Share Email Print

Proceedings Paper

Machine learning algorithm for automatic detection of CT-identifiable hyperdense lesions associated with traumatic brain injury
Author(s): Krishna N. Keshavamurthy; Owen P. Leary; Lisa H. Merck; Benjamin Kimia; Scott Collins; David W. Wright; Jason W. Allen; Jeffrey F. Brock; Derek Merck
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Traumatic brain injury (TBI) is a major cause of death and disability in the United States. Time to treatment is often related to patient outcome. Access to cerebral imaging data in a timely manner is a vital component of patient care. Current methods of detecting and quantifying intracranial pathology can be time-consuming and require careful review of 2D/3D patient images by a radiologist. Additional time is needed for image protocoling, acquisition, and processing. These steps often occur in series, adding more time to the process and potentially delaying time-dependent management decisions for patients with traumatic brain injury.

Our team adapted machine learning and computer vision methods to develop a technique that rapidly and automatically detects CT-identifiable lesions. Specifically, we use scale invariant feature transform (SIFT)1 and deep convolutional neural networks (CNN)2 to identify important image features that can distinguish TBI lesions from background data. Our learning algorithm is a linear support vector machine (SVM)3. Further, we also employ tools from topological data analysis (TDA) for gleaning insights into the correlation patterns between healthy and pathological data. The technique was validated using 409 CT scans of the brain, acquired via the Progesterone for the Treatment of Traumatic Brain Injury phase III clinical trial (ProTECT_III) which studied patients with moderate to severe TBI4. CT data were annotated by a central radiologist and included patients with positive and negative scans. Additionally, the largest lesion on each positive scan was manually segmented. We reserved 80% of the data for training the SVM and used the remaining 20% for testing. Preliminary results are promising with 92.55% prediction accuracy (sensitivity = 91.15%, specificity = 93.45%), indicating the potential usefulness of this technique in clinical scenarios.

Paper Details

Date Published: 23 March 2017
PDF: 9 pages
Proc. SPIE 10134, Medical Imaging 2017: Computer-Aided Diagnosis, 101342G (23 March 2017); doi: 10.1117/12.2254227
Show Author Affiliations
Krishna N. Keshavamurthy, Brown Univ. (United States)
Owen P. Leary, Brown Univ. (United States)
Rhode Island Hospital (United States)
Lisa H. Merck, The Warren Alpert Medical School, Brown Univ. (United States)
Rhode Island Hospital (United States)
Benjamin Kimia, Brown Univ. (United States)
Scott Collins, Rhode Island Hospital (United States)
David W. Wright, Emory Univ. School of Medicine (United States)
Jason W. Allen, Emory Univ. School of Medicine (United States)
Jeffrey F. Brock, Brown Univ. (United States)
Derek Merck, Brown Univ. (United States)
Rhode Island Hospital (United States)

Published in SPIE Proceedings Vol. 10134:
Medical Imaging 2017: Computer-Aided Diagnosis
Samuel G. Armato III; Nicholas A. Petrick, 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?