skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: SU-F-J-171: Robust Atlas Based Segmentation of the Prostate and Peripheral Zone Regions On MRI Utilizing Multiple MRI System Vendors

Abstract

Purpose: Automatically generated prostate MRI contours can be used to aid in image registration with CT or ultrasound and to reduce the burden of contouring for radiation treatment planning. In addition, prostate and zonal contours can assist to automate quantitative imaging features extraction and the analyses of longitudinal MRI studies. These potential gains are limited if the solutions are not compatible across different MRI vendors. The goal of this study is to characterize an atlas based automatic segmentation procedure of the prostate collected on MRI systems from multiple vendors. Methods: The prostate and peripheral zone (PZ) were manually contoured by an expert radiation oncologist on T2-weighted scans acquired on both GE (n=31) and Siemens (n=33) 3T MRI systems. A leave-one-out approach was utilized where the target subject is removed from the atlas before the segmentation algorithm is initiated. The atlas-segmentation method finds the best nine matched atlas subjects and then performs a normalized intensity-based free-form deformable registration of these subjects to the target subject. These nine contours are then merged into a single contour using Simultaneous Truth and Performance Level Estimation (STAPLE). Contour comparisons were made using Dice similarity coefficients (DSC) and Hausdorff distances. Results: Using the T2 FatSat (FS)more » GE datasets the atlas generated contours resulted in an average DSC of 0.83±0.06 for prostate, 0.57±0.12 for PZ and 0.75±0.09 for CG. Similar results were found when using the Siemens data with a DSC of 0.79±0.14 for prostate, 0.54±0.16 and 0.70±0.9. Contrast between prostate and surrounding anatomy and between the PZ and CG contours for both vendors demonstrated superior contrast separation; significance was found for all comparisons p-value < 0.0001. Conclusion: Atlas-based segmentation yielded promising results for all contours compared to expertly defined contours in both Siemens and GE 3T systems providing fast and automatic segmentation of the prostate. Funding Support, Disclosures, and Conflict of Interest: AS Nelson is a partial owner of MIM Software, Inc. AS Nelson, and A Swallen are current employees at MIM Software, Inc.« less

Authors:
; ;  [1]; ;  [2]
  1. University of Miami, Miami, Florida (United States)
  2. MIM Software Inc., Cleveland, OH (United States)
Publication Date:
OSTI Identifier:
22634768
Resource Type:
Journal Article
Resource Relation:
Journal Name: Medical Physics; Journal Volume: 43; Journal Issue: 6; Other Information: (c) 2016 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; 61 RADIATION PROTECTION AND DOSIMETRY; ALGORITHMS; ANATOMY; BIOMEDICAL RADIOGRAPHY; CALORIMETRY; COMPUTER CODES; COMPUTERIZED TOMOGRAPHY; DATASETS; MEDICAL PERSONNEL; NMR IMAGING; PROSTATE

Citation Formats

Padgett, K, Pollack, A, Stoyanova, R, Swallen, A, and Nelson, A. SU-F-J-171: Robust Atlas Based Segmentation of the Prostate and Peripheral Zone Regions On MRI Utilizing Multiple MRI System Vendors. United States: N. p., 2016. Web. doi:10.1118/1.4956079.
Padgett, K, Pollack, A, Stoyanova, R, Swallen, A, & Nelson, A. SU-F-J-171: Robust Atlas Based Segmentation of the Prostate and Peripheral Zone Regions On MRI Utilizing Multiple MRI System Vendors. United States. doi:10.1118/1.4956079.
Padgett, K, Pollack, A, Stoyanova, R, Swallen, A, and Nelson, A. Wed . "SU-F-J-171: Robust Atlas Based Segmentation of the Prostate and Peripheral Zone Regions On MRI Utilizing Multiple MRI System Vendors". United States. doi:10.1118/1.4956079.
@article{osti_22634768,
title = {SU-F-J-171: Robust Atlas Based Segmentation of the Prostate and Peripheral Zone Regions On MRI Utilizing Multiple MRI System Vendors},
author = {Padgett, K and Pollack, A and Stoyanova, R and Swallen, A and Nelson, A},
abstractNote = {Purpose: Automatically generated prostate MRI contours can be used to aid in image registration with CT or ultrasound and to reduce the burden of contouring for radiation treatment planning. In addition, prostate and zonal contours can assist to automate quantitative imaging features extraction and the analyses of longitudinal MRI studies. These potential gains are limited if the solutions are not compatible across different MRI vendors. The goal of this study is to characterize an atlas based automatic segmentation procedure of the prostate collected on MRI systems from multiple vendors. Methods: The prostate and peripheral zone (PZ) were manually contoured by an expert radiation oncologist on T2-weighted scans acquired on both GE (n=31) and Siemens (n=33) 3T MRI systems. A leave-one-out approach was utilized where the target subject is removed from the atlas before the segmentation algorithm is initiated. The atlas-segmentation method finds the best nine matched atlas subjects and then performs a normalized intensity-based free-form deformable registration of these subjects to the target subject. These nine contours are then merged into a single contour using Simultaneous Truth and Performance Level Estimation (STAPLE). Contour comparisons were made using Dice similarity coefficients (DSC) and Hausdorff distances. Results: Using the T2 FatSat (FS) GE datasets the atlas generated contours resulted in an average DSC of 0.83±0.06 for prostate, 0.57±0.12 for PZ and 0.75±0.09 for CG. Similar results were found when using the Siemens data with a DSC of 0.79±0.14 for prostate, 0.54±0.16 and 0.70±0.9. Contrast between prostate and surrounding anatomy and between the PZ and CG contours for both vendors demonstrated superior contrast separation; significance was found for all comparisons p-value < 0.0001. Conclusion: Atlas-based segmentation yielded promising results for all contours compared to expertly defined contours in both Siemens and GE 3T systems providing fast and automatic segmentation of the prostate. Funding Support, Disclosures, and Conflict of Interest: AS Nelson is a partial owner of MIM Software, Inc. AS Nelson, and A Swallen are current employees at MIM Software, Inc.},
doi = {10.1118/1.4956079},
journal = {Medical Physics},
number = 6,
volume = 43,
place = {United States},
year = {Wed Jun 15 00:00:00 EDT 2016},
month = {Wed Jun 15 00:00:00 EDT 2016}
}