Breast cancer histology images classification: Training from scratch or transfer learning?
We demonstrated the ability of transfer learning in comparison with the fully-trained network on the histopathological imaging modality by considering three pre-trained networks: VGG16, VGG19, and ResNet50 and analyzed their behavior for magnification independent breast cancer classification. Concur...
Saved in:
| Published in | ICT express Vol. 4; no. 4; pp. 247 - 254 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier
01.12.2018
한국통신학회 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 2405-9595 2405-9595 |
| DOI | 10.1016/j.icte.2018.10.007 |
Cover
Loading…
| Abstract | We demonstrated the ability of transfer learning in comparison with the fully-trained network on the histopathological imaging modality by considering three pre-trained networks: VGG16, VGG19, and ResNet50 and analyzed their behavior for magnification independent breast cancer classification. Concurrently, we examined the effect of training–testing data size on the performance of considered networks. A fine-tuned pre-trained VGG16 with logistic regression classifier yielded the best performance with 92.60% accuracy, 95.65% area under ROC curve (AUC), and 95.95% accuracy precision score (APS) for 90%–10% training–testing data splitting. Layer-wise fine-tuning and different weight initialization schemes can be a future aspect of this study. Keywords: Breast cancer, Histopathological images, Convolutional neural network, Full training, Transfer learning |
|---|---|
| AbstractList | We demonstrated the ability of transfer learning in comparison with the fully-trained network on the histopathological imaging modality by considering three pre-trained networks: VGG16, VGG19, and ResNet50 and analyzed their behavior for magnification independent breast cancer classification. Concurrently, we examined the effect of training–testing data size on the performance of considered networks. A fine-tuned pre-trained VGG16 with logistic regression classifier yielded the best performance with 92.60% accuracy, 95.65% area under ROC curve (AUC), and 95.95% accuracy precision score (APS) for 90%–10% training–testing data splitting. Layer-wise fine-tuning and different weight initialization schemes can be a future aspect of this study. KCI Citation Count: 35 We demonstrated the ability of transfer learning in comparison with the fully-trained network on the histopathological imaging modality by considering three pre-trained networks: VGG16, VGG19, and ResNet50 and analyzed their behavior for magnification independent breast cancer classification. Concurrently, we examined the effect of training–testing data size on the performance of considered networks. A fine-tuned pre-trained VGG16 with logistic regression classifier yielded the best performance with 92.60% accuracy, 95.65% area under ROC curve (AUC), and 95.95% accuracy precision score (APS) for 90%–10% training–testing data splitting. Layer-wise fine-tuning and different weight initialization schemes can be a future aspect of this study. Keywords: Breast cancer, Histopathological images, Convolutional neural network, Full training, Transfer learning |
