Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients
Background and purpose: Quantifying radiation dose to cardiac substructures is important for research on the etiology and prevention of complications following radiotherapy; however, segmentation of substructures is challenging. In this study we demonstrate the application of our atlas-based automat...
Main Authors: | , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2021-07-01
|
Series: | Physics and Imaging in Radiation Oncology |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405631621000506 |
id |
doaj-147ccc395194418b9200d1177a23db5c |
---|---|
record_format |
Article |
spelling |
doaj-147ccc395194418b9200d1177a23db5c2021-09-07T04:13:48ZengElsevierPhysics and Imaging in Radiation Oncology2405-63162021-07-0119138144Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patientsJae Won Jung0Matthew M. Mille1Bonnie Ky2Walter Kenworthy3Choonik Lee4Yeon Soo Yeom5Aaron Kwag6Walter Bosch7Shannon MacDonald8Oren Cahlon9Justin E. Bekelman10Choonsik Lee11Department of Physics, East Carolina University, Greenville, NC 27858, United StatesDivision of Cancer Epidemiology and Genetics, National Cancer Institute, National Institutes of Health, Rockville, MD 20850, United StatesDepartment of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA 19104, United StatesDepartment of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA 19104, United StatesDepartment of Radiation Oncology, University of Michigan, Ann Arbor, MI 48109, United StatesDivision of Cancer Epidemiology and Genetics, National Cancer Institute, National Institutes of Health, Rockville, MD 20850, United StatesDepartment of Neuroscience, Vanderbilt University, Nashville, TN 37240, United StatesDepartment of Radiation Oncology, Washington University, St. Louis, MO 63130, United StatesDepartment of Radiation Oncology, Massachusetts General Hospital, Boston, MA 02114, United StatesDepartment of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, United StatesDepartment of Radiation Oncology, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA 19104, United StatesDivision of Cancer Epidemiology and Genetics, National Cancer Institute, National Institutes of Health, Rockville, MD 20850, United States; Corresponding author at: Division of Cancer Epidemiology and Genetics, National Cancer Institute, National Institutes of Health, 9609 Medical Center Drive, Rockville, MD 20850, United States.Background and purpose: Quantifying radiation dose to cardiac substructures is important for research on the etiology and prevention of complications following radiotherapy; however, segmentation of substructures is challenging. In this study we demonstrate the application of our atlas-based automatic segmentation method to breast cancer radiotherapy plans for generating radiation doses in support of late effects research. Material and methods: We applied our segmentation method to contour heart substructures on the computed tomography (CT) images of 70 breast cancer patients who received external photon radiotherapy. Two cardiologists provided manual segmentation of the whole heart (WH), left/right atria, left/right ventricles, and left anterior descending artery (LAD). The automatically contours were compared with manual delineations to evaluate similarity in terms of geometry and dose. Results: The mean Dice similarity coefficient between manual and automatic segmentations was 0.96 for the WH, 0.65 to 0.82 for the atria and ventricles, and 0.06 for the LAD. The mean average surface distance was 1.2 mm for the WH, 3.4 to 4.1 mm for the atria and ventricles, and 6.4 mm for the LAD. We found the dose to the cardiac substructures based on our automatic segmentation agrees with manual segmentation within expected observer variability. For left breast patients, the mean absolute difference in mean dose was 0.1 Gy for the WH, 0.2 to 0.7 Gy for the atria and ventricles, and 1.8 Gy for the LAD. For right breast patients, these values were 0.0 Gy, 0.1 to 0.4 Gy, and 0.4 Gy, respectively. Conclusion: Our automatic segmentation method will facilitate the development of radiotherapy prescriptive criteria for mitigating cardiovascular complications.http://www.sciencedirect.com/science/article/pii/S2405631621000506Cardiac structuresAutomatic segmentationBreast cancerRadiotherapyLate effects |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jae Won Jung Matthew M. Mille Bonnie Ky Walter Kenworthy Choonik Lee Yeon Soo Yeom Aaron Kwag Walter Bosch Shannon MacDonald Oren Cahlon Justin E. Bekelman Choonsik Lee |
spellingShingle |
