Classification of lung adenocarcinoma transcriptome subtypes from pathological images using deep convolutional networks

Purpose Convolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we developed a method for classifying subtypes of lung adenocarcinoma from pathological images using neural network whose that can evaluate phe...

Full description

Saved in:

Bibliographic Details
Published in:	International journal for computer assisted radiology and surgery Vol. 13; no. 12; pp. 1905 - 1913
Main Authors:	Antonio, Victor Andrew A., Ono, Naoaki, Saito, Akira, Sato, Tetsuo, Altaf-Ul-Amin, Md, Kanaya, Shigehiko
Format:	Journal Article
Language:	English
Published:	Cham Springer International Publishing 01.12.2018 Springer Nature B.V
Subjects:	Adenocarcinoma of Lung - classification Adenocarcinoma of Lung - diagnosis Adenocarcinoma of Lung - genetics Artificial neural networks Biopsy Classification Computer Imaging Computer Science Entropy (Information theory) Feature extraction Feature recognition Health Informatics Humans Image analysis Image classification Image Processing, Computer-Assisted - methods Imaging Medicine Medicine & Public Health Neural networks Neural Networks (Computer) Object recognition Original Original Article Pattern recognition Pattern Recognition and Graphics Radiology Surgery Transcriptome Tumors Vision Deep learning Autoencoder Independent subspace analysis Lung cancer Computer-aided diagnosis
ISSN:	1861-6410, 1861-6429, 1861-6429
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Purpose Convolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we developed a method for classifying subtypes of lung adenocarcinoma from pathological images using neural network whose that can evaluate phenotypic features from wider area to consider cellular distributions. Methods In order to recognize the types of tumors, we need not only to detail features of cells, but also to incorporate statistical distribution of the different types of cells. Variants of autoencoders as building blocks of pre-trained convolutional layers of neural networks are implemented. A sparse deep autoencoder which minimizes local information entropy on the encoding layer is then proposed and applied to images of size 2048 × 2048 . We applied this model for feature extraction from pathological images of lung adenocarcinoma, which is comprised of three transcriptome subtypes previously defined by the Cancer Genome Atlas network. Since the tumor tissue is composed of heterogeneous cell populations, recognition of tumor transcriptome subtypes requires more information than local pattern of cells. The parameters extracted using this approach will then be used in multiple reduction stages to perform classification on larger images. Results We were able to demonstrate that these networks successfully recognize morphological features of lung adenocarcinoma. We also performed classification and reconstruction experiments to compare the outputs of the variants. The results showed that the larger input image that covers a certain area of the tissue is required to recognize transcriptome subtypes. The sparse autoencoder network with 2048 × 2048 input provides a 98.9% classification accuracy. Conclusion This study shows the potential of autoencoders as a feature extraction paradigm and paves the way for a whole slide image analysis tool to predict molecular subtypes of tumors from pathological features.
AbstractList	Purpose Convolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we developed a method for classifying subtypes of lung adenocarcinoma from pathological images using neural network whose that can evaluate phenotypic features from wider area to consider cellular distributions. Methods In order to recognize the types of tumors, we need not only to detail features of cells, but also to incorporate statistical distribution of the different types of cells. Variants of autoencoders as building blocks of pre-trained convolutional layers of neural networks are implemented. A sparse deep autoencoder which minimizes local information entropy on the encoding layer is then proposed and applied to images of size 2048 × 2048 . We applied this model for feature extraction from pathological images of lung adenocarcinoma, which is comprised of three transcriptome subtypes previously defined by the Cancer Genome Atlas network. Since the tumor tissue is composed of heterogeneous cell populations, recognition of tumor transcriptome subtypes requires more information than local pattern of cells. The parameters extracted using this approach will then be used in multiple reduction stages to perform classification on larger images. Results We were able to demonstrate that these networks successfully recognize morphological features of lung adenocarcinoma. We also performed classification and reconstruction experiments to compare the outputs of the variants. The results showed that the larger input image that covers a certain area of the tissue is required to recognize transcriptome subtypes. The sparse autoencoder network with 2048 × 2048 input provides a 98.9% classification accuracy. Conclusion This study shows the potential of autoencoders as a feature extraction paradigm and paves the way for a whole slide image analysis tool to predict molecular subtypes of tumors from pathological features. Convolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we developed a method for classifying subtypes of lung adenocarcinoma from pathological images using neural network whose that can evaluate phenotypic features from wider area to consider cellular distributions.PURPOSEConvolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we developed a method for classifying subtypes of lung adenocarcinoma from pathological images using neural network whose that can evaluate phenotypic features from wider area to consider cellular distributions.In order to recognize the types of tumors, we need not only to detail features of cells, but also to incorporate statistical distribution of the different types of cells. Variants of autoencoders as building blocks of pre-trained convolutional layers of neural networks are implemented. A sparse deep autoencoder which minimizes local information entropy on the encoding layer is then proposed and applied to images of size [Formula: see text]. We applied this model for feature extraction from pathological images of lung adenocarcinoma, which is comprised of