CNN-based survival model for pancreatic ductal adenocarcinoma in medical imaging.
Convolutional neural network
Cox proportional hazard model
Radiomics
Survial analysis
Journal
BMC medical imaging
ISSN: 1471-2342
Titre abrégé: BMC Med Imaging
Pays: England
ID NLM: 100968553
Informations de publication
Date de publication:
03 02 2020
03 02 2020
Historique:
received:
29
07
2019
accepted:
27
01
2020
entrez:
5
2
2020
pubmed:
6
2
2020
medline:
26
9
2020
Statut:
epublish
Résumé
Cox proportional hazard model (CPH) is commonly used in clinical research for survival analysis. In quantitative medical imaging (radiomics) studies, CPH plays an important role in feature reduction and modeling. However, the underlying linear assumption of CPH model limits the prognostic performance. In this work, using transfer learning, a convolutional neural network (CNN) based survival model was built and tested on preoperative CT images of resectable Pancreatic Ductal Adenocarcinoma (PDAC) patients. The proposed CNN-based survival model outperformed the traditional CPH-based radiomics approach in terms of concordance index and index of prediction accuracy, providing a better fit for patients' survival patterns. The proposed CNN-based survival model outperforms CPH-based radiomics pipeline in PDAC prognosis. This approach offers a better fit for survival patterns based on CT images and overcomes the limitations of conventional survival models.
Sections du résumé
BACKGROUND
Cox proportional hazard model (CPH) is commonly used in clinical research for survival analysis. In quantitative medical imaging (radiomics) studies, CPH plays an important role in feature reduction and modeling. However, the underlying linear assumption of CPH model limits the prognostic performance. In this work, using transfer learning, a convolutional neural network (CNN) based survival model was built and tested on preoperative CT images of resectable Pancreatic Ductal Adenocarcinoma (PDAC) patients.
RESULTS
The proposed CNN-based survival model outperformed the traditional CPH-based radiomics approach in terms of concordance index and index of prediction accuracy, providing a better fit for patients' survival patterns.
CONCLUSIONS
The proposed CNN-based survival model outperforms CPH-based radiomics pipeline in PDAC prognosis. This approach offers a better fit for survival patterns based on CT images and overcomes the limitations of conventional survival models.
Identifiants
pubmed: 32013871
doi: 10.1186/s12880-020-0418-1
pii: 10.1186/s12880-020-0418-1
pmc: PMC6998249
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
11Références
J Nucl Cardiol. 2014 Aug;21(4):686-94
pubmed: 24810431
Breast Cancer Res Treat. 1997 Jun;44(2):167-78
pubmed: 9232275
Sci Rep. 2019 Apr 1;9(1):5449
pubmed: 30931954
Ann Transl Med. 2017 May;5(10):211
pubmed: 28603726
Diagn Progn Res. 2018 May 4;2:7
pubmed: 31093557
PLoS One. 2019 Jan 18;14(1):e0210758
pubmed: 30657785
Br J Radiol. 2018 Nov;91(1091):20170926
pubmed: 29947266
BMC Med Res Methodol. 2018 Feb 26;18(1):24
pubmed: 29482517
Insights Imaging. 2018 Aug;9(4):611-629
pubmed: 29934920
PLoS Comput Biol. 2018 Apr 10;14(4):e1006076
pubmed: 29634719
Front Immunol. 2018 May 14;9:1044
pubmed: 29868007
JAMA Oncol. 2016 Dec 1;2(12):1636-1642
pubmed: 27541161
Radiology. 2016 Dec;281(3):947-957
pubmed: 27347764
Sci Rep. 2017 Apr 18;7:46349
pubmed: 28418006
Radiology. 2018 Mar;286(3):887-896
pubmed: 29059036
Int J Mol Sci. 2017 Jun 22;18(7):null
pubmed: 28640192
Nature. 2015 May 28;521(7553):436-44
pubmed: 26017442
IEEE Trans Med Imaging. 2016 May;35(5):1299-1312
pubmed: 26978662
PeerJ. 2019 Jan 25;7:e6257
pubmed: 30701130
J Thorac Oncol. 2016 Dec;11(12):2120-2128
pubmed: 27422797
Cancer Res. 2017 Nov 1;77(21):e104-e107
pubmed: 29092951
Sci Rep. 2017 Sep 4;7(1):10353
pubmed: 28871110
Surgery. 2016 Jun;159(6):1520-1527
pubmed: 26847803
Med Phys. 2018 Nov;45(11):5019-5029
pubmed: 30176047
Nat Commun. 2014 Jun 03;5:4006
pubmed: 24892406
Cancer Imaging. 2017 Jan 23;17(1):4
pubmed: 28114978
Bioinformatics. 2011 Nov 15;27(22):3206-8
pubmed: 21903630
IEEE Trans Med Imaging. 2016 May;35(5):1285-98
pubmed: 26886976