Share Email Print

Proceedings Paper

Extracting 2D weak labels from volume labels using multiple instance learning in CT hemorrhage detection
Author(s): Samuel Remedios; Zihao Wu; Camilo Bermudez; Cailey I. Kerley; Snehashis Roy; Mayur B. Patel; John A. Butman; Bennett A. Landman; Dzung L. Pham
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Multiple instance learning (MIL) is a supervised learning methodology that aims to allow models to learn instance class labels from bag class labels, where a bag is defined to contain multiple instances. MIL is gaining traction for learning from weak labels but has not been widely applied to 3D medical imaging. MIL is well-suited to clinical CT acquisitions since (1) the highly anisotropic voxels hinder application of traditional 3D networks and (2) patch-based networks have limited ability to learn whole volume labels. In this work, we apply MIL with a deep convolutional neural network to identify whether clinical CT head image volumes possess one or more large hemorrhages (>; 20cm3 ), resulting in a learned 2D model without the need for 2D slice annotations. Individual image volumes are considered separate bags, and the slices in each volume are instances. Such a framework sets the stage for incorporating information obtained in clinical reports to help train a 2D segmentation approach. Within this context, we evaluate the data requirements to enable generalization of MIL by varying the amount of training data. Our results show that a training size of at least 400 patient image volumes was needed to achieve accurate per-slice hemorrhage detection. Over a five-fold cross-validation, the leading model, which made use of the maximum number of training volumes, had an average true positive rate of 98.10%, an average true negative rate of 99.36%, and an average precision of 0.9698. The models have been made available along with source code1 to enabled continued exploration and adaption of MIL in CT neuroimaging.

Paper Details

Date Published: 10 March 2020
PDF: 10 pages
Proc. SPIE 11313, Medical Imaging 2020: Image Processing, 113130F (10 March 2020); doi: 10.1117/12.2549356
Show Author Affiliations
Samuel Remedios, Henry Jackson Foundation (United States)
National Institute of Health (United States)
Middle Tennessee State Univ. (United States)
Zihao Wu, Vanderbilt Univ. (United States)
Camilo Bermudez, Vanderbilt Univ. (United States)
Cailey I. Kerley, Vanderbilt Univ. (United States)
Snehashis Roy, Henry Jackson Foundation (United States)
Mayur B. Patel, Vanderbilt Brain Institute, Vanderbilt Univ. Medical Ctr. (United States)
John A. Butman, National Institute of Health (United States)
Bennett A. Landman, Vanderbilt Univ. (United States)
Dzung L. Pham, Henry Jackson Foundation (United States)
National Institute of Health (United States)

Published in SPIE Proceedings Vol. 11313:
Medical Imaging 2020: Image Processing
Ivana Išgum; Bennett A. Landman, 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?