three transcriptome subtypes previously defined by the Cancer Genome Atlas network. Since the tumor tissue is composed of heterogeneous cell populations, recognition of tumor transcriptome subtypes requires more information than local pattern of cells. The parameters extracted using this approach will then be used in multiple reduction stages to perform classification on larger images.METHODSIn order to recognize the types of tumors, we need not only to detail features of cells, but also to incorporate statistical distribution of the different types of cells. Variants of autoencoders as building blocks of pre-trained convolutional layers of neural networks are implemented. A sparse deep autoencoder which minimizes local information entropy on the encoding layer is then proposed and applied to images of size [Formula: see text]. We applied this model for feature extraction from pathological images of lung adenocarcinoma, which is comprised of three transcriptome subtypes previously defined by the Cancer Genome Atlas network. Since the tumor tissue is composed of heterogeneous cell populations, recognition of tumor transcriptome subtypes requires more information than local pattern of cells. The parameters extracted using this approach will then be used in multiple reduction stages to perform classification on larger images.We were able to demonstrate that these networks successfully recognize morphological features of lung adenocarcinoma. We also performed classification and reconstruction experiments to compare the outputs of the variants. The results showed that the larger input image that covers a certain area of the tissue is required to recognize transcriptome subtypes. The sparse autoencoder network with [Formula: see text] input provides a 98.9% classification accuracy.RESULTSWe were able to demonstrate that these networks successfully recognize morphological features of lung adenocarcinoma. We also performed classification and reconstruction experiments to compare the outputs of the variants. The results showed that the larger input image that covers a certain area of the tissue is required to recognize transcriptome subtypes. The sparse autoencoder network with [Formula: see text] input provides a 98.9% classification accuracy.This study shows the potential of autoencoders as a feature extraction paradigm and paves the way for a whole slide image analysis tool to predict molecular subtypes of tumors from pathological features.CONCLUSIONThis study shows the potential of autoencoders as a feature extraction paradigm and paves the way for a whole slide image analysis tool to predict molecular subtypes of tumors from pathological features. PurposeConvolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we developed a method for classifying subtypes of lung adenocarcinoma from pathological images using neural network whose that can evaluate phenotypic features from wider area to consider cellular distributions.MethodsIn order to recognize the types of tumors, we need not only to detail features of cells, but also to incorporate statistical distribution of the different types of cells. Variants of autoencoders as building blocks of pre-trained convolutional layers of neural networks are implemented. A sparse deep autoencoder which minimizes local information entropy on the encoding layer is then proposed and applied to images of size 2048×2048. We applied this model for feature extraction from pathological images of lung adenocarcinoma, which is comprised of three transcriptome subtypes previously defined by the Cancer Genome Atlas network. Since the tumor tissue is composed of heterogeneous cell populations, recognition of tumor transcriptome subtypes requires more information than local pattern of cells. The parameters extracted using this approach will then be used in multiple reduction stages to perform classification on larger images.ResultsWe were able to demonstrate that these networks successfully recognize morphological features of lung adenocarcinoma. We also performed classification and reconstruction experiments to compare the outputs of the variants. The results showed that the larger input image that covers a certain area of the tissue is required to recognize transcriptome subtypes. The sparse autoencoder network with 2048×2048 input provides a 98.9% classification accuracy.ConclusionThis study shows the potential of autoencoders as a feature extraction paradigm and paves the way for a whole slide image analysis tool to predict molecular subtypes of tumors from pathological features. Convolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we developed a method for classifying subtypes of lung adenocarcinoma from pathological images using neural network whose that can evaluate phenotypic features from wider area to consider cellular distributions. In order to recognize the types of tumors, we need not only to detail features of cells, but also to incorporate statistical distribution of the different types of cells. Variants of autoencoders as building blocks of pre-trained convolutional layers of neural networks are implemented. A sparse deep autoencoder which minimizes local information entropy on the encoding layer is then proposed and applied to images of size [Formula: see text]. We applied this model for feature extraction from pathological images of lung adenocarcinoma, which is comprised of three transcriptome subtypes previously defined by the Cancer Genome Atlas network. Since the tumor tissue is composed of heterogeneous cell populations, recognition of tumor transcriptome subtypes requires more information than local pattern of cells. The parameters extracted using this approach will then be used in multiple reduction stages to perform classification on larger images. We were able to demonstrate that these networks successfully recognize morphological features of lung adenocarcinoma. We also performed classification and reconstruction experiments to compare the outputs of the variants. The results showed that the larger input image that covers a certain area of the tissue is required to recognize transcriptome subtypes. The sparse autoencoder network with [Formula: see text] input provides a 98.9% classification accuracy. This study shows the potential of autoencoders as a feature extraction paradigm and paves the way for a whole slide image analysis tool to predict molecular subtypes of tumors from pathological features.
