Share Email Print

Proceedings Paper

Blood flow anomaly detection via generative adversarial networks: a preliminary study
Author(s): Asha Singanamalli; Jhimli Mitra; Kirk Wallace; Prem Venugopal; Scott Smith; Larry Mo; Lai Yee Leung; Jonathan Morrison; Todd Rasmussen; Luca Marinelli
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This work explores a Generative Adversarial Network (GAN) based approach for hemorrhage detection on color Doppler ultrasound images of blood vessels. Given the challenges of collecting hemorrhage data and the inherent pathology variability, we investigate an unsupervised anomaly detection network which learns a manifold of normal blood flow variability and subsequently identifies anomalous flow patterns that fall outside the learned manifold. As an initial, feasibility study, we collected ultrasound color Doppler images of brachial arteries from 11 healthy volunteers. The images were pre-processed to mask out velocities in surrounding tissues and were subsequently cropped, resized, augmented and normalized. The network was trained on 1530 images from 8 healthy volunteers and tested on 70 images from 2 healthy volunteers. In addition, the network was tested on 6 synthetic images generated to simulate blood flow velocity patterns at the site of hemorrhage. Results show significant (p<0.05) differences in anomaly scores of normal arteries and simulated injured arteries. The residual images, or the reconstruction error maps, show promise in localizing anomalies at pixel level.

Paper Details

Date Published: 16 March 2020
PDF: 6 pages
Proc. SPIE 11315, Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling, 1131522 (16 March 2020); doi: 10.1117/12.2549094
Show Author Affiliations
Asha Singanamalli, GE Research (United States)
Jhimli Mitra, GE Research (United States)
Kirk Wallace, GE Research (United States)
Prem Venugopal, GE Research (United States)
Scott Smith, GE Research (United States)
Larry Mo, GE Research (United States)
Lai Yee Leung, Uniformed Services Univ. (United States)
Jonathan Morrison, Univ. of Maryland (United States)
Todd Rasmussen, Uniformed Services Univ. (United States)
Luca Marinelli, GE Research (United States)

Published in SPIE Proceedings Vol. 11315:
Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling
Baowei Fei; Cristian A. Linte, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?