| Author | Shallu Mehra, Rajesh |
| Author_xml | – sequence: 1 surname: Shallu fullname: Shallu – sequence: 2 givenname: Rajesh surname: Mehra fullname: Mehra, Rajesh |
| BackLink | https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002424232$$DAccess content in National Research Foundation of Korea (NRF) |
| BookMark | eNp9kU9PGzEQxa0KpNKQL8DJ1x4S7N31v14qilqIhFSpChcu1mTWXhyWdWX7wrfHmyCEeuhprOf3ftLM-0JOpjg5Qi44W3PG5eV-HbC4dcO4rsKaMfWJnDUdEysjjDj58P5MljnvGWPcNJwbdUYefiQHuVCECV2ijyGXOMbhhYZnGFymOELOwQeEEuL0jW4ThClMA_UpPtOMCQo-0phoSTBlXxGjgzQ7vp-TUw9jdsu3uSD3v35ur29Xd79vNtdXdytsDS8rYB06NI2XvdKguETsHVNagusQdr7TStZ_qYRzvpUcleuro--NRKV70S7I1yN3St4-YbARwmEO0T4le_Vnu7GtaYTRrHo3R28fYW__prplejkEDkJMg4VUAo7OotSdRL4TToquBb5rUWDP1Y5pbbT3ldUcWZhizsn5dx5ndi7G7u1cjJ2LmbVaTA3pf0IYyuG29YBh_F_0FUZZmMI |
| CitedBy_id | crossref_primary_10_1016_j_sciaf_2023_e01612 crossref_primary_10_1016_j_artmed_2021_102191 crossref_primary_10_3389_frai_2022_733345 crossref_primary_10_1088_2632_2153_ad10cc crossref_primary_10_1155_2022_8904768 crossref_primary_10_1088_1742_6596_1767_1_012042 crossref_primary_10_1109_TCSVT_2023_3295375 crossref_primary_10_1007_s13755_021_00163_7 crossref_primary_10_1016_j_compbiomed_2022_106476 crossref_primary_10_1049_ipr2_12449 crossref_primary_10_2478_fcds_2019_0016 crossref_primary_10_3390_diagnostics10090662 crossref_primary_10_1016_j_mlwa_2021_100198 crossref_primary_10_1007_s11042_022_14276_y crossref_primary_10_1016_j_physa_2019_123592 crossref_primary_10_1515_jisys_2022_0198 crossref_primary_10_1016_j_biosystemseng_2020_03_015 crossref_primary_10_1007_s42803_023_00077_8 crossref_primary_10_1016_j_matpr_2023_10_154 crossref_primary_10_1109_ACCESS_2024_3516535 crossref_primary_10_1371_journal_pone_0283121 crossref_primary_10_1142_S0218488523500204 crossref_primary_10_1155_2022_3041811 crossref_primary_10_1016_j_cmpb_2019_07_003 crossref_primary_10_1016_j_cie_2024_110280 crossref_primary_10_1109_ACCESS_2025_3544923 crossref_primary_10_1007_s11831_022_09776_x crossref_primary_10_1007_s41782_023_00261_4 crossref_primary_10_1055_a_1971_1274 crossref_primary_10_13104_imri_2021_25_4_266 crossref_primary_10_3390_diagnostics13111977 crossref_primary_10_1016_j_jag_2024_104061 crossref_primary_10_1016_j_jksuci_2021_09_003 crossref_primary_10_1145_3492865 crossref_primary_10_3390_cells10040787 crossref_primary_10_1109_ACCESS_2020_2993788 crossref_primary_10_3233_JIFS_189850 crossref_primary_10_1016_j_asoc_2019_105765 crossref_primary_10_1016_j_hmedic_2024_100106 crossref_primary_10_1007_s00500_020_05424_3 crossref_primary_10_1109_ACCESS_2023_3335604 crossref_primary_10_1049_ipr2_12074 crossref_primary_10_1007_s11831_023_09968_z crossref_primary_10_1007_s12652_023_04600_1 crossref_primary_10_1016_j_icte_2021_04_005 crossref_primary_10_1016_j_yamp_2021_07_005 crossref_primary_10_1093_comjnl_bxad127 crossref_primary_10_1016_j_icte_2020_04_009 crossref_primary_10_1016_j_bspc_2023_104775 crossref_primary_10_1007_s11227_023_05742_x crossref_primary_10_3390_diagnostics12051152 crossref_primary_10_1002_cam4_6363 crossref_primary_10_1016_j_imed_2022_05_004 crossref_primary_10_1016_j_eswa_2023_121416 crossref_primary_10_3390_cancers15123075 