Author	Kanaya, Shigehiko Ono, Naoaki Saito, Akira Antonio, Victor Andrew A. Sato, Tetsuo Altaf-Ul-Amin, Md
Author_xml	– sequence: 1 givenname: Victor Andrew A. surname: Antonio fullname: Antonio, Victor Andrew A. organization: Graduate School of Science and Technology, Nara Institute of Science and Technology – sequence: 2 givenname: Naoaki orcidid: 0000-0002-7722-055X surname: Ono fullname: Ono, Naoaki email: nono@is.naist.jp organization: Data Science Center, Nara Institute of Science and Technology – sequence: 3 givenname: Akira surname: Saito fullname: Saito, Akira organization: Division for Health Service Promotion, University of Tokyo – sequence: 4 givenname: Tetsuo surname: Sato fullname: Sato, Tetsuo organization: Graduate School of information Science, Nara Institute of Science and Technology – sequence: 5 givenname: Md surname: Altaf-Ul-Amin fullname: Altaf-Ul-Amin, Md organization: Graduate School of Science and Technology, Nara Institute of Science and Technology – sequence: 6 givenname: Shigehiko surname: Kanaya fullname: Kanaya, Shigehiko organization: Graduate School of Science and Technology, Nara Institute of Science and Technology
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/30159833$$D View this record in MEDLINE/PubMed
BookMark	eNp9kUtv1TAQhS1URB_wA9ggS2zYBPxM4g0SuuIlVWIDa8txxqmLYwc7adV_jy-3LVAJVh5pzvl8RucUHcUUAaHnlLymhHRvCqVS9A2hfUN7Lhv2CJ3QvqVNK5g6up8pOUanpVwSImTH5RN0zAmVquf8BF3vginFO2_N6lPEyeGwxQmbEWKyJlsf02zwmk0sNvtlTTPgsg3rzQIFu5xmvJj1IoU0VUTAfjZTXWzFV8gIsGCb4lUK255e9xHW65S_l6fosTOhwLPb9wx9-_D-6-5Tc_7l4-fdu_PGSt6ujeVqMJxbR-jQU2EpUwJUKzrhlB2MGFslRSsVSGnJSGxHnBAWiFNkkDByfobeHrjLNswwWoj1lKCXXIPmG52M139vor_QU7rSLWO8k7ICXt0CcvqxQVn17IuFEEyEtBXNiOqkYqLb__XygfQybbleXVWUU9YxTkVVvfgz0X2Uu06qoDsIbE6lZHDa-vVXOzWgD5oSvW9fH9rXtX29b1-z6qQPnHfw_3nYwVOqNk6Qf4f-t-knGGrE9Q
CitedBy_id	crossref_primary_10_1007_s11042_022_13412_y crossref_primary_10_1007_s11042_022_13566_9 crossref_primary_10_1002_1878_0261_13014 crossref_primary_10_1002_jbio_202300174 crossref_primary_10_3390_cancers15153981 crossref_primary_10_3390_diagnostics13071353 crossref_primary_10_1007_s00500_020_05048_7 crossref_primary_10_1038_s41379_021_00987_4 crossref_primary_10_1016_j_compbiomed_2022_105209 crossref_primary_10_1155_2020_6153657
Cites_doi	10.1109/ICASSP.2014.6853873 10.1109/TMI.2015.2458702 10.1016/j.artmed.2015.04.004 10.1007/s10278-013-9622-7 10.1371/journal.pone.0036530 10.1109/ISBI.2012.6235544 10.1016/j.trsl.2015.08.001 10.1016/j.neucom.2016.12.083 10.1109/TMI.2016.2528162 10.1038/nature13385 10.1007/s11263-015-0816-y 10.1007/978-3-642-40763-5_12 10.1136/amiajnl-2012-001540 10.1109/TMI.2015.2482920 10.4103/2153-3539.112694 10.1007/978-3-642-21735-7_7 10.1080/21681163.2015.1135299 10.1200/JCO.2005.05.1748 10.1109/ISBI.2013.6556499
ContentType	Journal Article
Copyright	The Author(s) 2018 Copyright Springer Science & Business Media 2018
Copyright_xml	– notice: The Author(s) 2018 – notice: Copyright Springer Science & Business Media 2018
DBID	C6C AAYXX CITATION CGR CUY CVF ECM EIF NPM K9. 7X8 5PM
DOI	10.1007/s11548-018-1835-2
DatabaseName	Springer Nature OA Free Journals CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed ProQuest Health & Medical Complete (Alumni) MEDLINE - Academic PubMed Central (Full Participant titles)
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) ProQuest Health & Medical Complete (Alumni) MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic ProQuest Health & Medical Complete (Alumni) MEDLINE
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Medicine Computer Science
EISSN	1861-6429
EndPage	1913
ExternalDocumentID	PMC6223755 30159833 10_1007_s11548_018_1835_2
Genre	Journal Article
GrantInformation_xml	– fundername: Japan Society for the Promotion of Science grantid: 15H01123 funderid: http://dx.doi.org/10.13039/501100001691 – fundername: Japan Society for the Promotion of Science grantid: 15H01123 – fundername: ; grantid: 15H01123
