schliessen

Filtern

 

Bibliotheken

Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma

Abstract We aimed to identify optimal machine-learning methods for radiomics-based prediction of local failure and distant failure in advanced nasopharyngeal carcinoma (NPC). We enrolled 110 patients with advanced NPC. A total of 970 radiomic features were extracted from MRI images for each patient.... Full description

Journal Title: Cancer letters 2017, Vol.403, p.21-27
Main Author: Zhang, Bin
Other Authors: He, Xin , Ouyang, Fusheng , Gu, Dongsheng , Dong, Yuhao , Zhang, Lu , Mo, Xiaokai , Huang, Wenhui , Tian, Jie , Zhang, Shuixing
Format: Electronic Article Electronic Article
Language: English
Subjects:
Quelle: Alma/SFX Local Collection
Publisher: Ireland: Elsevier B.V
ID: ISSN: 0304-3835
Link: https://www.ncbi.nlm.nih.gov/pubmed/28610955
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: cdi_proquest_miscellaneous_1909745224
title: Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma
format: Article
creator:
  • Zhang, Bin
  • He, Xin
  • Ouyang, Fusheng
  • Gu, Dongsheng
  • Dong, Yuhao
  • Zhang, Lu
  • Mo, Xiaokai
  • Huang, Wenhui
  • Tian, Jie
  • Zhang, Shuixing
subjects:
  • Algorithms
  • Area Under Curve
  • Biomarkers
  • Cancer
  • Carcinoma
  • Carcinoma - diagnostic imaging
  • Carcinoma - pathology
  • Carcinoma - therapy
  • Classification
  • Clinical decision making
  • Decision making
  • Decision Support Techniques
  • Diagnosis, Computer-Assisted - methods
  • Feature extraction
  • Gene expression
  • Genotype & phenotype
  • Hematology, Oncology and Palliative Medicine
  • High-Throughput Screening Assays
  • Histology
  • Humans
  • Identification methods
  • Image classification
  • Image Interpretation, Computer-Assisted - methods
  • Imaging
  • Learning algorithms
  • Linear Models
  • Lung cancer
  • Machine learning
  • Machinery
  • Magnetic resonance imaging
  • Magnetic Resonance Imaging - methods
  • Medical imaging
  • Medical imaging equipment
  • Medical prognosis
  • Nasopharyngeal Carcinoma
  • Nasopharyngeal Neoplasms - diagnostic imaging
  • Nasopharyngeal Neoplasms - pathology
  • Nasopharyngeal Neoplasms - therapy
  • Neural networks
  • Oncology
  • Patients
  • Precision medicine
  • Predictive Value of Tests
  • Radiation therapy
  • Radiomics
  • Reproducibility of Results
  • Risk Assessment
  • Risk Factors
  • ROC Curve
  • Support Vector Machine
  • Support vector machines
  • Teaching methods
  • Treatment Failure
ispartof: Cancer letters, 2017, Vol.403, p.21-27
description: Abstract We aimed to identify optimal machine-learning methods for radiomics-based prediction of local failure and distant failure in advanced nasopharyngeal carcinoma (NPC). We enrolled 110 patients with advanced NPC. A total of 970 radiomic features were extracted from MRI images for each patient. Six feature selection methods and nine classification methods were evaluated in terms of their performance. We applied the 10-fold cross-validation as the criterion for feature selection and classification. We repeated each combination for 50 times to obtain the mean area under the curve (AUC) and test error. We observed that the combination methods Random Forest (RF) + RF (AUC, 0.8464 ± 0.0069; test error, 0.3135 ± 0.0088) had the highest prognostic performance, followed by RF + Adaptive Boosting (AdaBoost) (AUC, 0.8204 ± 0.0095; test error, 0.3384 ± 0.0097), and Sure Independence Screening (SIS) + Linear Support Vector Machines (LSVM) (AUC, 0.7883 ± 0.0096; test error, 0.3985 ± 0.0100). Our radiomics study identified optimal machine-learning methods for the radiomics-based prediction of local failure and distant failure in advanced NPC, which could enhance the applications of radiomics in precision oncology and clinical practice.