crossref_primary_10_1016_j_bspc_2020_102192 crossref_primary_10_3233_JIFS_231563 crossref_primary_10_7717_peerj_cs_493 crossref_primary_10_1109_TCBB_2020_2980831 crossref_primary_10_1007_s12065_021_00564_3 crossref_primary_10_3390_diagnostics13101793 crossref_primary_10_1016_j_jksuci_2023_01_017 crossref_primary_10_1007_s10489_021_02425_z crossref_primary_10_1140_epjc_s10052_023_12290_4 crossref_primary_10_1080_14942119_2024_2398943 crossref_primary_10_1007_s11042_021_11409_7 crossref_primary_10_1016_j_compbiomed_2021_104608 crossref_primary_10_1109_ACCESS_2020_3034343 crossref_primary_10_1038_s41598_020_77170_3 crossref_primary_10_1002_ima_22465 crossref_primary_10_1007_s40747_021_00474_y crossref_primary_10_1016_j_imu_2021_100616 crossref_primary_10_1007_s11831_022_09738_3 crossref_primary_10_1016_j_atech_2023_100275 crossref_primary_10_4018_IJIRR_289655 crossref_primary_10_3390_cancers13112764 crossref_primary_10_1016_j_bbe_2021_05_013 crossref_primary_10_1016_j_bbe_2021_07_004 crossref_primary_10_1088_1742_6596_1755_1_012026 crossref_primary_10_1038_s41598_022_22984_6 crossref_primary_10_1109_ACCESS_2024_3514322 crossref_primary_10_3390_bioengineering9080391 crossref_primary_10_1145_3572033 crossref_primary_10_1016_j_health_2023_100207 crossref_primary_10_1007_s00371_021_02153_y crossref_primary_10_1038_s41598_022_20012_1 crossref_primary_10_1007_s00521_022_07648_w crossref_primary_10_16984_saufenbilder_720693 crossref_primary_10_1109_ACCESS_2021_3069937 crossref_primary_10_1155_2021_9025470 crossref_primary_10_1016_j_cviu_2024_104065 crossref_primary_10_1007_s40031_023_00882_3 crossref_primary_10_1186_s13640_024_00658_9 crossref_primary_10_1007_s11042_021_10927_8 crossref_primary_10_2478_acss_2020_0018 crossref_primary_10_3233_JIFS_219254 crossref_primary_10_1007_s11548_022_02826_6 crossref_primary_10_3390_diagnostics11030528 crossref_primary_10_1016_j_jksuci_2021_08_004 crossref_primary_10_1016_j_compbiomed_2024_108910 crossref_primary_10_1007_s10916_020_01689_1 crossref_primary_10_1007_s40846_020_00545_4 crossref_primary_10_1016_j_compbiomed_2020_103954 crossref_primary_10_1007_s10278_019_00307_y crossref_primary_10_1007_s10916_021_01786_9 crossref_primary_10_1016_j_icte_2022_07_007 crossref_primary_10_4018_IJSSMET_2020040102 crossref_primary_10_3390_electronics12030676 crossref_primary_10_1007_s42484_022_00062_4 crossref_primary_10_1007_s42979_022_01275_x crossref_primary_10_1016_j_jobe_2021_102537 crossref_primary_10_3390_cancers14112770 crossref_primary_10_1016_j_artmed_2022_102276 crossref_primary_10_1371_journal_pone_0269826 crossref_primary_10_3390_app10103359 crossref_primary_10_1007_s10278_023_00887_w crossref_primary_10_1016_j_bspc_2023_105382 crossref_primary_10_1109_ACCESS_2021_3056641 crossref_primary_10_1007_s00521_024_10849_0 crossref_primary_10_1016_j_procs_2020_03_340 crossref_primary_10_1002_ima_22399 crossref_primary_10_1007_s00371_019_01768_6 crossref_primary_10_1016_j_ijmedinf_2021_104669 crossref_primary_10_1007_s00521_024_10464_z crossref_primary_10_1016_j_compbiomed_2021_104879 crossref_primary_10_1007_s11042_024_19313_6 crossref_primary_10_1007_s11517_025_03297_y crossref_primary_10_3389_frai_2024_1449329 