CT texture analysis for the prediction of KRAS mutation status in colorectal cancer via a machine learning approach.
Aged
Colorectal Neoplasms
/ diagnostic imaging
Female
Humans
Machine Learning
Male
Mutation
/ genetics
Predictive Value of Tests
Proto-Oncogene Proteins p21(ras)
/ genetics
ROC Curve
Radiographic Image Interpretation, Computer-Assisted
/ methods
Retrospective Studies
Tomography, X-Ray Computed
/ methods
CT texture analysis
Colorectal cancer
KRAS mutation
Machine learning
Radiogenomics
Journal
European journal of radiology
ISSN: 1872-7727
Titre abrégé: Eur J Radiol
Pays: Ireland
ID NLM: 8106411
Informations de publication
Date de publication:
Sep 2019
Sep 2019
Historique:
received:
11
03
2019
revised:
27
05
2019
accepted:
30
06
2019
entrez:
24
8
2019
pubmed:
24
8
2019
medline:
31
12
2019
Statut:
ppublish
Résumé
This study aimed to investigate whether a machine learning-based computed tomography (CT) texture analysis could predict the mutation status of V-Ki-ras2 Kirsten rat sarcoma viral oncogene homolog (KRAS) in colorectal cancer. This retrospective study comprised 40 patients with pathologically confirmed colorectal cancer who underwent KRAS mutation testing, contrast-enhancement CT, and In the univariate analyses, the AUC of each CT texture parameter ranged from 0.4 to 0.7, while the AUC of the SUV A machine learning-based CT texture analysis was superior to the SUV
Identifiants
pubmed: 31439256
pii: S0720-048X(19)30232-3
doi: 10.1016/j.ejrad.2019.06.028
pii:
doi:
Substances chimiques
KRAS protein, human
0
Proto-Oncogene Proteins p21(ras)
EC 3.6.5.2
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
38-43Informations de copyright
Copyright © 2019 Elsevier B.V. All rights reserved.