GroupedDBID	--- -5E -5G -BR -EM -Y2 -~C .86 .VR 06C 06D 0R~ 0VY 1N0 203 29J 29~ 2J2 2JN 2JY 2KG 2KM 2LR 2VQ 2~H 30V 4.4 406 408 409 40D 40E 53G 5GY 5VS 67Z 6NX 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANXM AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDZT ABECU ABFTD ABFTV ABHLI ABHQN ABIPD ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABOCM ABPLI ABQBU ABQSL ABSXP ABTEG ABTKH ABTMW ABULA ABWNU ABXPI ACAOD ACDTI ACGFS ACHSB ACHXU ACKNC ACMLO ACOKC ACOMO ACPIV ACSNA ACZOJ ADHHG ADHIR ADINQ ADJJI ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETCA AETLH AEVLU AEXYK AFBBN AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHIZS AHKAY AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ AKMHD ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR ARMRJ ASPBG AVWKF AVXWI AXYYD AZFZN B-. BA0 BDATZ BGNMA BSONS C6C CAG COF CS3 CSCUP DNIVK DPUIP EBD EBLON EBS EIOEI EJD EMOBN EN4 ESBYG F5P FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC G-Y G-Z GGCAI GGRSB GJIRD GNWQR GQ6 GQ7 GQ8 GXS H13 HF~ HG5 HG6 HLICF HMJXF HQYDN HRMNR HVGLF HZ~ IHE IJ- IKXTQ IMOTQ IWAJR IXC IXD IXE IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ KDC KOV KPH LLZTM M4Y MA- N2Q N9A NPVJJ NQJWS NU0 O9- O93 O9I O9J OAM P2P P9S PF0 PT4 QOR QOS R89 R9I RNS ROL RPX RSV S16 S1Z S27 S37 S3B SAP SDH SHX SISQX SJYHP SMD SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW SSXJD STPWE SV3 SZ9 SZN T13 TSG TSK TSV TT1 TUC U2A U9L UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WJK WK8 YLTOR Z45 Z7R Z7V Z7X Z82 Z83 Z87 Z88 ZMTXR ZOVNA ~A9 7X7 88E 8FI 8FJ AAYXX ABBRH ABDBE ABFSG ABRTQ ABUWG ACSTC ADHKG ADKFA AEZWR AFDZB AFFHD AFHIU AFKRA AFOHR AGQPQ AHPBZ AHWEU AIXLP ARAPS ATHPR AYFIA BENPR BGLVJ CCPQU CITATION FYUFA HCIFZ HMCUK M1P PHGZM PHGZT PJZUB PPXIY PQGLB PSQYO UKHRP CGR CUY CVF ECM EIF NPM K9. 7X8 5PM
ID	FETCH-LOGICAL-c536t-c39ba33cf01b814c1294e96474f9cba4d6954659e55c0d0c70f44ce0f90b5ed33
IEDL.DBID	RSV
ISICitedReferencesCount	12
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000449775700004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1861-6410 1861-6429
IngestDate	Thu Aug 21 14:04:53 EDT 2025 Sun Nov 09 11:17:28 EST 2025 Tue Oct 07 06:57:55 EDT 2025 Wed Feb 19 02:34:20 EST 2025 Sat Nov 29 01:30:15 EST 2025 Tue Nov 18 22:18:58 EST 2025 Fri Feb 21 02:42:11 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	12
Keywords	Deep learning Autoencoder Independent subspace analysis Lung cancer Computer-aided diagnosis
Language	English
License	Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c536t-c39ba33cf01b814c1294e96474f9cba4d6954659e55c0d0c70f44ce0f90b5ed33
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-7722-055X
OpenAccessLink	https://link.springer.com/10.1007/s11548-018-1835-2
PMID	30159833
PQID	2131272314
PQPubID	2043910
PageCount	9
ParticipantIDs	pubmedcentral_primary_oai_pubmedcentral_nih_gov_6223755 proquest_miscellaneous_2097592473 proquest_journals_2131272314 pubmed_primary_30159833 crossref_citationtrail_10_1007_s11548_018_1835_2 crossref_primary_10_1007_s11548_018_1835_2 springer_journals_10_1007_s11548_018_1835_2
PublicationCentury	2000
PublicationDate	2018-12-01
PublicationDateYYYYMMDD	2018-12-01
PublicationDate_xml	– month: 12 year: 2018 text: 2018-12-01 day: 01
PublicationDecade	2010
PublicationPlace	Cham
PublicationPlace_xml	– name: Cham – name: Germany – name: Heidelberg
PublicationSubtitle	A journal for interdisciplinary research, development and applications of image guided diagnosis and therapy
PublicationTitle	International journal for computer assisted radiology and surgery
PublicationTitleAbbrev	Int J CARS
PublicationTitleAlternate	Int J Comput Assist Radiol Surg
PublicationYear	2018
Publisher	Springer International Publishing Springer Nature B.V
Publisher_xml	– name: Springer International Publishing – name: Springer Nature B.V