crossref_primary_10_1038_s41598_025_90288_6 crossref_primary_10_1016_j_icte_2021_11_010 crossref_primary_10_1016_j_jksuci_2021_05_015 crossref_primary_10_1007_s00521_023_09156_x crossref_primary_10_3390_healthcare10010166 crossref_primary_10_1016_j_compbiomed_2022_105636 crossref_primary_10_1016_j_dsp_2022_103400 crossref_primary_10_1016_j_jmir_2019_11_001 crossref_primary_10_3390_diagnostics13172853 crossref_primary_10_1007_s00521_022_07966_z crossref_primary_10_1016_j_ecoinf_2022_101688 crossref_primary_10_1016_j_eswa_2020_114161 crossref_primary_10_1016_j_reth_2025_01_011 crossref_primary_10_1016_j_mlwa_2022_100422 crossref_primary_10_1109_ACCESS_2020_3029881 crossref_primary_10_3390_biology10121347 crossref_primary_10_1145_3648359 crossref_primary_10_3390_info16030227 |
| Cites_doi | 10.1109/CAC.2017.8243510 10.1109/TMI.2016.2528162 10.1109/CVPRW.2014.131 10.1007/978-3-319-24261-3_7 10.1016/j.conbuildmat.2017.09.110 10.1109/TMI.2016.2532122 10.1109/CVPRW.2015.7301382 10.1109/TBME.2015.2496264 10.1038/nature14539 10.1086/301749 10.1109/RBME.2012.2232289 10.1109/TMI.2016.2535865 10.4103/2153-3539.116866 10.1109/TMI.2016.2527619 10.1109/TMI.2016.2535302 10.3322/caac.21395 10.1109/WACV.2017.83 10.1371/journal.pone.0052807 10.1146/annurev-bioeng-071516-044442 10.1109/IJCNN.2016.7727519 10.1109/TMI.2015.2470529 10.3390/a3010044 |
| ContentType | Journal Article |
| DBID | AAYXX CITATION DOA ACYCR |
| DOI | 10.1016/j.icte.2018.10.007 |
| DatabaseName | CrossRef DOAJ Directory of Open Access Journals Korean Citation Index |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2405-9595 |
| EndPage | 254 |
| ExternalDocumentID | oai_kci_go_kr_ARTI_3925980 oai_doaj_org_article_c6846c1b5e6543a1b3c5cd17b08898ff 10_1016_j_icte_2018_10_007 |
| GroupedDBID | 0R~ 457 5VS AAEDW AALRI AAXUO AAYWO AAYXX ABMAC ACGFS ACVFH ADBBV ADCNI ADEZE ADVLN AEUPX AEXQZ AFJKZ AFPUW AFTJW AGHFR AIGII AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ APXCP BCNDV CITATION EBS EJD FDB GROUPED_DOAJ IPNFZ KQ8 M~E O9- OK1 RIG ROL SSZ 0SF 6I. AACTN AAFTH ACYCR NCXOZ |
| ID | FETCH-LOGICAL-c391t-a04cec92f6d78a716ccde0786ae4cabf4876ec9675eef361c7edcdedd96c78d53 |
| IEDL.DBID | DOA |
| ISSN | 2405-9595 |
| IngestDate | Tue Nov 21 21:41:10 EST 2023 Wed Aug 27 01:20:39 EDT 2025 Tue Jul 01 03:49:11 EDT 2025 Thu Apr 24 23:02:16 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c391t-a04cec92f6d78a716ccde0786ae4cabf4876ec9675eef361c7edcdedd96c78d53 |
| OpenAccessLink | https://doaj.org/article/c6846c1b5e6543a1b3c5cd17b08898ff |
| PageCount | 8 |
| ParticipantIDs | nrf_kci_oai_kci_go_kr_ARTI_3925980 doaj_primary_oai_doaj_org_article_c6846c1b5e6543a1b3c5cd17b08898ff crossref_primary_10_1016_j_icte_2018_10_007 crossref_citationtrail_10_1016_j_icte_2018_10_007 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2018-12-00 2018-12-01 2018-12 |
| PublicationDateYYYYMMDD | 2018-12-01 |
| PublicationDate_xml | – month: 12 year: 2018 text: 2018-12-00 |
| PublicationDecade | 2010 |
| PublicationTitle | ICT express |
| PublicationYear | 2018 |
| Publisher | Elsevier 한국통신학회 |
| Publisher_xml | – name: Elsevier – name: 한국통신학회 |
