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

Title: SU-F-J-111: A Novel Distance-Dose Weighting Method for Label Fusion in Multi- Atlas Segmentation for Prostate Radiation Therapy

Abstract

Purpose: A novel distance-dose weighting method for label fusion was developed to increase segmentation accuracy in dosimetrically important regions for prostate radiation therapy. Methods: Label fusion as implemented in the original SIMPLE (OS) for multi-atlas segmentation relies iteratively on the majority vote to generate an estimated ground truth and DICE similarity measure to screen candidates. The proposed distance-dose weighting puts more values on dosimetrically important regions when calculating similarity measure. Specifically, we introduced distance-to-dose error (DDE), which converts distance to dosimetric importance, in performance evaluation. The DDE calculates an estimated DE error derived from surface distance differences between the candidate and estimated ground truth label by multiplying a regression coefficient. To determine the coefficient at each simulation point on the rectum, we fitted DE error with respect to simulated voxel shift. The DEs were calculated by the multi-OAR geometry-dosimetry training model previously developed in our research group. Results: For both the OS and the distance-dose weighted SIMPLE (WS) results, the evaluation metrics for twenty patients were calculated using the ground truth segmentation. The mean difference of DICE, Hausdorff distance, and mean absolute distance (MAD) between OS and WS have shown 0, 0.10, and 0.11, respectively. In partial MAD of WSmore » which calculates MAD within a certain PTV expansion voxel distance, the lower MADs were observed at the closer distances from 1 to 8 than those of OS. The DE results showed that the segmentation from WS produced more accurate results than OS. The mean DE error of V75, V70, V65, and V60 were decreased by 1.16%, 1.17%, 1.14%, and 1.12%, respectively. Conclusion: We have demonstrated that the method can increase the segmentation accuracy in rectum regions adjacent to PTV. As a result, segmentation using WS have shown improved dosimetric accuracy than OS. The WS will provide dosimetrically important label selection strategy in multi-atlas segmentation. CPRIT grant RP150485.« less

Authors:
; ; ;  [1];  [2]
  1. UT Southwestern Medical Center, Dallas, TX (United States)
  2. Southern Medical University, Guangzhou, Guangdong (China)
Publication Date:
OSTI Identifier:
22634718
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; ACCURACY; DISTANCE; DOSIMETRY; ERRORS; GROUND TRUTH MEASUREMENTS; ITERATIVE METHODS; PROSTATE; RADIATION DOSES; RADIOTHERAPY; RECTUM; SIMULATION

Citation Formats

Chang, J, Gu, X, Lu, W, Jiang, S, and Song, T. SU-F-J-111: A Novel Distance-Dose Weighting Method for Label Fusion in Multi- Atlas Segmentation for Prostate Radiation Therapy. United States: N. p., 2016. Web. doi:10.1118/1.4956019.
Chang, J, Gu, X, Lu, W, Jiang, S, & Song, T. SU-F-J-111: A Novel Distance-Dose Weighting Method for Label Fusion in Multi- Atlas Segmentation for Prostate Radiation Therapy. United States. doi:10.1118/1.4956019.
Chang, J, Gu, X, Lu, W, Jiang, S, and Song, T. Wed . "SU-F-J-111: A Novel Distance-Dose Weighting Method for Label Fusion in Multi- Atlas Segmentation for Prostate Radiation Therapy". United States. doi:10.1118/1.4956019.
@article{osti_22634718,
title = {SU-F-J-111: A Novel Distance-Dose Weighting Method for Label Fusion in Multi- Atlas Segmentation for Prostate Radiation Therapy},
author = {Chang, J and Gu, X and Lu, W and Jiang, S and Song, T},
abstractNote = {Purpose: A novel distance-dose weighting method for label fusion was developed to increase segmentation accuracy in dosimetrically important regions for prostate radiation therapy. Methods: Label fusion as implemented in the original SIMPLE (OS) for multi-atlas segmentation relies iteratively on the majority vote to generate an estimated ground truth and DICE similarity measure to screen candidates. The proposed distance-dose weighting puts more values on dosimetrically important regions when calculating similarity measure. Specifically, we introduced distance-to-dose error (DDE), which converts distance to dosimetric importance, in performance evaluation. The DDE calculates an estimated DE error derived from surface distance differences between the candidate and estimated ground truth label by multiplying a regression coefficient. To determine the coefficient at each simulation point on the rectum, we fitted DE error with respect to simulated voxel shift. The DEs were calculated by the multi-OAR geometry-dosimetry training model previously developed in our research group. Results: For both the OS and the distance-dose weighted SIMPLE (WS) results, the evaluation metrics for twenty patients were calculated using the ground truth segmentation. The mean difference of DICE, Hausdorff distance, and mean absolute distance (MAD) between OS and WS have shown 0, 0.10, and 0.11, respectively. In partial MAD of WS which calculates MAD within a certain PTV expansion voxel distance, the lower MADs were observed at the closer distances from 1 to 8 than those of OS. The DE results showed that the segmentation from WS produced more accurate results than OS. The mean DE error of V75, V70, V65, and V60 were decreased by 1.16%, 1.17%, 1.14%, and 1.12%, respectively. Conclusion: We have demonstrated that the method can increase the segmentation accuracy in rectum regions adjacent to PTV. As a result, segmentation using WS have shown improved dosimetric accuracy than OS. The WS will provide dosimetrically important label selection strategy in multi-atlas segmentation. CPRIT grant RP150485.},
doi = {10.1118/1.4956019},
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}
}