References	RothHRLuLLiuJYaoJSeffACherryKKimLSummersRMImproving computer-aided detection using convolutional neural networks and random view aggregationIEEE Trans Med Imaging20163551170118110.1109/TMI.2015.2482920 HayesDNMontiSParmigianiGGilksCBNaokiKBhattacharjeeASocinskiMAPerouCMeyersonMGene expression profiling reveals reproducible human lung adenocarcinoma subtypes in multiple independent patient cohortsJ Clin Oncol20062431507950901:CAS:528:DC%2BD28Xht1Gnur3I10.1200/JCO.2005.05.1748 MasciJonathanMeierUeliCireşanDanSchmidhuberJürgenStacked Convolutional Auto-Encoders for Hierarchical Feature ExtractionLecture Notes in Computer Science2011Berlin, HeidelbergSpringer Berlin Heidelberg5259 The Cancer Genome Atlas Research NetworkComprehensive molecular profiling of lung adenocarcinomaNature201451154355010.1038/nature13385 MalonCCosattoEClassification of mitotic figures with convolutional neural networks and seeded blob featuresJ Pathol Inform20134910.4103/2153-3539.112694 Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision (ECCV 2014), Lecture notes in computer science. Springer, vol 8689, pp 818–833 ClarkKVendtBSmithKFreymannJKirbyJKoppelPMooreSPhillipsSMaffittDPringleMTarboxLPriorFThe Cncer Imaging Archive (TCIA): maintaining and operating a public information repositoryJ Digit Imaging201326601045105710.1007/s10278-013-9622-7 Le Q, Han J, Gray J, Spellman P, Borowsky A, Parvin B (2012) Learning invariant features of tumor signatures. In: 2012 9th IEEE international symposium on biomedical imaging (ISBI), pp 302–305 ChangHangNayakNanditaSpellmanPaul T.ParvinBahramCharacterization of Tissue Histopathology via Predictive Sparse Decomposition and Spatial Pyramid MatchingAdvanced Information Systems Engineering2013Berlin, HeidelbergSpringer Berlin Heidelberg919810.1007/978-3-642-40763-5_12 KothariSPhanJHStokesTHWangMDPathology imaging informatics for quantitative analysis of whole-slide imagesJ Am Med Inform Assoc20132061099110810.1136/amiajnl-2012-001540 Nayak N, Chang H, Borowsky A, Spellman P, Parvin B (2013) Classification of tumor histopathology via sparse feature learning. In: 2013 IEEE 10th international symposium on biomedical imaging, pp 410–413 Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado G S, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Mane D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viegas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zhe X (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 ArevaloJCruz-RoaAAriasVRomeroEGonzálezFAAn unsupervised feature learning framework for basal cell carcinoma image analysisArtif Intell Med201364213114510.1016/j.artmed.2015.04.004 ShinHCRothHRGaoMLuLXuZNoguesIYaoJMolluraDSummersRMDeep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learningIEEE Trans Med Imaging20163551285129810.1109/TMI.2016.2528162 Xu Y, Mo T, Feng Q, Zhong P, Lai M, Chang EIC (2014) Deep learning of feature representation with multiple instance learning for medical image analysis. In: 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 1626–1630 HayesDLeeCRobertsPBellMBThorneLSchallheimJBernardPFunkhouserBSubtypes of lung adenocarcinoma derived from gene expression patterns are recapitulated using a tissue microarray system and immunohistochemistryCancer Res2007679188188 ChengXZhangLZhengYDeep similarity learning for multimodal medical imagesComput Methods Biomech Biomed Eng Imaging Vis20186324825210.1080/21681163.2015.1135299 WilkersonMDYinXWalterVZhaoNCabanskiCRHaywardMCMillerCRSocinskiMAParsonsAMThorneLBHaithcockBEVeeramachaneniNKFunkhouserWKRandellSHBernardPSPerouCMHayesDNDifferential pathogenesis of lung adenocarcinoma subtypes involving sequence mutations, copy number, chromosomal instability, and methylationPLoS ONE201275e365301:CAS:528:DC%2BC38Xns1Ghu70%3D10.1371/journal.pone.0036530 ChangJTHLeeYMHuangRSThe impact of the Cancer Genome Atlas on lung cancerTransl Res201516665685851:CAS:528:DC%2BC2MXhsVeqtbbP10.1016/j.trsl.2015.08.001 XuJXiangLLiuQGilmoreHWuJTangJMadabhushiAStacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology imagesIEEE Trans Med Imaging201635111913010.1109/TMI.2015.2458702 FurushoYKuboTIkedaKRoles of pre-training in deep neural networks from information theoretical perspectiveNeurocomputing2017248767910.1016/j.neucom.2016.12.083 RussakovskyODengJSuHKrauseJSatheeshSMaSHuangZKarpathyAKhoslaABernsteinMBergACFei-FeiLImageNet large scale visual recognition challengeComput Sci2015115321125210.1007/s11263-015-0816-y Y Furusho (1835_CR7) 2017; 248 1835_CR11 1835_CR22 Jonathan Masci (1835_CR13) 2011 C Malon (1835_CR12) 2013; 4 MD Wilkerson (1835_CR19) 2012; 7 S Kothari (1835_CR10) 2013; 20 1835_CR20 X Cheng (1835_CR5) 2018; 6 The Cancer Genome Atlas Research Network (1835_CR18) 2014; 511 O Russakovsky (1835_CR16) 2015; 115 J Arevalo (1835_CR2) 2013; 64 1835_CR14 Hang Chang (1835_CR3) 2013 K Clark (1835_CR6) 2013; 26 D Hayes (1835_CR8) 2007; 67 DN Hayes (1835_CR9) 2006; 24 HR Roth (1835_CR15) 2016; 35 J Xu (1835_CR21) 2016; 35 1835_CR1 HC Shin (1835_CR17) 2016; 35 JTH Chang (1835_CR4) 2015; 166