| References | Spanhol (10.1016/j.icte.2018.10.007_b36) 2015; 63 Gopalakrishnan (10.1016/j.icte.2018.10.007_b23) 2017; 157 Loukas (10.1016/j.icte.2018.10.007_b35) 2013 Fleet (10.1016/j.icte.2018.10.007_b7) 2014 10.1016/j.icte.2018.10.007_b14 Azizpour (10.1016/j.icte.2018.10.007_b22) 2014 10.1016/j.icte.2018.10.007_b5 10.1016/j.icte.2018.10.007_b12 He (10.1016/j.icte.2018.10.007_b28) 2015 10.1016/j.icte.2018.10.007_b32 Sellaro (10.1016/j.icte.2018.10.007_b33) 2013; 4 Han (10.1016/j.icte.2018.10.007_b15) 2017 Zheng (10.1016/j.icte.2018.10.007_b6) 2010; 3 10.1016/j.icte.2018.10.007_b18 Shen (10.1016/j.icte.2018.10.007_b9) 2017; 19 Voulodimos (10.1016/j.icte.2018.10.007_b13) 2017; 2018 Peikari (10.1016/j.icte.2018.10.007_b34) 2016; 35 10.1016/j.icte.2018.10.007_b31 10.1016/j.icte.2018.10.007_b30 Hoo-Chang (10.1016/j.icte.2018.10.007_b19) 2016; 35 10.1016/j.icte.2018.10.007_b27 10.1016/j.icte.2018.10.007_b26 10.1016/j.icte.2018.10.007_b24 Anthimopoulos (10.1016/j.icte.2018.10.007_b16) 2016; 35 Keskin (10.1016/j.icte.2018.10.007_b37) 2013; 8 10.1016/j.icte.2018.10.007_b21 Siegel (10.1016/j.icte.2018.10.007_b1) 2017; 67 Kallenberg (10.1016/j.icte.2018.10.007_b3) 2016; 35 Shallu (10.1016/j.icte.2018.10.007_b11) 2017 Aubreville (10.1016/j.icte.2018.10.007_b17) 2017 Tajbakhsh (10.1016/j.icte.2018.10.007_b25) 2016; 35 Ford (10.1016/j.icte.2018.10.007_b2) 1998; 62 10.1016/j.icte.2018.10.007_b29 İrsoy (10.1016/j.icte.2018.10.007_b20) 2018 Tan (10.1016/j.icte.2018.10.007_b8) 2016; 35 LeCun (10.1016/j.icte.2018.10.007_b10) 2015; 521 Ganesan (10.1016/j.icte.2018.10.007_b4) 2012; 6 |
| References_xml | – ident: 10.1016/j.icte.2018.10.007_b29 doi: 10.1109/CAC.2017.8243510 – ident: 10.1016/j.icte.2018.10.007_b5 – volume: 35 start-page: 1285 issue: 5 year: 2016 ident: 10.1016/j.icte.2018.10.007_b19 article-title: Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characterristics and transfer learning publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2016.2528162 – ident: 10.1016/j.icte.2018.10.007_b21 doi: 10.1109/CVPRW.2014.131 – ident: 10.1016/j.icte.2018.10.007_b12 doi: 10.1007/978-3-319-24261-3_7 – volume: 157 start-page: 322 year: 2017 ident: 10.1016/j.icte.2018.10.007_b23 article-title: Deep convolutional neural networks with transfer learning for computer vision-based data-driven pavement distress detection publication-title: Constr. Buil. Mater. doi: 10.1016/j.conbuildmat.2017.09.110 – ident: 10.1016/j.icte.2018.10.007_b31 – volume: 35 start-page: 1322 issue: 5 year: 2016 ident: 10.1016/j.icte.2018.10.007_b3 article-title: Unsupervised deep learning applied to breast density segmentation and mammographic risk scoring publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2016.2532122 – year: 2017 ident: 10.1016/j.icte.2018.10.007_b11 article-title: An insight into the convolutional neural network for the analysis of medical images – ident: 10.1016/j.icte.2018.10.007_b24 doi: 10.1109/CVPRW.2015.7301382 – volume: 63 start-page: 1455 issue: 7 year: 2015 ident: 10.1016/j.icte.2018.10.007_b36 article-title: A dataset for breast cancer histopathological image classification publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2015.2496264 – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.icte.2018.10.007_b10 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – start-page: 1 year: 2017 ident: 10.1016/j.icte.2018.10.007_b17 article-title: Automatic classification of cancerous tissue in laser endo-microscopy images of the oral cavity using deep learning publication-title: Nature, Sci. Rep. – volume: 62 start-page: 676 year: 1998 ident: 10.1016/j.icte.2018.10.007_b2 article-title: Genetic heterogeneity and penetrance analysis of the BRCA1 and BRCA2 genes in breast cancer families publication-title: Am. J. Hum. Genet. doi: 10.1086/301749 – volume: 6 start-page: 77 year: 2012 ident: 10.1016/j.icte.2018.10.007_b4 article-title: Computer-aided breast cancer detection using mammograms: A review publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/RBME.2012.2232289 – ident: 10.1016/j.icte.2018.10.007_b18 doi: 10.1109/TMI.2016.2535865 – volume: 4 year: 2013 ident: 10.1016/j.icte.2018.10.007_b33 article-title: Relationship between magnification and resolution in digital pathology systems publication-title: J. Pathol. Inform. doi: 10.4103/2153-3539.116866 – start-page: 1 year: 2017 ident: 10.1016/j.icte.2018.10.007_b15 article-title: Breast cancer multi-classification from histopathological images with structured deep learning model publication-title: Nature, Sci. Rep. – year: 2018 ident: 10.1016/j.icte.2018.10.007_b20 – year: 2014 ident: 10.1016/j.icte.2018.10.007_b22 – ident: 10.1016/j.icte.2018.10.007_b27 – volume: 35 start-page: 1719 issue: 7 year: 2016 ident: 10.1016/j.icte.2018.10.007_b8 article-title: Association between changes in mammographic image features and risk for near-term breast cancer development publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2016.2527619 – year: 2013 ident: 10.1016/j.icte.2018.10.007_b35 article-title: Breast cancer characterization based on image classification of tissue sections visualized under low magnification – ident: 10.1016/j.icte.2018.10.007_b32 – volume: 2018 start-page: 1 year: 2017 ident: 10.1016/j.icte.2018.10.007_b13 article-title: Deep learning for computer vision: A brief review publication-title: Comput. Intel. Neurosc. – volume: 35 start-page: 1299 issue: 5 year: 2016 ident: 10.1016/j.icte.2018.10.007_b25 article-title: Convolutional neural networks for medical image analysis: Full training or fine tuning? publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2016.2535302 – volume: 67 start-page: 177 issue: 3 year: 2017 ident: 10.1016/j.icte.2018.10.007_b1 article-title: Colorectal cancer statistics, 2017 publication-title: CA Cancer J. Clin. doi: 10.3322/caac.21395 – ident: 10.1016/j.icte.2018.10.007_b26 – year: 2015 ident: 10.1016/j.icte.2018.10.007_b28 – ident: 10.1016/j.icte.2018.10.007_b30 doi: 10.1109/WACV.2017.83 – volume: 8 issue: 1 year: 2013 ident: 10.1016/j.icte.2018.10.007_b37 article-title: Image classification of human carcinoma cells using complex wavelet based covariance descriptors publication-title: PLoS One doi: 10.1371/journal.pone.0052807 – volume: 19 start-page: 221 year: 2017 ident: 10.1016/j.icte.2018.10.007_b9 article-title: Deep learning in medical image analysis publication-title: Annu. Rev. Biomed. Eng. doi: 