Augmented Intelligence Dermatology: Deep Neural Networks Empower Medical Professionals in Diagnosing Skin Cancer and Predicting Treatment Options for 134 Skin Disorders

Although deep learning algorithms have demonstrated expert-level performance, previous efforts were mostly binary classifications of limited disorders. We trained an algorithm with 220,680 images of 174 disorders and validated it using Edinburgh (1,300 images; 10 disorders) and SNU datasets (2,201 i...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Journal of investigative dermatology Ročník 140; číslo 9; s. 1753
Hlavní autoři:	Han, Seung Seog, Park, Ilwoo, Eun Chang, Sung, Lim, Woohyung, Kim, Myoung Shin, Park, Gyeong Hun, Chae, Je Byeong, Huh, Chang Hun, Na, Jung-Im
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States 01.09.2020
Témata:	Adolescent Adult Aged Anti-Bacterial Agents - therapeutic use Antifungal Agents - therapeutic use Antiviral Agents - therapeutic use Clinical Competence - statistics & numerical data Datasets as Topic Deep Learning Dermatologists - statistics & numerical data Dermatology - methods Dermoscopy - methods Drug Therapy, Computer-Assisted Feasibility Studies Female Glucocorticoids - therapeutic use Humans Image Interpretation, Computer-Assisted Internship and Residency - statistics & numerical data Male Middle Aged Photography - methods ROC Curve Skin - diagnostic imaging Skin Diseases - diagnosis Skin Diseases - drug therapy Skin Diseases - microbiology Skin Neoplasms - diagnosis Young Adult
ISSN:	1523-1747, 1523-1747
On-line přístup:	Zjistit podrobnosti o přístupu
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Although deep learning algorithms have demonstrated expert-level performance, previous efforts were mostly binary classifications of limited disorders. We trained an algorithm with 220,680 images of 174 disorders and validated it using Edinburgh (1,300 images; 10 disorders) and SNU datasets (2,201 images; 134 disorders). The algorithm could accurately predict malignancy, suggest primary treatment options, render multi-class classification among 134 disorders, and improve the performance of medical professionals. The area under the curves for malignancy detection were 0.928 ± 0.002 (Edinburgh) and 0.937 ± 0.004 (SNU). The area under the curves of primary treatment suggestion (SNU) were 0.828 ± 0.012, 0.885 ± 0.006, 0.885 ± 0.006, and 0.918 ± 0.006 for steroids, antibiotics, antivirals, and antifungals, respectively. For multi-class classification, the mean top-1 and top-5 accuracies were 56.7 ± 1.6% and 92.0 ± 1.1% (Edinburgh) and 44.8 ± 1.2% and 78.1 ± 0.3% (SNU), respectively. With the assistance of our algorithm, the sensitivity and specificity of 47 clinicians (21 dermatologists and 26 dermatology residents) for malignancy prediction (SNU; 240 images) were improved by 12.1% (P < 0.0001) and 1.1% (P < 0.0001), respectively. The malignancy prediction sensitivity of 23 non-medical professionals was significantly increased by 83.8% (P < 0.0001). The top-1 and top-3 accuracies of four doctors in the multi-class classification of 134 diseases (SNU; 2,201 images) were increased by 7.0% (P = 0.045) and 10.1% (P = 0.0020), respectively. The results suggest that our algorithm may serve as augmented intelligence that can empower medical professionals in diagnostic dermatology.
AbstractList	Although deep learning algorithms have demonstrated expert-level performance, previous efforts were mostly binary classifications of limited disorders. We trained an algorithm with 220,680 images of 174 disorders and validated it using Edinburgh (1,300 images; 10 disorders) and SNU datasets (2,201 images; 134 disorders). The algorithm could accurately predict malignancy, suggest primary treatment options, render multi-class classification among 134 disorders, and improve the performance of medical professionals. The area under the curves for malignancy detection were 0.928 ± 0.002 (Edinburgh) and 0.937 ± 0.004 (SNU). The area under the curves of primary treatment suggestion (SNU) were 0.828 ± 0.012, 0.885 ± 0.006, 0.885 ± 0.006, and 0.918 ± 0.006 for steroids, antibiotics, antivirals, and antifungals, respectively. For multi-class classification, the mean top-1 and top-5 accuracies were 56.7 ± 1.6% and 92.0 ± 1.1% (Edinburgh) and 44.8 ± 1.2% and 78.1 ± 0.3% (SNU), respectively. With the assistance of our algorithm, the sensitivity and specificity of 47 clinicians (21 dermatologists and 26 dermatology residents) for malignancy prediction (SNU; 240 images) were improved by 12.1% (P < 0.0001) and 1.1% (P < 0.0001), respectively. The malignancy prediction sensitivity of 23 non-medical professionals was significantly increased by 83.8% (P < 0.0001). The