language: eng
source: Alma/SFX Local Collection
identifier: ISSN: 0304-3835
fulltext: fulltext
issn:
  • 0304-3835
  • 1872-7980
url: Link


@attributes
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
RANK2.7907119
LOCALfalse
PrimoNMBib
record
control
sourceidgale_proqu
recordidTN_cdi_proquest_miscellaneous_1909745224
sourceformatXML
sourcesystemPC
galeidA521883403
sourcerecordidA521883403
originalsourceidFETCH-LOGICAL-c475t-60e1c332365e6bcc931c3dde8a9ec4201ae35a5cb746962209cef6098facc2cd3
addsrcrecordideNqVUsuKFDEULURx2tE_EClwM5sq86jUw4UwDL5gQPCxDrdv3epJTzppk-qB_ntv0aPCbESyyOucw8k5KYqXUtRSyPbNtkYInuZaCdnVoq2FaB4VK9l3quqGXjwuVkKLptK9NmfFs5y3QgjTdOZpcab6VorBmFUxfoXRxZ3Dcgd44wJVniAFFzYlesjZTY5SLqeYyn2KmxDzzNg1UyDdLjdxKmG8g4A0lgFy3N9AOoYNgS8RErrAyOfFkwl8phf383nx48P771efqusvHz9fXV5XyLbmqhUkUWulW0PtGnHQvB1H6mEgbPiZQNqAwXXXtEOrlBiQplYM_QSICkd9XlycdNnqzwPl2e5cRvIeAsVDtnIQQ9cYpRqGvn4A3cZDCuyOUaox0pheMqo-oTbgybowxTkB8hiJI4uBJsfnl0bJvteN0ExoTgRMMedEk90nx1EdrRR2qc1u7ak2u9RmRWu5Nqa9undzWO9o_EP63RMD3j7QRTfD7GJgQ87_S_3diUyc_R33aTM6WhpziXC2Y3T_K4DeBYfgb-lI-W9yNisr7Lfl3y3fTnZa6J7XvwBp4tQm
sourcetypeAggregation Database
isCDItrue
recordtypearticle
pqid1924515581
display
typearticle
titleRadiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma
sourceAlma/SFX Local Collection
creatorZhang, Bin ; He, Xin ; Ouyang, Fusheng ; Gu, Dongsheng ; Dong, Yuhao ; Zhang, Lu ; Mo, Xiaokai ; Huang, Wenhui ; Tian, Jie ; Zhang, Shuixing
creatorcontribZhang, Bin ; He, Xin ; Ouyang, Fusheng ; Gu, Dongsheng ; Dong, Yuhao ; Zhang, Lu ; Mo, Xiaokai ; Huang, Wenhui ; Tian, Jie ; Zhang, Shuixing
descriptionAbstract We aimed to identify optimal machine-learning methods for radiomics-based prediction of local failure and distant failure in advanced nasopharyngeal carcinoma (NPC). We enrolled 110 patients with advanced NPC. A total of 970 radiomic features were extracted from MRI images for each patient. Six feature selection methods and nine classification methods were evaluated in terms of their performance. We applied the 10-fold cross-validation as the criterion for feature selection and classification. We repeated each combination for 50 times to obtain the mean area under the curve (AUC) and test error. We observed that the combination methods Random Forest (RF) + RF (AUC, 0.8464 ± 0.0069; test error, 0.3135 ± 0.0088) had the highest prognostic performance, followed by RF + Adaptive Boosting (AdaBoost) (AUC, 0.8204 ± 0.0095; test error, 0.3384 ± 0.0097), and Sure Independence Screening (SIS) + Linear Support Vector Machines (LSVM) (AUC, 0.7883 ± 0.0096; test error, 0.3985 ± 0.0100). Our radiomics study identified optimal machine-learning methods for the radiomics-based prediction of local failure and distant failure in advanced NPC, which could enhance the applications of radiomics in precision oncology and clinical practice.
