Automatic Brain Organ Segmentation with 3D Fully Convolutional Neural Network for Radiation Therapy Treatment Planning

• Type of Material: Article
• Authors: Hongyi Duanmu, SUNY Stony Brook; Jinkoo Kim, Stony Brook University Hospital; Praitayini Kanakaraj, Vanderbilt University; Andrew Wang, Ward Melville High School; John Joshua, Ward Melville High School; Jun Kong, Emory University; Fusheng Wang, Emory University
• Language: English
• Date: 2020-01-01
• Publisher: IEEE
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2020, IEEE
• Final Published Version (URL): http://dx.doi.org/10.1109/ISBI45749.2020.9098485
• Title of Journal or Parent Work: 2020 IEEE 17TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2020)
• Volume: 2020-April
• Start Page: 758
• End Page: 762
• Grant/Funding Information: This research is supported in part by grants from National Institute of Health 7K25CA181503-06, 1U01CA242936-01, and National Science Foundation ACI 1443054 and IIS 1350885.
• Keywords: Science & Technology; Brain Segmentation; Fully Connected Convolutional Neural Network; Life Sciences & Biomedicine; Radiology, Nuclear Medicine & Medical Imaging; Deep Learning; Radiation Therapy; Biomedical Image Analysis; Technology; Engineering, Biomedical; Engineering

Abstract

3D organ contouring is an essential step in radiation therapy treatment planning for organ dose estimation as well as for optimizing plans to reduce organs-at-risk doses. Manual contouring is time-consuming and its inter-clinician variability adversely affects the outcomes study. Such organs also vary dramatically on sizes - up to two orders of magnitude difference in volumes. In this paper, we present BrainSegNet, a novel 3D fully convolutional neural network (FCNN) based approach for automatic segmentation of brain organs. Brain-SegN et takes a multiple resolution paths approach and uses a weighted loss function to solve the major challenge of the large variability in organ sizes. We evaluated our approach with a dataset of 46 Brain CT image volumes with corresponding expert organ contours as reference. Compared with those of LiviaNet and V-Net, BrainSegNet has a superior performance in segmenting tiny or thin organs, such as chiasm, optic nerves, and cochlea, and outperforms these methods in segmenting large organs as well. BrainSegNet can reduce the manual contouring time of a volume from an hour to less than two minutes, and holds high potential to improve the efficiency of radiation therapy workflow.