Automatic contouring system for cervical cancer using convolutional neural networks.
auto-contouring
cervical cancer
convolutional neural network
deep learning
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Nov 2020
Nov 2020
Historique:
received:
29
07
2020
revised:
01
09
2020
accepted:
07
09
2020
pubmed:
24
9
2020
medline:
15
5
2021
entrez:
23
9
2020
Statut:
ppublish
Résumé
To develop a tool for the automatic contouring of clinical treatment volumes (CTVs) and normal tissues for radiotherapy treatment planning in cervical cancer patients. An auto-contouring tool based on convolutional neural networks (CNN) was developed to delineate three cervical CTVs and 11 normal structures (seven OARs, four bony structures) in cervical cancer treatment for use with the Radiation Planning Assistant, a web-based automatic plan generation system. A total of 2254 retrospective clinical computed tomography (CT) scans from a single cancer center and 210 CT scans from a segmentation challenge were used to train and validate the CNN-based auto-contouring tool. The accuracy of the tool was evaluated by calculating the Sørensen-dice similarity coefficient (DSC) and mean surface and Hausdorff distances between the automatically generated contours and physician-drawn contours on 140 internal CT scans. A radiation oncologist scored the automatically generated contours on 30 external CT scans from three South African hospitals. The average DSC, mean surface distance, and Hausdorff distance of our CNN-based tool were 0.86/0.19 cm/2.02 cm for the primary CTV, 0.81/0.21 cm/2.09 cm for the nodal CTV, 0.76/0.27 cm/2.00 cm for the PAN CTV, 0.89/0.11 cm/1.07 cm for the bladder, 0.81/0.18 cm/1.66 cm for the rectum, 0.90/0.06 cm/0.65 cm for the spinal cord, 0.94/0.06 cm/0.60 cm for the left femur, 0.93/0.07 cm/0.66 cm for the right femur, 0.94/0.08 cm/0.76 cm for the left kidney, 0.95/0.07 cm/0.84 cm for the right kidney, 0.93/0.05 cm/1.06 cm for the pelvic bone, 0.91/0.07 cm/1.25 cm for the sacrum, 0.91/0.07 cm/0.53 cm for the L4 vertebral body, and 0.90/0.08 cm/0.68 cm for the L5 vertebral bodies. On average, 80% of the CTVs, 97% of the organ at risk, and 98% of the bony structure contours in the external test dataset were clinically acceptable based on physician review. Our CNN-based auto-contouring tool performed well on both internal and external datasets and had a high rate of clinical acceptability.
Identifiants
pubmed: 32964477
doi: 10.1002/mp.14467
pmc: PMC7756586
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
5648-5658Subventions
Organisme : Varian Medical Systems (Varian)
Organisme : National Institutes of Health/National Cancer Institute
ID : UH2-CA202665
Organisme : National Institutes of Health/National Cancer Institute
ID : UH3-CA202665
Organisme : National Institutes of Health/National Cancer Institute
ID : P30CA016672
Informations de copyright
© 2020 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.
Références
Med Phys. 2017 Oct;44(10):5221-5233
pubmed: 28730602
Radiother Oncol. 2006 Jan;78(1):67-77
pubmed: 16403584
J Vis Exp. 2018 Apr 11;(134):
pubmed: 29708544
Int J Radiat Oncol Biol Phys. 2018 Jun 1;101(2):468-478
pubmed: 29559291
Med Phys. 2017 Feb;44(2):547-557
pubmed: 28205307
Radiother Oncol. 2018 Feb;126(2):312-317
pubmed: 29208513
Med Phys. 2019 Nov;46(11):5086-5097
pubmed: 31505046
IEEE Trans Pattern Anal Mach Intell. 2017 Apr;39(4):640-651
pubmed: 27244717
Comput Med Imaging Graph. 2018 Jun;66:90-99
pubmed: 29573583
Pract Radiat Oncol. 2013 Oct-Dec;3(4):e139-47
pubmed: 24674411
Med Phys. 2019 May;46(5):2169-2180
pubmed: 30830685
Int J Comput Assist Radiol Surg. 2018 Aug;13(8):1211-1219
pubmed: 29766373
Int J Radiat Oncol Biol Phys. 2019 Jul 15;104(4):924-932
pubmed: 30890447
IEEE Trans Med Imaging. 2013 Jun;32(6):1043-57
pubmed: 23475352
Int J Comput Assist Radiol Surg. 2018 Nov;13(11):1687-1696
pubmed: 30088208
J Glob Oncol. 2019 Jan;5:1-9
pubmed: 30629457
Strahlenther Onkol. 2014 May;190(5):433-43
pubmed: 24595416
Phys Med Biol. 2017 Nov 14;62(23):9140-9158
pubmed: 29049027
CA Cancer J Clin. 2016 Jul;66(4):271-89
pubmed: 27253694
J Med Imaging (Bellingham). 2017 Oct;4(4):041302
pubmed: 28840173
Int J Comput Assist Radiol Surg. 2017 Mar;12(3):399-411
pubmed: 27885540
Int J Cancer. 2015 Mar 1;136(5):E359-86
pubmed: 25220842
J Glob Oncol. 2016 May 25;2(5):311-340
pubmed: 28717717
Phys Med Biol. 2018 Nov 22;63(23):235002
pubmed: 30465543
Semin Radiat Oncol. 2019 Jul;29(3):185-197
pubmed: 31027636
Med Phys. 2020 Jun;47(6):e236-e272
pubmed: 31967655
J Glob Oncol. 2018 Jul;4:1-11
pubmed: 30110221
Neural Netw. 2018 Oct;106:249-259
pubmed: 30092410
Phys Med Biol. 2018 Dec 14;63(24):245015
pubmed: 30523973
Cancer Radiother. 2018 Dec;22(8):747-753
pubmed: 30322819
Tomography. 2016 Dec;2(4):421-429
pubmed: 28105470
Sci Rep. 2017 Jul 13;7(1):5301
pubmed: 28706185
Annu Int Conf IEEE Eng Med Biol Soc. 2017 Jul;2017:1752-1755
pubmed: 29060226
Med Phys. 2017 Dec;44(12):6377-6389
pubmed: 28963779
Phys Med. 2020 Jan;69:184-191
pubmed: 31918371