identifier
0ISSN: 0304-3835
1EISSN: 1872-7980
2DOI: 10.1016/j.canlet.2017.06.004
3PMID: 28610955
languageeng
publisherIreland: Elsevier B.V
subjectAlgorithms ; Area Under Curve ; Biomarkers ; Cancer ; Carcinoma ; Carcinoma - diagnostic imaging ; Carcinoma - pathology ; Carcinoma - therapy ; Classification ; Clinical decision making ; Decision making ; Decision Support Techniques ; Diagnosis, Computer-Assisted - methods ; Feature extraction ; Gene expression ; Genotype & phenotype ; Hematology, Oncology and Palliative Medicine ; High-Throughput Screening Assays ; Histology ; Humans ; Identification methods ; Image classification ; Image Interpretation, Computer-Assisted - methods ; Imaging ; Learning algorithms ; Linear Models ; Lung cancer ; Machine learning ; Machinery ; Magnetic resonance imaging ; Magnetic Resonance Imaging - methods ; Medical imaging ; Medical imaging equipment ; Medical prognosis ; Nasopharyngeal Carcinoma ; Nasopharyngeal Neoplasms - diagnostic imaging ; Nasopharyngeal Neoplasms - pathology ; Nasopharyngeal Neoplasms - therapy ; Neural networks ; Oncology ; Patients ; Precision medicine ; Predictive Value of Tests ; Radiation therapy ; Radiomics ; Reproducibility of Results ; Risk Assessment ; Risk Factors ; ROC Curve ; Support Vector Machine ; Support vector machines ; Teaching methods ; Treatment Failure
ispartofCancer letters, 2017, Vol.403, p.21-27
rights
0Elsevier B.V.
12017 Elsevier B.V.
2Copyright © 2017 Elsevier B.V. All rights reserved.
3COPYRIGHT 2017 Elsevier B.V.
4Copyright Elsevier Limited Sep 10, 2017
lds50peer_reviewed
citedbyFETCH-LOGICAL-c475t-60e1c332365e6bcc931c3dde8a9ec4201ae35a5cb746962209cef6098facc2cd3
orcidid0000-0001-7377-382X
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
thumbnail$$Usyndetics_thumb_exl
backlink$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/28610955$$D View this record in MEDLINE/PubMed
search
creatorcontrib
0Zhang, Bin
1He, Xin
2Ouyang, Fusheng
3Gu, Dongsheng
4Dong, Yuhao
5Zhang, Lu
6Mo, Xiaokai
7Huang, Wenhui
8Tian, Jie
9Zhang, Shuixing
title
0Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma
1Cancer letters
addtitleCancer Lett
descriptionAbstract We aimed to identify optimal machine-learning methods for radiomics-based prediction of local failure and distant failure in advanced nasopharyngeal carcinoma (NPC). We enrolled 110 patients with advanced NPC. A total of 970 radiomic features were extracted from MRI images for each patient. Six feature selection methods and nine classification methods were evaluated in terms of their performance. We applied the 10-fold cross-validation as the criterion for feature selection and classification. We repeated each combination for 50 times to obtain the mean area under the curve (AUC) and test error. We observed that the combination methods Random Forest (RF) + RF (AUC, 0.8464 ± 0.0069; test error, 0.3135 ± 0.0088) had the highest prognostic performance, followed by RF + Adaptive Boosting (AdaBoost) (AUC, 0.8204 ± 0.0095; test error, 0.3384 ± 0.0097), and Sure Independence Screening (SIS) + Linear Support Vector Machines (LSVM) (AUC, 0.7883 ± 0.0096; test error, 0.3985 ± 0.0100). Our radiomics study identified optimal machine-learning methods for the radiomics-based prediction of local failure and distant failure in advanced NPC, which could enhance the applications of radiomics in precision oncology and clinical practice.
