2 March 2018 Splenomegaly segmentation using global convolutional kernels and conditional generative adversarial networks
Author Affiliations +
Abstract
Spleen volume estimation using automated image segmentation technique may be used to detect splenomegaly (abnormally enlarged spleen) on Magnetic Resonance Imaging (MRI) scans. In recent years, Deep Convolutional Neural Networks (DCNN) segmentation methods have demonstrated advantages for abdominal organ segmentation. However, variations in both size and shape of the spleen on MRI images may result in large false positive and false negative labeling when deploying DCNN based methods. In this paper, we propose the Splenomegaly Segmentation Network (SSNet) to address spatial variations when segmenting extraordinarily large spleens. SSNet was designed based on the framework of image-to-image conditional generative adversarial networks (cGAN). Specifically, the Global Convolutional Network (GCN) was used as the generator to reduce false negatives, while the Markovian discriminator (PatchGAN) was used to alleviate false positives. A cohort of clinically acquired 3D MRI scans (both T1 weighted and T2 weighted) from patients with splenomegaly were used to train and test the networks. The experimental results demonstrated that a mean Dice coefficient of 0.9260 and a median Dice coefficient of 0.9262 using SSNet on independently tested MRI volumes of patients with splenomegaly.
Conference Presentation
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yuankai Huo, Yuankai Huo, Zhoubing Xu, Zhoubing Xu, Shunxing Bao, Shunxing Bao, Camilo Bermudez, Camilo Bermudez, Andrew J. Plassard, Andrew J. Plassard, Jiaqi Liu, Jiaqi Liu, Yuang Yao, Yuang Yao, Albert Assad, Albert Assad, Richard G. Abramson, Richard G. Abramson, Bennett A. Landman, Bennett A. Landman, } "Splenomegaly segmentation using global convolutional kernels and conditional generative adversarial networks", Proc. SPIE 10574, Medical Imaging 2018: Image Processing, 1057409 (2 March 2018); doi: 10.1117/12.2293406; https://doi.org/10.1117/12.2293406
PROCEEDINGS
7 PAGES + PRESENTATION

SHARE
Back to Top