Combining population and patient-specific characteristics for prostate segmentation on 3D CT images

• Type of Material: Conference Paper
• Authors: Ling Ma, Emory University; RongRong Guo, Emory University; Zhiqiang Tian, Emory University; Rajesh Venkataraman, Eigen; Saradwata Sarkar, Eigen; Xiabi Liu, Beijing Institute of Technology; Funmilayo Tade, Emory University; David Schuster, Emory University; Baowei Fei, Emory University
• Language: English
• Date: 2016-01-01
• Publisher: Emory University Libraries
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2016 Society of Photo Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
• Final Published Version (URL): http://dx.doi.org/10.1117/12.2216255
• Title of Journal or Parent Work: Proceedings of SPIE
• Conference or Event Name: Medical Imaging 2016: Image Processing
• Volume: 9784
• Grant/Funding Information: XL was partially supported by National Natural Science Foundation of China (Grant no. 60973059, 81171407) and the Program for New Century Excellent Talents in Universities of China (Grant No. NCET-10-0044).; This research is supported in part by NIH grants (CA176684 and CA156775).; LM was partially supported by International Graduate Exchange Program of Beijing Institute of Technology.
• Keywords: prostate; population characteristics; patient-specific characteristics; image segmentation; CT
• Research Categories: Engineering, Biomedical; Health Sciences, Radiology

Abstract

Prostate segmentation on CT images is a challenging task. In this paper, we explore the population and patient-specific characteristics for the segmentation of the prostate on CT images. Because population learning does not consider the inter-patient variations and because patient-specific learning may not perform well for different patients, we are combining the population and patient-specific information to improve segmentation performance. Specifically, we train a population model based on the population data and train a patient-specific model based on the manual segmentation on three slice of the new patient. We compute the similarity between the two models to explore the influence of applicable population knowledge on the specific patient. By combining the patient-specific knowledge with the influence, we can capture the population and patient-specific characteristics to calculate the probability of a pixel belonging to the prostate. Finally, we smooth the prostate surface according to the prostate-density value of the pixels in the distance transform image. We conducted the leave-one-out validation experiments on a set of CT volumes from 15 patients. Manual segmentation results from a radiologist serve as the gold standard for the evaluation. Experimental results show that our method achieved an average DSC of 85.1% as compared to the manual segmentation gold standard. This method outperformed the population learning method and the patient-specific learning approach alone. The CT segmentation method can have various applications in prostate cancer diagnosis and therapy.