subject
0Algorithms
1Area Under Curve
2Biomarkers
3Cancer
4Carcinoma
5Carcinoma - diagnostic imaging
6Carcinoma - pathology
7Carcinoma - therapy
8Classification
9Clinical decision making
10Decision making
11Decision Support Techniques
12Diagnosis, Computer-Assisted - methods
13Feature extraction
14Gene expression
15Genotype & phenotype
16Hematology, Oncology and Palliative Medicine
17High-Throughput Screening Assays
18Histology
19Humans
20Identification methods
21Image classification
22Image Interpretation, Computer-Assisted - methods
23Imaging
24Learning algorithms
25Linear Models
26Lung cancer
27Machine learning
28Machinery
29Magnetic resonance imaging
30Magnetic Resonance Imaging - methods
31Medical imaging
32Medical imaging equipment
33Medical prognosis
34Nasopharyngeal Carcinoma
35Nasopharyngeal Neoplasms - diagnostic imaging
36Nasopharyngeal Neoplasms - pathology
37Nasopharyngeal Neoplasms - therapy
38Neural networks
39Oncology
40Patients
41Precision medicine
42Predictive Value of Tests
43Radiation therapy
44Radiomics
45Reproducibility of Results
46Risk Assessment
47Risk Factors
48ROC Curve
49Support Vector Machine
50Support vector machines
51Teaching methods
52Treatment Failure
issn
00304-3835
11872-7980
fulltexttrue
rsrctypearticle
creationdate2017
recordtypearticle
recordideNqVUsuKFDEULURx2tE_EClwM5sq86jUw4UwDL5gQPCxDrdv3epJTzppk-qB_ntv0aPCbESyyOucw8k5KYqXUtRSyPbNtkYInuZaCdnVoq2FaB4VK9l3quqGXjwuVkKLptK9NmfFs5y3QgjTdOZpcab6VorBmFUxfoXRxZ3Dcgd44wJVniAFFzYlesjZTY5SLqeYyn2KmxDzzNg1UyDdLjdxKmG8g4A0lgFy3N9AOoYNgS8RErrAyOfFkwl8phf383nx48P771efqusvHz9fXV5XyLbmqhUkUWulW0PtGnHQvB1H6mEgbPiZQNqAwXXXtEOrlBiQplYM_QSICkd9XlycdNnqzwPl2e5cRvIeAsVDtnIQQ9cYpRqGvn4A3cZDCuyOUaox0pheMqo-oTbgybowxTkB8hiJI4uBJsfnl0bJvteN0ExoTgRMMedEk90nx1EdrRR2qc1u7ak2u9RmRWu5Nqa9undzWO9o_EP63RMD3j7QRTfD7GJgQ87_S_3diUyc_R33aTM6WhpziXC2Y3T_K4DeBYfgb-lI-W9yNisr7Lfl3y3fTnZa6J7XvwBp4tQm
startdate2017
enddate2017
creator
0Zhang, Bin
1He, Xin
2Ouyang, Fusheng
3Gu, Dongsheng
4Dong, Yuhao
5Zhang, Lu
6Mo, Xiaokai
7Huang, Wenhui
8Tian, Jie
9Zhang, Shuixing
general
0Elsevier B.V
1Elsevier Limited
scope
0CGR
1CUY
2CVF
3ECM
4EIF
5NPM
6AAYXX
7CITATION
8BSHEE
93V.
107RV
117TO
127U9
137X7
147XB
1588E
1688G
178AO
188C1
198FE
208FH
218FI
228FJ
238FK
248G5
25ABUWG
26AZQEC
27BBNVY
28BENPR
29BHPHI
30DWQXO
31FYUFA
32GHDGH
33GNUQQ
34GUQSH
35H94
36HCIFZ
37K9.
38KB0
39LK8
40M0S
41M1P
42M2M
43M2O
44M7P
45MBDVC
46NAPCQ
47PADUT
48PQEST
49PQQKQ
50PQUKI
51PRINS
52Q9U
537X8
orcididhttps://orcid.org/0000-0001-7377-382X
sort
creationdate2017
titleRadiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma
authorZhang, Bin ; He, Xin ; Ouyang, Fusheng ; Gu, Dongsheng ; Dong, Yuhao ; Zhang, Lu ; Mo, Xiaokai ; Huang, Wenhui ; Tian, Jie ; Zhang, Shuixing
facets
frbrtype5
frbrgroupidcdi_FETCH-LOGICAL-c475t-60e1c332365e6bcc931c3dde8a9ec4201ae35a5cb746962209cef6098facc2cd3
rsrctypearticles
prefilterarticles
languageeng
creationdate2017
topic
0Algorithms
1Area Under Curve
2Biomarkers
3Cancer
4Carcinoma
5Carcinoma - diagnostic imaging
6Carcinoma - pathology
7Carcinoma - therapy
8Classification
9Clinical decision making
10Decision making
11Decision Support Techniques
12Diagnosis, Computer-Assisted - methods
13Feature extraction
14Gene expression
15Genotype & phenotype
16Hematology, Oncology and Palliative Medicine
17High-Throughput Screening Assays
18Histology
19Humans
20Identification methods
21Image classification
22Image Interpretation, Computer-Assisted - methods
23Imaging
24Learning algorithms
25Linear Models
26Lung cancer
27Machine learning
28Machinery
29Magnetic resonance imaging
30Magnetic Resonance Imaging - methods
31Medical imaging
32Medical imaging equipment
33Medical prognosis
34Nasopharyngeal Carcinoma
35Nasopharyngeal Neoplasms - diagnostic imaging
36Nasopharyngeal Neoplasms - pathology
37Nasopharyngeal Neoplasms - therapy
38Neural networks
