PleThora: Pleural effusion and thoracic cavity segmentations in diseased lungs for benchmarking chest CT processing pipelines.
computer-aided decision support systems
image processing
image segmentation techniques
informatics in imaging
quantitative imaging
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:
07
04
2020
revised:
22
07
2020
accepted:
27
07
2020
pubmed:
5
8
2020
medline:
15
5
2021
entrez:
5
8
2020
Statut:
ppublish
Résumé
This manuscript describes a dataset of thoracic cavity segmentations and discrete pleural effusion segmentations we have annotated on 402 computed tomography (CT) scans acquired from patients with non-small cell lung cancer. The segmentation of these anatomic regions precedes fundamental tasks in image analysis pipelines such as lung structure segmentation, lesion detection, and radiomics feature extraction. Bilateral thoracic cavity volumes and pleural effusion volumes were manually segmented on CT scans acquired from The Cancer Imaging Archive "NSCLC Radiomics" data collection. Four hundred and two thoracic segmentations were first generated automatically by a U-Net based algorithm trained on chest CTs without cancer, manually corrected by a medical student to include the complete thoracic cavity (normal, pathologic, and atelectatic lung parenchyma, lung hilum, pleural effusion, fibrosis, nodules, tumor, and other anatomic anomalies), and revised by a radiation oncologist or a radiologist. Seventy-eight pleural effusions were manually segmented by a medical student and revised by a radiologist or radiation oncologist. Interobserver agreement between the radiation oncologist and radiologist corrections was acceptable. All expert-vetted segmentations are publicly available in NIfTI format through The Cancer Imaging Archive at https://doi.org/10.7937/tcia.2020.6c7y-gq39. Tabular data detailing clinical and technical metadata linked to segmentation cases are also available. Thoracic cavity segmentations will be valuable for developing image analysis pipelines on pathologic lungs - where current automated algorithms struggle most. In conjunction with gross tumor volume segmentations already available from "NSCLC Radiomics," pleural effusion segmentations may be valuable for investigating radiomics profile differences between effusion and primary tumor or training algorithms to discriminate between them.
Identifiants
pubmed: 32749075
doi: 10.1002/mp.14424
pmc: PMC7722027
mid: NIHMS1630940
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
5941-5952Subventions
Organisme : NCI NIH HHS
ID : R01 CA214825
Pays : United States
Organisme : NIBIB NIH HHS
ID : R25 EB025787
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR003167
Pays : United States
Organisme : NIDCR NIH HHS
ID : R56 DE025248
Pays : United States
Organisme : HHS | NIH | National Institute of Biomedical Imaging and Bioengineering (NIBIB)
ID : R25EB025787-01
Organisme : HHS | National Institutes of Health (NIH)
ID : 1R01DE025248
Organisme : HHS | National Institutes of Health (NIH)
ID : 1R01CA214825
Organisme : NIA NIH HHS
ID : R01 AG066749
Pays : United States
Organisme : HHS | National Institutes of Health (NIH)
ID : R56DE025248
Organisme : NCI NIH HHS
ID : P30 CA016672
Pays : United States
Organisme : NCI NIH HHS
ID : P50 CA097007
Pays : United States
Organisme : National Science Foundation (NSF)
ID : NSF1557679
Organisme : NIDCR NIH HHS
ID : R01 DE028290
Pays : United States
Organisme : NIDCR NIH HHS
ID : R01 DE025248
Pays : United States
Organisme : National Science Foundation (NSF)
ID : NSF1933369
Organisme : HHS | National Institutes of Health (NIH)
ID : UL1TR003167
Organisme : Cancer Prevention and Research Institute of Texas (CPRIT)
ID : RP170668
Organisme : HHS | NIH | National Cancer Institute (NCI)
ID : P30CA016672
Organisme : HHS | National Institutes of Health (NIH)
ID : R01DE028290
Organisme : HHS | NIH | National Cancer Institute (NCI)
ID : P50CA097007
Organisme : UTHealth Center for Clinical and Translational Sciences
Organisme : NCI NIH HHS
ID : R01 CA218148
Pays : United States
Organisme : HHS | National Institutes of Health (NIH)
ID : R01AG066749
Organisme : HHS | NIH | National Cancer Institute (NCI)
ID : 1R01CA218148
Organisme : Swiss Cancer League
ID : BIL KLS-4300-08-2017
Informations de copyright
© 2020 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.
