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

Title: Automatic Segmentation of Pelvic Structures From Magnetic Resonance Images for Prostate Cancer Radiotherapy

Abstract

Purpose: Target-volume and organ-at-risk delineation is a time-consuming task in radiotherapy planning. The development of automated segmentation tools remains problematic, because of pelvic organ shape variability. We evaluate a three-dimensional (3D), deformable-model approach and a seeded region-growing algorithm for automatic delineation of the prostate and organs-at-risk on magnetic resonance images. Methods and Materials: Manual and automatic delineation were compared in 24 patients using a sagittal T2-weighted (T2-w) turbo spin echo (TSE) sequence and an axial T1-weighted (T1-w) 3D fast-field echo (FFE) or TSE sequence. For automatic prostate delineation, an organ model-based method was used. Prostates without seminal vesicles were delineated as the clinical target volume (CTV). For automatic bladder and rectum delineation, a seeded region-growing method was used. Manual contouring was considered the reference method. The following parameters were measured: volume ratio (Vr) (automatic/manual), volume overlap (Vo) (ratio of the volume of intersection to the volume of union; optimal value = 1), and correctly delineated volume (Vc) (percent ratio of the volume of intersection to the manually defined volume; optimal value 100). Results: For the CTV, the Vr, Vo, and Vc were 1.13 ({+-}0.1 SD), 0.78 ({+-}0.05 SD), and 94.75 ({+-}3.3 SD), respectively. For the rectum, the Vr, Vo, andmore » Vc were 0.97 ({+-}0.1 SD), 0.78 ({+-}0.06 SD), and 86.52 ({+-}5 SD), respectively. For the bladder, the Vr, Vo, and Vc were 0.95 ({+-}0.03 SD), 0.88 ({+-}0.03 SD), and 91.29 ({+-}3.1 SD), respectively. Conclusions: Our results show that the organ-model method is robust, and results in reproducible prostate segmentation with minor interactive corrections. For automatic bladder and rectum delineation, magnetic resonance imaging soft-tissue contrast enables the use of region-growing methods.« less

Authors:
 [1];  [2];  [3];  [3];  [2];  [3]
  1. Departement Universitaire de Radiotherapie, Centre Oscar Lambret, Universite Lille II, Lille (France) and Laboratoire de Biophysique EA 1049, Institut National de la Sante Et de la Recherche Medicale U703 Thiais, Universite Lille II, Lille (France) and Institut de Technologie Medicale, Centre Hospitalier Universitaire de Lille, Lille (France). E-mail: d-pasquier@o-lambret.fr
  2. Departement Universitaire de Radiotherapie, Centre Oscar Lambret, Universite Lille II, Lille (France)
  3. Laboratoire de Biophysique EA 1049, Institut National de la Sante Et de la Recherche Medicale U703 Thiais, Universite Lille II, Lille (France) and Institut de Technologie Medicale, Centre Hospitalier Universitaire de Lille, Lille (France)
Publication Date:
OSTI Identifier:
20951682
Resource Type:
Journal Article
Resource Relation:
Journal Name: International Journal of Radiation Oncology, Biology and Physics; Journal Volume: 68; Journal Issue: 2; Other Information: DOI: 10.1016/j.ijrobp.2007.02.005; PII: S0360-3016(07)00252-0; Copyright (c) 2007 Elsevier Science B.V., Amsterdam, Netherlands, All rights reserved; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
62 RADIOLOGY AND NUCLEAR MEDICINE; ALGORITHMS; BLADDER; CARCINOMAS; CORRECTIONS; IMAGES; MAGNETIC RESONANCE; NMR IMAGING; PROSTATE; RADIOTHERAPY; RECTUM; SPIN ECHO