39Oncology
40Patients
41Precision medicine
42Predictive Value of Tests
43Radiation therapy
44Radiomics
45Reproducibility of Results
46Risk Assessment
47Risk Factors
48ROC Curve
49Support Vector Machine
50Support vector machines
51Teaching methods
52Treatment Failure
toplevel
0peer_reviewed
1online_resources
creatorcontrib
0Zhang, Bin
1He, Xin
2Ouyang, Fusheng
3Gu, Dongsheng
4Dong, Yuhao
5Zhang, Lu
6Mo, Xiaokai
7Huang, Wenhui
8Tian, Jie
9Zhang, Shuixing
collection
0Medline
1MEDLINE
2MEDLINE (Ovid)
3MEDLINE
4MEDLINE
5PubMed
6CrossRef
7Academic OneFile (A&I only)
8ProQuest Central (Corporate)
9Nursing & Allied Health Database
10Oncogenes and Growth Factors Abstracts
11Virology and AIDS Abstracts
12Health & Medical Collection
13ProQuest Central (purchase pre-March 2016)
14Medical Database (Alumni Edition)
15Psychology Database (Alumni)
16ProQuest Pharma Collection
17Public Health Database
18ProQuest SciTech Collection
19ProQuest Natural Science Collection
20Hospital Premium Collection
21Hospital Premium Collection (Alumni Edition)
22ProQuest Central (Alumni) (purchase pre-March 2016)
23Research Library (Alumni Edition)
24ProQuest Central (Alumni Edition)
25ProQuest Central Essentials
26Biological Science Collection
27ProQuest Central
28Natural Science Collection
29ProQuest Central Korea
30Health Research Premium Collection
31Health Research Premium Collection (Alumni)
32ProQuest Central Student
33Research Library Prep
34AIDS and Cancer Research Abstracts
35SciTech Premium Collection
36ProQuest Health & Medical Complete (Alumni)
37Nursing & Allied Health Database (Alumni Edition)
38ProQuest Biological Science Collection
39Health & Medical Collection (Alumni Edition)
40Medical Database
41Psychology Database
42Research Library
43Biological Science Database
44Research Library (Corporate)
45Nursing & Allied Health Premium
46Research Library China
47ProQuest One Academic Eastern Edition
48ProQuest One Academic
49ProQuest One Academic UKI Edition
50ProQuest Central China
51ProQuest Central Basic
52MEDLINE - Academic
jtitleCancer letters
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
au
0Zhang, Bin
1He, Xin
2Ouyang, Fusheng
3Gu, Dongsheng
4Dong, Yuhao
5Zhang, Lu
6Mo, Xiaokai
7Huang, Wenhui
8Tian, Jie
9Zhang, Shuixing
formatjournal
genrearticle
ristypeJOUR
atitleRadiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma
jtitleCancer letters
addtitleCancer Lett
date2017
risdate2017
volume403
spage21
epage27
pages21-27
issn0304-3835
eissn1872-7980
abstractAbstract We aimed to identify optimal machine-learning methods for radiomics-based prediction of local failure and distant failure in advanced nasopharyngeal carcinoma (NPC). We enrolled 110 patients with advanced NPC. A total of 970 radiomic features were extracted from MRI images for each patient. Six feature selection methods and nine classification methods were evaluated in terms of their performance. We applied the 10-fold cross-validation as the criterion for feature selection and classification. We repeated each combination for 50 times to obtain the mean area under the curve (AUC) and test error. We observed that the combination methods Random Forest (RF) + RF (AUC, 0.8464 ± 0.0069; test error, 0.3135 ± 0.0088) had the highest prognostic performance, followed by RF + Adaptive Boosting (AdaBoost) (AUC, 0.8204 ± 0.0095; test error, 0.3384 ± 0.0097), and Sure Independence Screening (SIS) + Linear Support Vector Machines (LSVM) (AUC, 0.7883 ± 0.0096; test error, 0.3985 ± 0.0100). Our radiomics study identified optimal machine-learning methods for the radiomics-based prediction of local failure and distant failure in advanced NPC, which could enhance the applications of radiomics in precision oncology and clinical practice.
copIreland
pubElsevier B.V
pmid28610955
doi10.1016/j.canlet.2017.06.004
orcididhttps://orcid.org/0000-0001-7377-382X