Auto-segmentations by convolutional neural network in cervical and anorectal cancer with clinical structure sets as the ground truth
Background: It is time-consuming for oncologists to delineate volumes for radiotherapy treatment in computer tomography (CT) images. Automatic delineation based on image processing exists, but with varied accuracy and moderate time savings. Using convolutional neural network (CNN), delineations of v...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2020-11-01
|
Series: | Clinical and Translational Radiation Oncology |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405630820300756 |
id |
doaj-025c081f2c874041abc66a1ac8a9b6f0 |
---|---|
record_format |
Article |
spelling |
doaj-025c081f2c874041abc66a1ac8a9b6f02021-06-02T18:45:53ZengElsevierClinical and Translational Radiation Oncology2405-63082020-11-01253745Auto-segmentations by convolutional neural network in cervical and anorectal cancer with clinical structure sets as the ground truthHanna Sartor0David Minarik1Olof Enqvist2Johannes Ulén3Anders Wittrup4Maria Bjurberg5Elin Trägårdh6Diagnostic Radiology, Department of Translational Medicine, Lund University, Skåne University Hospital, Lund, Sweden; Corresponding author at: Entrégatan 22185, Lund, Sweden.Radiation Physics, Department of Translational Medicine, Lund University, Skåne University Hospital, Malmö, SwedenEigenvision AB, Malmö, SwedenEigenvision AB, Malmö, SwedenDepartment of Hematology, Oncology and Radiation Physics, Skåne University Hospital and Department of Clinical Sciences, Lund University, Lund, Sweden; Wallenberg Centre for Molecular Medicine, Lund University, Lund, SwedenDepartment of Hematology, Oncology and Radiation Physics, Skåne University Hospital and Department of Clinical Sciences, Lund University, Lund, SwedenWallenberg Centre for Molecular Medicine, Lund University, Lund, Sweden; Department of Clinical Physiology and Nuclear Medicine, Department of Translational Medicine, Lund University, Skåne University Hospital, Malmö, SwedenBackground: It is time-consuming for oncologists to delineate volumes for radiotherapy treatment in computer tomography (CT) images. Automatic delineation based on image processing exists, but with varied accuracy and moderate time savings. Using convolutional neural network (CNN), delineations of volumes are faster and more accurate. We have used CTs with the annotated structure sets to train and evaluate a CNN. Material and methods: The CNN is a standard segmentation network modified to minimize memory usage. We used CTs and structure sets from 75 cervical cancers and 191 anorectal cancers receiving radiation therapy at Skåne University Hospital 2014-2018. Five structures were investigated: left/right femoral heads, bladder, bowel bag, and clinical target volume of lymph nodes (CTVNs). Dice score and mean surface distance (MSD) (mm) evaluated accuracy, and one oncologist qualitatively evaluated auto-segmentations. Results: Median Dice/MSD scores for anorectal cancer: 0.91–0.92/1.93–1.86 femoral heads, 0.94/2.07 bladder, and 0.83/6.80 bowel bag. Median Dice scores for cervical cancer were 0.93–0.94/1.42–1.49 femoral heads, 0.84/3.51 bladder, 0.88/5.80 bowel bag, and 0.82/3.89 CTVNs. With qualitative evaluation, performance on femoral heads and bladder auto-segmentations was mostly excellent, but CTVN auto-segmentations were not acceptable to a larger extent. Discussion: It is possible to train a CNN with high overlap using structure sets as ground truth. Manually delineated pelvic volumes from structure sets do not always strictly follow volume boundaries and are sometimes inaccurately defined, which leads to similar inaccuracies in the CNN output. More data that is consistently annotated is needed to achieve higher CNN accuracy and to enable future clinical implementation.http://www.sciencedirect.com/science/article/pii/S2405630820300756Cervical cancer radiotherapyOrgans-at-riskClinical Target VolumeAutomatic segmentationConvolutional neural network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hanna Sartor David Minarik Olof Enqvist Johannes Ulén Anders Wittrup Maria Bjurberg Elin Trägårdh |
spellingShingle |