Citation Formats

Pasquier, David, Lacornerie, Thomas, Vermandel, Maximilien, Rousseau, Jean, Lartigau, Eric, and Betrouni, Nacim. Automatic Segmentation of Pelvic Structures From Magnetic Resonance Images for Prostate Cancer Radiotherapy. United States: N. p., 2007. Web. doi:10.1016/j.ijrobp.2007.02.005.
Pasquier, David, Lacornerie, Thomas, Vermandel, Maximilien, Rousseau, Jean, Lartigau, Eric, & Betrouni, Nacim. Automatic Segmentation of Pelvic Structures From Magnetic Resonance Images for Prostate Cancer Radiotherapy. United States. doi:10.1016/j.ijrobp.2007.02.005.
Pasquier, David, Lacornerie, Thomas, Vermandel, Maximilien, Rousseau, Jean, Lartigau, Eric, and Betrouni, Nacim. Fri . "Automatic Segmentation of Pelvic Structures From Magnetic Resonance Images for Prostate Cancer Radiotherapy". United States. doi:10.1016/j.ijrobp.2007.02.005.
@article{osti_20951682,
title = {Automatic Segmentation of Pelvic Structures From Magnetic Resonance Images for Prostate Cancer Radiotherapy},
author = {Pasquier, David and Lacornerie, Thomas and Vermandel, Maximilien and Rousseau, Jean and Lartigau, Eric and Betrouni, Nacim},
abstractNote = {Purpose: Target-volume and organ-at-risk delineation is a time-consuming task in radiotherapy planning. The development of automated segmentation tools remains problematic, because of pelvic organ shape variability. We evaluate a three-dimensional (3D), deformable-model approach and a seeded region-growing algorithm for automatic delineation of the prostate and organs-at-risk on magnetic resonance images. Methods and Materials: Manual and automatic delineation were compared in 24 patients using a sagittal T2-weighted (T2-w) turbo spin echo (TSE) sequence and an axial T1-weighted (T1-w) 3D fast-field echo (FFE) or TSE sequence. For automatic prostate delineation, an organ model-based method was used. Prostates without seminal vesicles were delineated as the clinical target volume (CTV). For automatic bladder and rectum delineation, a seeded region-growing method was used. Manual contouring was considered the reference method. The following parameters were measured: volume ratio (Vr) (automatic/manual), volume overlap (Vo) (ratio of the volume of intersection to the volume of union; optimal value = 1), and correctly delineated volume (Vc) (percent ratio of the volume of intersection to the manually defined volume; optimal value 100). Results: For the CTV, the Vr, Vo, and Vc were 1.13 ({+-}0.1 SD), 0.78 ({+-}0.05 SD), and 94.75 ({+-}3.3 SD), respectively. For the rectum, the Vr, Vo, and Vc were 0.97 ({+-}0.1 SD), 0.78 ({+-}0.06 SD), and 86.52 ({+-}5 SD), respectively. For the bladder, the Vr, Vo, and Vc were 0.95 ({+-}0.03 SD), 0.88 ({+-}0.03 SD), and 91.29 ({+-}3.1 SD), respectively. Conclusions: Our results show that the organ-model method is robust, and results in reproducible prostate segmentation with minor interactive corrections. For automatic bladder and rectum delineation, magnetic resonance imaging soft-tissue contrast enables the use of region-growing methods.},
doi = {10.1016/j.ijrobp.2007.02.005},
journal = {International Journal of Radiation Oncology, Biology and Physics},
number = 2,
volume = 68,
place = {United States},
year = {Fri Jun 01 00:00:00 EDT 2007},
month = {Fri Jun 01 00:00:00 EDT 2007}
}
  • Purpose: To describe and evaluate a method for generating synthetic computed tomography (synCT) images from magnetic resonance simulation (MR-SIM) data for accurate digitally reconstructed radiograph (DRR) generation and dose calculations in prostate cancer radiation therapy. Methods and Materials: A retrospective evaluation was performed in 9 prostate cancer patients who had undergone MR-SIM in addition to CT simulation (CT-SIM). MR-SIM data were used to generate synCT images by using a novel, voxel-based weighted summation approach. A subset of patients was used for weight optimization, and the number of patients to use during optimization was determined. Hounsfield unit (HU) differences between CT-SIM andmore » synCT images were analyzed via mean absolute error (MAE). Original, CT-based treatment plans were mapped onto synCTs. DRRs were generated, and agreement between CT and synCT-generated DRRs was evaluated via Dice similarity coefficient (DSC). Dose was recalculated, and dose-volume metrics and gamma analysis were used to evaluate resulting treatment plans. Results: Full field-of-view synCT MAE across all patients was 74.3 ± 10.9 HU with differences from CTs of 2.0 ± 8.1 HU and 11.9 ± 46.7 HU for soft tissue structures (prostate, bladder, and rectum) and femoral bones, respectively. Calculated DSCs for anterior-posterior and lateral DRRs were 0.90 ± 0.04 and 0.92 ± 0.05, respectively. Differences in D99%, mean dose, and maximum dose to the clinical target volume from CT-SIM dose calculations were 0.75% ± 0.35%, 0.63% ± 0.34%, and 0.54% ± 0.33%, respectively, for synCT-generated plans. Gamma analysis (2%/2 mm dose difference/distance to agreement) revealed pass rates of 99.9% ± 0.1% (range, 99.7%-100%). Conclusion: Generated synCTs enabled accurate DRR generation and dose computation for prostate MR-only simulation. Dose recalculated on synCTs agreed well with original planning distributions. Further validation using a larger patient cohort is warranted.« less
