluid-related representation. The tree-structured RNN builds a long-distance spatial dependency of blood flow information inside the coronary tree. The experiments performed on 13000 synthetic coronary trees and 180 real coronary trees from clinical patients show that the values of the area under ROC curve (AUC) are 0.92 and 0.93 under two clinical criterions. These results can demonstrate the effectiveness of our framework and its superiority to seven FFR computation methods based on machine learning.