10.1146/annurev-bioeng-071516-044442 – ident: 10.1016/j.icte.2018.10.007_b14 doi: 10.1109/IJCNN.2016.7727519 – volume: 35 start-page: 1207 issue: 5 year: 2016 ident: 10.1016/j.icte.2018.10.007_b16 article-title: Lung pattern classification for interstitial lung disease using a deep convolutional neural network publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2016.2535865 – volume: 35 start-page: 307 issue: 1 year: 2016 ident: 10.1016/j.icte.2018.10.007_b34 article-title: Triaging diagnostically relevant regions from pathology whole slides of breast cancer: A texture based approach publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2015.2470529 – volume: 3 start-page: 44 issue: 1 year: 2010 ident: 10.1016/j.icte.2018.10.007_b6 article-title: Breast cancer detection with Gabor features from digital mammograms publication-title: Algorithms doi: 10.3390/a3010044 – start-page: 9 year: 2014 ident: 10.1016/j.icte.2018.10.007_b7 article-title: Breast cancer detection using haralick features of images reconstructed from ultra wideband microwave scans publication-title: Transl. Res. Med. Imaging |
| SSID | ssj0001921197 |
| Score | 2.508629 |
| Snippet | We demonstrated the ability of transfer learning in comparison with the fully-trained network on the histopathological imaging modality by considering three... |
| SourceID | nrf doaj crossref |
| SourceType | Open Website Enrichment Source Index Database |
| StartPage | 247 |
| SubjectTerms | 전자/정보통신공학 |
| Title | Breast cancer histology images classification: Training from scratch or transfer learning? |
| URI | https://doaj.org/article/c6846c1b5e6543a1b3c5cd17b08898ff https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002424232 |
| Volume | 4 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| ispartofPNX | ICT Express , 2018, 4(4), , pp.247-254 |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA7iSQ_iE9cXQbxJtbFN2ngRVxQfKAgriJeQTlLdXd2VWv-_M2ld1otevLTQJk34Msyj-TLD2B4oj9G_EpEt0jRKrU0i63wcZTr2qZOJglDr8PZOXT6k14_ycarUF3HCmvTADXCHoNBCgiikp1OQVhQJSHAiK4ifk5claV8cbSqYGjR-C-2PUWU59EgiLbVsT8w05K4-hByZIj8I1K7sh1UKyfvR1oyqcsrWXCyyhdZJ5KfN5JbYjB8ts_mp1IEr7KlLbPKaA61axUPaYPpBzvtvqCE-OJBXTDSggPwx77WlIDidJ-GoK1AFv_BxxevgueIn2voRzyer7OHivHd2GbV1EiJItKgjG6fgQR-VymW5xQAIAOHOcmV9CrYoMSZR-B5DA-_LRAnIvMMWzmkFWY4LssZmR-ORX2fcIsZxKWIbtmTjTBdeaYlK0bm8cFp2mPjGyUCbRJxqWbyab7bYwBC2hrClZ4hth-1P-rw3KTR-bd0l-CctKf11eIBCYVqhMH8JRYft4uKZIfRDf7o_j82wMhgkXBl0CaXO443_GGmTzdHkG4LLFputq0-_jW5KXewEicTrzX3-BWM85Uk |
| linkProvider | Directory of Open Access Journals |
| 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=Breast+cancer+histology+images+classification%3A+Training+from+scratch+or+transfer+learning%3F&rft.jtitle=ICT+express&rft.au=Shallu&rft.au=Mehra%2C+Rajesh&rft.date=2018-12-01&rft.issn=2405-9595&rft.eissn=2405-9595&rft.volume=4&rft.issue=4&rft.spage=247&rft.epage=254&rft_id=info:doi/10.1016%2Fj.icte.2018.10.007&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_icte_2018_10_007 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2405-9595&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2405-9595&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2405-9595&client=summon |