References_xml	– reference: WilkersonMDYinXWalterVZhaoNCabanskiCRHaywardMCMillerCRSocinskiMAParsonsAMThorneLBHaithcockBEVeeramachaneniNKFunkhouserWKRandellSHBernardPSPerouCMHayesDNDifferential pathogenesis of lung adenocarcinoma subtypes involving sequence mutations, copy number, chromosomal instability, and methylationPLoS ONE201275e365301:CAS:528:DC%2BC38Xns1Ghu70%3D10.1371/journal.pone.0036530 – reference: Xu Y, Mo T, Feng Q, Zhong P, Lai M, Chang EIC (2014) Deep learning of feature representation with multiple instance learning for medical image analysis. In: 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 1626–1630 – reference: KothariSPhanJHStokesTHWangMDPathology imaging informatics for quantitative analysis of whole-slide imagesJ Am Med Inform Assoc20132061099110810.1136/amiajnl-2012-001540 – reference: MasciJonathanMeierUeliCireşanDanSchmidhuberJürgenStacked Convolutional Auto-Encoders for Hierarchical Feature ExtractionLecture Notes in Computer Science2011Berlin, HeidelbergSpringer Berlin Heidelberg5259 – reference: ShinHCRothHRGaoMLuLXuZNoguesIYaoJMolluraDSummersRMDeep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learningIEEE Trans Med Imaging20163551285129810.1109/TMI.2016.2528162 – reference: ChengXZhangLZhengYDeep similarity learning for multimodal medical imagesComput Methods Biomech Biomed Eng Imaging Vis20186324825210.1080/21681163.2015.1135299 – reference: HayesDNMontiSParmigianiGGilksCBNaokiKBhattacharjeeASocinskiMAPerouCMeyersonMGene expression profiling reveals reproducible human lung adenocarcinoma subtypes in multiple independent patient cohortsJ Clin Oncol20062431507950901:CAS:528:DC%2BD28Xht1Gnur3I10.1200/JCO.2005.05.1748 – reference: MalonCCosattoEClassification of mitotic figures with convolutional neural networks and seeded blob featuresJ Pathol Inform20134910.4103/2153-3539.112694 – reference: ChangHangNayakNanditaSpellmanPaul T.ParvinBahramCharacterization of Tissue Histopathology via Predictive Sparse Decomposition and Spatial Pyramid MatchingAdvanced Information Systems Engineering2013Berlin, HeidelbergSpringer Berlin Heidelberg919810.1007/978-3-642-40763-5_12 – reference: FurushoYKuboTIkedaKRoles of pre-training in deep neural networks from information theoretical perspectiveNeurocomputing2017248767910.1016/j.neucom.2016.12.083 – reference: Nayak N, Chang H, Borowsky A, Spellman P, Parvin B (2013) Classification of tumor histopathology via sparse feature learning. In: 2013 IEEE 10th international symposium on biomedical imaging, pp 410–413 – reference: The Cancer Genome Atlas Research NetworkComprehensive molecular profiling of lung adenocarcinomaNature201451154355010.1038/nature13385 – reference: RothHRLuLLiuJYaoJSeffACherryKKimLSummersRMImproving computer-aided detection using convolutional neural networks and random view aggregationIEEE Trans Med Imaging20163551170118110.1109/TMI.2015.2482920 – reference: ClarkKVendtBSmithKFreymannJKirbyJKoppelPMooreSPhillipsSMaffittDPringleMTarboxLPriorFThe Cncer Imaging Archive (TCIA): maintaining and operating a public information repositoryJ Digit Imaging201326601045105710.1007/s10278-013-9622-7 – reference: Le Q, Han J, Gray J, Spellman P, Borowsky A, Parvin B (2012) Learning invariant features of tumor signatures. In: 2012 9th IEEE international symposium on biomedical imaging (ISBI), pp 302–305 – reference: HayesDLeeCRobertsPBellMBThorneLSchallheimJBernardPFunkhouserBSubtypes of lung adenocarcinoma derived from gene expression patterns are recapitulated using a tissue microarray