Références
Asian Pac J Cancer Prev. ;18(7):1869-1874
pubmed: 28749127
J Digit Imaging. 2013 Dec;26(6):1045-57
pubmed: 23884657
Medicine (Baltimore). 2015 Jul;94(29):e1010
pubmed: 26200610
Front Neuroinform. 2014 Feb 21;8:14
pubmed: 24600388
Sci Data. 2016 Mar 15;3:160018
pubmed: 26978244
J Digit Imaging. 2019 Dec;32(6):1019-1026
pubmed: 31396776
Magn Reson Imaging. 2012 Nov;30(9):1234-48
pubmed: 22898692
IEEE Trans Biomed Eng. 2013 Jul;60(7):1834-40
pubmed: 23372069
Med Image Anal. 2019 Jan;51:169-183
pubmed: 30453165
IEEE Trans Med Imaging. 2001 Jun;20(6):490-8
pubmed: 11437109
Nat Commun. 2014 Jun 03;5:4006
pubmed: 24892406
Lung. 2017 Oct;195(5):653-660
pubmed: 28656381
Sci Rep. 2018 Jun 28;8(1):9802
pubmed: 29955159
Eur Radiol Exp. 2020 Aug 20;4(1):50
pubmed: 32814998
IEEE Trans Med Imaging. 2019 Jul;38(7):1736-1749
pubmed: 30605097
PLoS One. 2017 Oct 2;12(10):e0185850
pubmed: 28968445
Radiology. 2016 Feb;278(2):593-600
pubmed: 26323029
IEEE Trans Med Imaging. 2016 May;35(5):1229-1239
pubmed: 26886978
Radiographics. 2015 Jul-Aug;35(4):1056-76
pubmed: 26172351
Ann Transl Med. 2019 Jun;7(12):259
pubmed: 31355226
J Neurosci Methods. 2016 May 1;264:47-56
pubmed: 26945974
Med Phys. 2017 Jul;44(7):e43-e76
pubmed: 28376237
J Med Imaging (Bellingham). 2018 Jul;5(3):034503
pubmed: 30840717
Nat Med. 2019 Jun;25(6):954-961
pubmed: 31110349
J Xray Sci Technol. 2017;25(6):887-905
pubmed: 28550270
Comput Biol Med. 2018 Dec 1;103:287-300
pubmed: 30415174
Chest. 2013 Apr;143(4):1054-1059
pubmed: 23632863
Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2018). 2018 Sep;11045:3-11
pubmed: 32613207
IEEE Trans Med Imaging. 2014 Dec;33(12):2293-310
pubmed: 25020069
IEEE Trans Med Imaging. 2017 Jan;36(1):263-276
pubmed: 27705854
Med Phys. 2020 Nov;47(11):5941-5952
pubmed: 32749075
PLoS One. 2018 Apr 11;13(4):e0193714
pubmed: 29641601
Respir Med. 2017 Mar;124:88-99
pubmed: 28233652
Med Phys. 2018 Oct;45(10):4568-4581
pubmed: 30144101
Neuroimage. 2006 Jul 1;31(3):1116-28
pubmed: 16545965
Biometrics. 1977 Mar;33(1):159-74
pubmed: 843571
Quant Imaging Med Surg. 2020 Jan;10(1):233-242
pubmed: 31956545
Comput Med Imaging Graph. 2015 Mar;40:13-29
pubmed: 25467805
Acad Radiol. 2010 Jul;17(7):841-8
pubmed: 20399688
Biomed Sci Instrum. 2013;49:13-9
pubmed: 23686175