  • Purpose: An automatic method for 3D prostate segmentation in magnetic resonance (MR) images is presented for planning image-guided radiotherapy treatment of prostate cancer. Methods: A spatial prior based on intersubject atlas registration is combined with organ-specific intensity information in a graph cut segmentation framework. The segmentation is tested on 67 axial T{sub 2}-weighted MR images in a leave-one-out cross validation experiment and compared with both manual reference segmentations and with multiatlas-based segmentations using majority voting atlas fusion. The impact of atlas selection is investigated in both the traditional atlas-based segmentation and the new graph cut method that combines atlas andmore » intensity information in order to improve the segmentation accuracy. Best results were achieved using the method that combines intensity information, shape information, and atlas selection in the graph cut framework. Results: A mean Dice similarity coefficient (DSC) of 0.88 and a mean surface distance (MSD) of 1.45 mm with respect to the manual delineation were achieved. Conclusions: This approaches the interobserver DSC of 0.90 and interobserver MSD 0f 1.15 mm and is comparable to other studies performing prostate segmentation in MR.« less
  • Purpose: To evaluate the metabolic response by comparing the time to resolution of spectroscopic abnormalities (TRSA) and the time to prostate-specific antigen level in low-risk prostate cancer patients after treatment with three-dimensional conformal external beam radiotherapy (3D-CRT) compared with permanent prostate implantation (PPI). Recent studies have suggested that the treatment of low-risk prostate cancer yields similar results for patients treated with 3D-CRT or PPI. Methods and Materials: A total of 50 patients, 25 in each group, who had been treated with 3D-CRT or PPI, had undergone endorectal magnetic resonance spectroscopy imaging before and/or at varying times after therapy. The 3D-CRTmore » patients had received radiation doses of {>=}72 Gy compared with 144 Gy for the PPI patients. The spectra from all usable voxels were examined for detectable levels of metabolic signal, and the percentages of atrophic and cancerous voxels were tabulated. Results: The median time to resolution of the spectroscopic abnormalities was 32.2 and 24.8 months and the time to the nadir prostate-specific antigen level was 52.4 and 38.0 months for the 3D-CRT and PPI patients, respectively. Of the 3D-CRT patients, 92% achieved negative endorectal magnetic resonance spectroscopy imaging findings, with 40% having complete metabolic atrophy. All 25 PPI patients had negative endorectal magnetic resonance spectroscopy imaging findings, with 60% achieving complete metabolic atrophy. Conclusion: The results of this study suggest that metabolic and biochemical responses of the prostate are more pronounced after PPI. Our results have not proved PPI is more effective at curing prostate cancer, but they have demonstrated that it may be more effective at destroying prostate metabolism.« less
  • Purpose: To determine the influence of magnetic-resonance-imaging (MRI)-vs. computed-tomography (CT)-based prostate and normal structure delineation on the dose to the target and organs at risk during proton therapy. Methods and Materials: Fourteen patients were simulated in the supine position using both CT and T2 MRI. The prostate, rectum, and bladder were delineated on both imaging modalities. The planning target volume (PTV) was generated from the delineated prostates with a 5-mm axial and 8-mm superior and inferior margin. Two plans were generated and analyzed for each patient: an MRI plan based on the MRI-delineated PTV, and a CT plan based onmore » the CT-delineated PTV. Doses of 78 Gy equivalents (GE) were prescribed to the PTV. Results: Doses to normal structures were lower when MRI was used to delineate the rectum and bladder compared with CT: bladder V50 was 15.3% lower (p = 0.04), and rectum V50 was 23.9% lower (p = 0.003). Poor agreement on the definition of the prostate apex was seen between CT and MRI (p = 0.007). The CT-defined prostate apex was within 2 mm of the apex on MRI only 35.7% of the time. Coverage of the MRI-delineated PTV was significantly decreased with the CT-based plan: the minimum dose to the PTV was reduced by 43% (p < 0.001), and the PTV V99% was reduced by 11% (p < 0.001). Conclusions: Using MRI to delineate the prostate results in more accurate target definition and a smaller target volume compared with CT, allowing for improved target coverage and decreased doses to critical normal structures.« less
  • Automated atlas-based segmentation has recently been evaluated for use in planning prostate cancer radiotherapy. In the typical approach, the essential step is the selection of an atlas from a database that best matches the target image. This work proposes an atlas selection strategy and evaluates its impact on the final segmentation accuracy. Prostate length (PL), right femoral head diameter (RFHD), and left femoral head diameter (LFHD) were measured in CT images of 20 patients. Each subject was then taken as the target image to which all remaining 19 images were affinely registered. For each pair of registered images, the overlapmore » between prostate and femoral head contours was quantified using the Dice Similarity Coefficient (DSC). Finally, we designed an atlas selection strategy that computed the ratio of PL (prostate segmentation), RFHD (right femur segmentation), and LFHD (left femur segmentation) between the target subject and each subject in the atlas database. Five atlas subjects yielding ratios nearest to one were then selected for further analysis. RFHD and LFHD were excellent parameters for atlas selection, achieving a mean femoral head DSC of 0.82 ± 0.06. PL had a moderate ability to select the most similar prostate, with a mean DSC of 0.63 ± 0.18. The DSC obtained with the proposed selection method were slightly lower than the maximums established using brute force, but this does not include potential improvements expected with deformable registration. Atlas selection based on PL for prostate and femoral diameter for femoral heads provides reasonable segmentation accuracy.« less