Jae Won Jung Matthew M. Mille Bonnie Ky Walter Kenworthy Choonik Lee Yeon Soo Yeom Aaron Kwag Walter Bosch Shannon MacDonald Oren Cahlon Justin E. Bekelman Choonsik Lee Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients Physics and Imaging in Radiation Oncology Cardiac structures Automatic segmentation Breast cancer Radiotherapy Late effects |
author_facet |
Jae Won Jung Matthew M. Mille Bonnie Ky Walter Kenworthy Choonik Lee Yeon Soo Yeom Aaron Kwag Walter Bosch Shannon MacDonald Oren Cahlon Justin E. Bekelman Choonsik Lee |
author_sort |
Jae Won Jung |
title |
Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients |
title_short |
Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients |
title_full |
Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients |
title_fullStr |
Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients |
title_full_unstemmed |
Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients |
title_sort |
application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients |
publisher |
Elsevier |
series |
Physics and Imaging in Radiation Oncology |
issn |
2405-6316 |
publishDate |
2021-07-01 |
description |
Background and purpose: Quantifying radiation dose to cardiac substructures is important for research on the etiology and prevention of complications following radiotherapy; however, segmentation of substructures is challenging. In this study we demonstrate the application of our atlas-based automatic segmentation method to breast cancer radiotherapy plans for generating radiation doses in support of late effects research. Material and methods: We applied our segmentation method to contour heart substructures on the computed tomography (CT) images of 70 breast cancer patients who received external photon radiotherapy. Two cardiologists provided manual segmentation of the whole heart (WH), left/right atria, left/right ventricles, and left anterior descending artery (LAD). The automatically contours were compared with manual delineations to evaluate similarity in terms of geometry and dose. Results: The mean Dice similarity coefficient between manual and automatic segmentations was 0.96 for the WH, 0.65 to 0.82 for the atria and ventricles, and 0.06 for the LAD. The mean average surface distance was 1.2 mm for the WH, 3.4 to 4.1 mm for the atria and ventricles, and 6.4 mm for the LAD. We found the dose to the cardiac substructures based on our automatic segmentation agrees with manual segmentation within expected observer variability. For left breast patients, the mean absolute difference in mean dose was 0.1 Gy for the WH, 0.2 to 0.7 Gy for the atria and ventricles, and 1.8 Gy for the LAD. For right breast patients, these values were 0.0 Gy, 0.1 to 0.4 Gy, and 0.4 Gy, respectively. Conclusion: Our automatic segmentation method will facilitate the development of radiotherapy prescriptive criteria for mitigating cardiovascular complications. |
topic |
Cardiac structures Automatic segmentation Breast cancer Radiotherapy Late effects |
url |
http://www.sciencedirect.com/science/article/pii/S2405631621000506 |
work_keys_str_mv |
AT jaewonjung applicationofanautomaticsegmentationmethodforevaluatingcardiacstructuredosesreceivedbybreastradiotherapypatients AT matthewmmille applicationofanautomaticsegmentationmethodforevaluatingcardiacstructuredosesreceivedbybreastradiotherapypatients AT bonnieky applicationofanautomaticsegmentationmethodforevaluatingcardiacstructuredosesreceivedbybreastradiotherapypatients AT walterkenworthy applicationofanautomaticsegmentationmethodforevaluatingcardiacstructuredosesreceivedbybreastradiotherapypatients AT chooniklee applicationofanautomaticsegmentationmethodforevaluatingcardiacstructuredosesreceivedbybreastradiotherapypatients AT yeonsooyeom applicationofanautomaticsegmentationmethodforevaluatingcardiacstructuredosesreceivedbybreastradiotherapypatients AT aaronkwag applicationofanautomaticsegmentationmethodforevaluatingcardiacstructuredosesreceivedbybreastradiotherapypatients AT walterbosch applicationofanautomaticsegmentationmethodforevaluatingcardiacstructuredosesreceivedbybreastradiotherapypatients AT shannonmacdonald applicationofanautomaticsegmentationmethodforevaluatingcardiacstructuredosesreceivedbybreastradiotherapypatients AT orencahlon applicationofanautomaticsegmentationmethodforevaluatingcardiacstructuredosesreceivedbybreastradiotherapypatients AT justinebekelman applicationofanautomaticsegmentationmethodforevaluatingcardiacstructuredosesreceivedbybreastradiotherapypatients AT choonsiklee applicationofanautomaticsegmentationmethodforevaluatingcardiacstructuredosesreceivedbybreastradiotherapypatients |
_version_ |
1717764868848746496 |