Share Email Print

Proceedings Paper

Fully convolutional neural networks improve abdominal organ segmentation
Author(s): Meg F. Bobo; Shunxing Bao; Yuankai Huo; Yuang Yao; Jack Virostko; Andrew J. Plassard; Ilwoo Lyu; Albert Assad; Richard G. Abramson; Melissa A. Hilmes; Bennett A. Landman
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Abdominal image segmentation is a challenging, yet important clinical problem. Variations in body size, position, and relative organ positions greatly complicate the segmentation process. Historically, multi-atlas methods have achieved leading results across imaging modalities and anatomical targets. However, deep learning is rapidly overtaking classical approaches for image segmentation. Recently, Zhou et al. showed that fully convolutional networks produce excellent results in abdominal organ segmentation of computed tomography (CT) scans. Yet, deep learning approaches have not been applied to whole abdomen magnetic resonance imaging (MRI) segmentation. Herein, we evaluate the applicability of an existing fully convolutional neural network (FCNN) designed for CT imaging to segment abdominal organs on T2 weighted (T2w) MRI’s with two examples. In the primary example, we compare a classical multi-atlas approach with FCNN on forty-five T2w MRI’s acquired from splenomegaly patients with five organs labeled (liver, spleen, left kidney, right kidney, and stomach). Thirty-six images were used for training while nine were used for testing. The FCNN resulted in a Dice similarity coefficient (DSC) of 0.930 in spleens, 0.730 in left kidneys, 0.780 in right kidneys, 0.913 in livers, and 0.556 in stomachs. The performance measures for livers, spleens, right kidneys, and stomachs were significantly better than multi-atlas (p < 0.05, Wilcoxon rank-sum test). In a secondary example, we compare the multi-atlas approach with FCNN on 138 distinct T2w MRI’s with manually labeled pancreases (one label). On the pancreas dataset, the FCNN resulted in a median DSC of 0.691 in pancreases versus 0.287 for multi-atlas. The results are highly promising given relatively limited training data and without specific training of the FCNN model and illustrate the potential of deep learning approaches to transcend imaging modalities. 1

Paper Details

Date Published: 2 March 2018
PDF: 8 pages
Proc. SPIE 10574, Medical Imaging 2018: Image Processing, 105742V (2 March 2018); doi: 10.1117/12.2293751
Show Author Affiliations
Meg F. Bobo, Vanderbilt Univ. (United States)
Shunxing Bao, Vanderbilt Univ. (United States)
Yuankai Huo, Vanderbilt Univ. (United States)
Yuang Yao, Vanderbilt Univ. (United States)
Jack Virostko, The Univ. of Texas at Austin (United States)
Andrew J. Plassard, Vanderbilt Univ. (United States)
Ilwoo Lyu, Vanderbilt Univ. (United States)
Albert Assad, Incyte Corp. (United States)
Richard G. Abramson, Vanderbilt Univ. (United States)
Melissa A. Hilmes, Vanderbilt Univ. (United States)
Bennett A. Landman, Vanderbilt Univ. (United States)

Published in SPIE Proceedings Vol. 10574:
Medical Imaging 2018: Image Processing
Elsa D. Angelini; Bennett A. Landman, Editor(s)

© SPIE. Terms of Use
Back to Top