Fully automated organ segmentation in male pelvic CT images

Content Provider	Scilit
Author	Balagopal, Anjali Kazemifar, Samaneh Nguyen, Dan Lin, Mu-Han Hannan, Raquibul Owrangi, Amir M. Jiang, Steve B.
Copyright Year	2018
Description	Journal: Physics in Medicine & Biology Accurate segmentation of prostate and surrounding organs at risk is important for prostate cancer radiotherapy treatment planning. We present a fully automated workflow for male pelvic CT image segmentation using deep learning. The architecture consists of a 2D localization network followed by a 3D segmentation network for volumetric segmentation of prostate, bladder, rectum, and femoral heads. We used a multi-channel 2D U-Net followed by a 3D U-Net with encoding arm modified with aggregated residual networks, known as ResNeXt. The models were trained and tested on a pelvic CT image dataset comprising 136 patients. Test results show that 3D U-Net based segmentation achieves mean (±SD) Dice coefficient values of 90 (±2.0)% ,96 (±3.0)%, 95 (±1.3)%, 95 (±1.5)%, and 84 (±3.7)% for prostate, left femoral head, right femoral head, bladder, and rectum, respectively, using the proposed fully automated segmentation method.
Related Links	http://arxiv.org/pdf/1805.12526 http://iopscience.iop.org/article/10.1088/1361-6560/aaf11c/pdf
ISSN	00319155
e-ISSN	13616560
DOI	10.1088/1361-6560/aaf11c
Journal	Physics in Medicine & Biology
Issue Number	24
Volume Number	63
Language	English
Publisher	IOP Publishing
Publisher Date	2018-11-15
Access Restriction	Open
Subject Keyword	Journal: Physics in Medicine & Biology Radiology, Nuclear Medicine and Imaging Ct Images Deep Learning Fully Automated Organ Segmentation Organs At Risk
Content Type	Text
Resource Type	Article
Subject	Radiology, Nuclear Medicine and Imaging Radiological and Ultrasound Technology