system and immunohistochemistryCancer Res2007679188188 – reference: ArevaloJCruz-RoaAAriasVRomeroEGonzálezFAAn unsupervised feature learning framework for basal cell carcinoma image analysisArtif Intell Med201364213114510.1016/j.artmed.2015.04.004 – reference: ChangJTHLeeYMHuangRSThe impact of the Cancer Genome Atlas on lung cancerTransl Res201516665685851:CAS:528:DC%2BC2MXhsVeqtbbP10.1016/j.trsl.2015.08.001 – reference: RussakovskyODengJSuHKrauseJSatheeshSMaSHuangZKarpathyAKhoslaABernsteinMBergACFei-FeiLImageNet large scale visual recognition challengeComput Sci2015115321125210.1007/s11263-015-0816-y – reference: Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado G S, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Mane D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viegas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zhe X (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 – reference: XuJXiangLLiuQGilmoreHWuJTangJMadabhushiAStacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology imagesIEEE Trans Med Imaging201635111913010.1109/TMI.2015.2458702 – reference: Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision (ECCV 2014), Lecture notes in computer science. Springer, vol 8689, pp 818–833 – ident: 1835_CR1 – ident: 1835_CR20 doi: 10.1109/ICASSP.2014.6853873 – volume: 35 start-page: 119 issue: 1 year: 2016 ident: 1835_CR21 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2015.2458702 – volume: 64 start-page: 131 issue: 2 year: 2013 ident: 1835_CR2 publication-title: Artif Intell Med doi: 10.1016/j.artmed.2015.04.004 – volume: 26 start-page: 1045 issue: 60 year: 2013 ident: 1835_CR6 publication-title: J Digit Imaging doi: 10.1007/s10278-013-9622-7 – volume: 7 start-page: e36530 issue: 5 year: 2012 ident: 1835_CR19 publication-title: PLoS ONE doi: 10.1371/journal.pone.0036530 – ident: 1835_CR11 doi: 10.1109/ISBI.2012.6235544 – volume: 166 start-page: 568 issue: 6 year: 2015 ident: 1835_CR4 publication-title: Transl Res doi: 10.1016/j.trsl.2015.08.001 – volume: 248 start-page: 76 year: 2017 ident: 1835_CR7 publication-title: Neurocomputing doi: 10.1016/j.neucom.2016.12.083 – volume: 35 start-page: 1285 issue: 5 year: 2016 ident: 1835_CR17 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2016.2528162 – volume: 67 start-page: 188 issue: 9 year: 2007 ident: 1835_CR8 publication-title: Cancer Res – volume: 511 start-page: 543 year: 2014 ident: 1835_CR18 publication-title: Nature doi: 10.1038/nature13385 – volume: 115 start-page: 211 issue: 3 year: 2015 ident: 1835_CR16 publication-title: Comput Sci doi: 10.1007/s11263-015-0816-y – start-page: 91 volume-title: Advanced Information Systems Engineering year: 2013 ident: 1835_CR3 doi: 10.1007/978-3-642-40763-5_12 – volume: 20 start-page: 1099 issue: 6 year: 2013 ident: 1835_CR10 publication-title: J Am Med Inform Assoc doi: 10.1136/amiajnl-2012-001540 – volume: 35 start-page: 1170 issue: 5 year: 2016 ident: 1835_CR15 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2015.2482920 – volume: 4 start-page: 9 year: 2013 ident: 1835_CR12 publication-title: J Pathol Inform doi: 10.4103/2153-3539.112694 – start-page: 52 volume-title: Lecture Notes in Computer Science year: 2011 ident: 1835_CR13 doi: 10.1007/978-3-642-21735-7_7 – volume: 6 start-page: 248 issue: 3 year: 2018 ident: 1835_CR5 publication-title: Comput Methods Biomech Biomed Eng Imaging Vis doi: 10.1080/21681163.2015.1135299 – volume: 24 start-page: 5079 issue: 31 year: 2006 ident: 1835_CR9 publication-title: J Clin Oncol doi: 10.1200/JCO.2005.05.1748 – ident: 1835_CR14 doi: 10.1109/ISBI.2013.6556499 – ident: 1835_CR22
SSID	ssj0045735
Score	2.240696
Snippet	Purpose Convolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we... Convolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we... PurposeConvolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we...
SourceID	pubmedcentral proquest pubmed crossref springer
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	1905