Hanna Sartor David Minarik Olof Enqvist Johannes Ulén Anders Wittrup Maria Bjurberg Elin Trägårdh Auto-segmentations by convolutional neural network in cervical and anorectal cancer with clinical structure sets as the ground truth Clinical and Translational Radiation Oncology Cervical cancer radiotherapy Organs-at-risk Clinical Target Volume Automatic segmentation Convolutional neural network |
author_facet |
Hanna Sartor David Minarik Olof Enqvist Johannes Ulén Anders Wittrup Maria Bjurberg Elin Trägårdh |
author_sort |
Hanna Sartor |
title |
Auto-segmentations by convolutional neural network in cervical and anorectal cancer with clinical structure sets as the ground truth |
title_short |
Auto-segmentations by convolutional neural network in cervical and anorectal cancer with clinical structure sets as the ground truth |
title_full |
Auto-segmentations by convolutional neural network in cervical and anorectal cancer with clinical structure sets as the ground truth |
title_fullStr |
Auto-segmentations by convolutional neural network in cervical and anorectal cancer with clinical structure sets as the ground truth |
title_full_unstemmed |
Auto-segmentations by convolutional neural network in cervical and anorectal cancer with clinical structure sets as the ground truth |
title_sort |
auto-segmentations by convolutional neural network in cervical and anorectal cancer with clinical structure sets as the ground truth |
publisher |
Elsevier |
series |
Clinical and Translational Radiation Oncology |
issn |
2405-6308 |
publishDate |
2020-11-01 |
description |
Background: It is time-consuming for oncologists to delineate volumes for radiotherapy treatment in computer tomography (CT) images. Automatic delineation based on image processing exists, but with varied accuracy and moderate time savings. Using convolutional neural network (CNN), delineations of volumes are faster and more accurate. We have used CTs with the annotated structure sets to train and evaluate a CNN. Material and methods: The CNN is a standard segmentation network modified to minimize memory usage. We used CTs and structure sets from 75 cervical cancers and 191 anorectal cancers receiving radiation therapy at Skåne University Hospital 2014-2018. Five structures were investigated: left/right femoral heads, bladder, bowel bag, and clinical target volume of lymph nodes (CTVNs). Dice score and mean surface distance (MSD) (mm) evaluated accuracy, and one oncologist qualitatively evaluated auto-segmentations. Results: Median Dice/MSD scores for anorectal cancer: 0.91–0.92/1.93–1.86 femoral heads, 0.94/2.07 bladder, and 0.83/6.80 bowel bag. Median Dice scores for cervical cancer were 0.93–0.94/1.42–1.49 femoral heads, 0.84/3.51 bladder, 0.88/5.80 bowel bag, and 0.82/3.89 CTVNs. With qualitative evaluation, performance on femoral heads and bladder auto-segmentations was mostly excellent, but CTVN auto-segmentations were not acceptable to a larger extent. Discussion: It is possible to train a CNN with high overlap using structure sets as ground truth. Manually delineated pelvic volumes from structure sets do not always strictly follow volume boundaries and are sometimes inaccurately defined, which leads to similar inaccuracies in the CNN output. More data that is consistently annotated is needed to achieve higher CNN accuracy and to enable future clinical implementation. |
topic |
Cervical cancer radiotherapy Organs-at-risk Clinical Target Volume Automatic segmentation Convolutional neural network |
url |
http://www.sciencedirect.com/science/article/pii/S2405630820300756 |
work_keys_str_mv |
AT hannasartor autosegmentationsbyconvolutionalneuralnetworkincervicalandanorectalcancerwithclinicalstructuresetsasthegroundtruth AT davidminarik autosegmentationsbyconvolutionalneuralnetworkincervicalandanorectalcancerwithclinicalstructuresetsasthegroundtruth AT olofenqvist autosegmentationsbyconvolutionalneuralnetworkincervicalandanorectalcancerwithclinicalstructuresetsasthegroundtruth AT johannesulen autosegmentationsbyconvolutionalneuralnetworkincervicalandanorectalcancerwithclinicalstructuresetsasthegroundtruth AT anderswittrup autosegmentationsbyconvolutionalneuralnetworkincervicalandanorectalcancerwithclinicalstructuresetsasthegroundtruth AT mariabjurberg autosegmentationsbyconvolutionalneuralnetworkincervicalandanorectalcancerwithclinicalstructuresetsasthegroundtruth AT elintragardh autosegmentationsbyconvolutionalneuralnetworkincervicalandanorectalcancerwithclinicalstructuresetsasthegroundtruth |
_version_ |
1721402017522384896 |