SubjectTerms	Adenocarcinoma of Lung - classification Adenocarcinoma of Lung - diagnosis Adenocarcinoma of Lung - genetics Artificial neural networks Biopsy Classification Computer Imaging Computer Science Entropy (Information theory) Feature extraction Feature recognition Health Informatics Humans Image analysis Image classification Image Processing, Computer-Assisted - methods Imaging Medicine Medicine & Public Health Neural networks Neural Networks (Computer) Object recognition Original Original Article Pattern recognition Pattern Recognition and Graphics Radiology Surgery Transcriptome Tumors Vision
Title	Classification of lung adenocarcinoma transcriptome subtypes from pathological images using deep convolutional networks
URI	https://link.springer.com/article/10.1007/s11548-018-1835-2 https://www.ncbi.nlm.nih.gov/pubmed/30159833 https://www.proquest.com/docview/2131272314 https://www.proquest.com/docview/2097592473 https://pubmed.ncbi.nlm.nih.gov/PMC6223755
Volume	13
WOSCitedRecordID	wos000449775700004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAVX databaseName: SpringerLINK customDbUrl: eissn: 1861-6429 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0045735 issn: 1861-6410 databaseCode: RSV dateStart: 20060301 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3db9MwED_BQGgvFAbbwkZlJJ5AkZzYjp1HhDbtYUyIj6lvUeI4rNKaTE26_fvcuUmqMkCCZ1_axLn73c-5L4C3VDupKpsj-nEXykqhSZmS7MpHuazQPnp-ea4vLsxsln7u67jbIdt9CEl6pN4UuxG7xqMvnnqQNoSIu4_Q2xma1_Dl6-UAv1JpP1UzMkkUJjIaQ5m_-4ltZ3SPYd5PlPwlWuqd0Onkv27_GTztOSf7sFaS5_DA1XswGeY5sN689-DJpz7Q_gLu_LBMSiPyb441FbtGWGA5whR6vyVKNYucdeTpPO40C8faVUFfdFtGNSuMZh0PyMrmC8StllGW_Q9WOnfDKN29V3tcr9fZ6O1L-H568u3jWdjPaAitEkkXWpEWuRC24lFhImmRPkhH1a2ySm2RyzJJadx66pSyvORW80pK63iV8kK5Uoh92Kmb2h0Cw-0xuopLJJxGupgXWgtboBhySKmLJAA-vKzM9g3MaY7GdbZpvUx7nOEeZ7THWRzAu_GSm3X3jr8JHw8akPWG3GZxJFBrkQTLAN6My2iCFFfJa9esUIanWuE5VosADtYKM_4b4qdKjcAVvaVKowC1995eqedXvs13gsxNKxXA-0GhNrf1x4d49U_SR7Abe42k9Jxj2OmWK_caHtvbbt4up_BQz8zUW9dPrvkfeA
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT9wwEB5VULVcoKUUQmnrSj0VRXJiO06OqAKBuqyqliJuUeI4dCU2QZtd-PvMeJOsFgoSPXvysmc-f868AL5S7qQqTYbox60vS4UmFRdkV87LZYR23vPzgR4O44uL5Gebx9100e6dS9Ih9SLZjdg1Hn3x1IO0wUfcXaUHUcH8X7_PO_iVSruumkEcBX4kg96V-a9bLG9GDxjmw0DJe95StwkdbfzX67-B9ZZzsoO5kryFF7bahI2unwNrzXsTXp22jvZ3cOuaZVIYkVs5VpfsCmGBZQhTuPtNUKoeZ2xKO53DnXpsWTPL6Y9uwyhnhVGv4w5Z2WiMuNUwirK_ZIW114zC3Vu1x_FqHo3ebMGfo8Oz78d-26PBN0pEU9-IJM-EMCUP8jiQBumDtJTdKsvE5JksooTarSdWKcMLbjQvpTSWlwnPlS2EeA8rVV3ZHWA4PbEuwwIJZyxtyHOthclRDDmk1HnkAe8WKzVtAXPqo3GVLkov0xynOMcpzXEaevCtv-R6Xr3jKeG9TgPS1pCbNAwEai2SYOnBl34YTZD8Klll6xnK8EQrPMdq4cH2XGH6pyF-qiQWOKKXVKkXoPLeyyPV6K8r8x0hc9NKebDfKdTitR79iN1nSX-G18dnp4N0cDL88QHWQqedFKqzByvTycx-hJfmZjpqJp-cjd0BaQQhdA
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB6hgioutJRXoAUjcQJFdWI7To6IdgWirCoBVW9R4thlpW6y2mTh7zPjJLtaCkiIsycve-bz58wL4BXlTipnCkQ_bkPpFJpUWpFdeS-XEdp7zy_O9HSaXl5m50Of03aMdh9dkn1OA1VpqrvjReWON4lvxLTxGIwnIKQQIWLwbUlx9HRc_3wxQrFU2nfYjNIkChMUGN2av7vF9sZ0g23eDJr8xXPqN6TJ3n9_yj7cG7goe9srz324ZesD2Bv7PLDB7A9g99PggH8AP3wTTQov8ivKGseuES5YgfCFu-ISpZp5wTraAT0eNXPL2lVJf3pbRrksjHogj4jLZnPEs5ZR9P0Vq6xdMAqDH8wBx-s-Sr19CF8np1_evQ-H3g2hUSLpQiOyshDCOB6VaSQN0gppKetVusyUhaySjNqwZ1YpwytuNHdSGstdxktlKyEewU7d1PYJMJyeVLu4QiKaShvzUmthShRDbil1mQTAx4XLzVDYnPprXOebksw0xznOcU5znMcBvF5fsuirevxN-HDUhnww8DaPI4HajORYBvByPYymSf6WorbNCmV4phWeb7UI4HGvPOunIa6qLBU4orfUai1AZb-3R-rZN1_-O0FGp5UK4M2oXJvX-uNHPP0n6Rewe34yyc8-TD8-g7uxV06K4DmEnW65skdwx3zvZu3yuTe3nzsHKlg
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Classification+of+lung+adenocarcinoma+transcriptome+subtypes+from+pathological+images+using+deep+convolutional+networks&rft.jtitle=International+journal+for+computer+assisted+radiology+and+surgery&rft.au=Antonio%2C+Victor+Andrew+A&rft.au=Ono%2C+Naoaki&rft.au=Saito%2C+Akira&rft.au=Sato%2C+Tetsuo&rft.date=2018-12-01&rft.pub=Springer+Nature+B.V&rft.issn=1861-6410&rft.eissn=1861-6429&rft.volume=13&rft.issue=12&rft.spage=1905&rft.epage=1913&rft_id=info:doi/10.1007%2Fs11548-018-1835-2&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1861-6410&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1861-6410&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1861-6410&client=summon