top-1 and top-3 accuracies of four doctors in the multi-class classification of 134 diseases (SNU; 2,201 images) were increased by 7.0% (P = 0.045) and 10.1% (P = 0.0020), respectively. The results suggest that our algorithm may serve as augmented intelligence that can empower medical professionals in diagnostic dermatology. Although deep learning algorithms have demonstrated expert-level performance, previous efforts were mostly binary classifications of limited disorders. We trained an algorithm with 220,680 images of 174 disorders and validated it using Edinburgh (1,300 images; 10 disorders) and SNU datasets (2,201 images; 134 disorders). The algorithm could accurately predict malignancy, suggest primary treatment options, render multi-class classification among 134 disorders, and improve the performance of medical professionals. The area under the curves for malignancy detection were 0.928 ± 0.002 (Edinburgh) and 0.937 ± 0.004 (SNU). The area under the curves of primary treatment suggestion (SNU) were 0.828 ± 0.012, 0.885 ± 0.006, 0.885 ± 0.006, and 0.918 ± 0.006 for steroids, antibiotics, antivirals, and antifungals, respectively. For multi-class classification, the mean top-1 and top-5 accuracies were 56.7 ± 1.6% and 92.0 ± 1.1% (Edinburgh) and 44.8 ± 1.2% and 78.1 ± 0.3% (SNU), respectively. With the assistance of our algorithm, the sensitivity and specificity of 47 clinicians (21 dermatologists and 26 dermatology residents) for malignancy prediction (SNU; 240 images) were improved by 12.1% (P < 0.0001) and 1.1% (P < 0.0001), respectively. The malignancy prediction sensitivity of 23 non-medical professionals was significantly increased by 83.8% (P < 0.0001). The top-1 and top-3 accuracies of four doctors in the multi-class classification of 134 diseases (SNU; 2,201 images) were increased by 7.0% (P = 0.045) and 10.1% (P = 0.0020), respectively. The results suggest that our algorithm may serve as augmented intelligence that can empower medical professionals in diagnostic dermatology.Although deep learning algorithms have demonstrated expert-level performance, previous efforts were mostly binary classifications of limited disorders. We trained an algorithm with 220,680 images of 174 disorders and validated it using Edinburgh (1,300 images; 10 disorders) and SNU datasets (2,201 images; 134 disorders). The algorithm could accurately predict malignancy, suggest primary treatment options, render multi-class classification among 134 disorders, and improve the performance of medical professionals. The area under the curves for malignancy detection were 0.928 ± 0.002 (Edinburgh) and 0.937 ± 0.004 (SNU). The area under the curves of primary treatment suggestion (SNU) were 0.828 ± 0.012, 0.885 ± 0.006, 0.885 ± 0.006, and 0.918 ± 0.006 for steroids, antibiotics, antivirals, and antifungals, respectively. For multi-class classification, the mean top-1 and top-5 accuracies were 56.7 ± 1.6% and 92.0 ± 1.1% (Edinburgh) and 44.8 ± 1.2% and 78.1 ± 0.3% (SNU), respectively. With the assistance of our algorithm, the sensitivity and specificity of 47 clinicians (21 dermatologists and 26 dermatology residents) for malignancy prediction (SNU; 240 images) were improved by 12.1% (P < 0.0001) and 1.1% (P < 0.0001), respectively. The malignancy prediction sensitivity of 23 non-medical professionals was significantly increased by 83.8% (P < 0.0001). The top-1 and top-3 accuracies of four doctors in the multi-class classification of 134 diseases (SNU; 2,201 images) were increased by 7.0% (P = 0.045) and 10.1% (P = 0.0020), respectively. The results suggest that our algorithm may serve as augmented intelligence that can empower medical professionals in diagnostic dermatology.
Author	Park, Ilwoo Eun Chang, Sung Park, Gyeong Hun Han, Seung Seog Na, Jung-Im Lim, Woohyung Chae, Je Byeong Huh, Chang Hun Kim, Myoung Shin
Author_xml	– sequence: 1 givenname: Seung Seog surname: Han fullname: Han, Seung Seog organization: I Dermatology Clinic, Seoul, Korea – sequence: 2 givenname: Ilwoo surname: Park fullname: Park, Ilwoo organization: Department of Radiology, Chonnam National University Medical School and Hospital, Gwangju, Korea – sequence: 3 givenname: Sung surname: Eun Chang fullname: Eun Chang, Sung organization: Department of Dermatology, Asan Medical Center, Ulsan University College of Medicine, Seoul, Korea – sequence: 4 givenname: Woohyung surname: Lim fullname: Lim, Woohyung organization: LG Sciencepark, Seoul, Korea – sequence: 5 givenname: Myoung Shin surname: Kim fullname: Kim, Myoung Shin organization: Department of Dermatology, Sanggye Paik Hospital, Inje University College of Medicine, Seoul, Korea – sequence: 6 givenname: Gyeong Hun surname: Park fullname: Park, Gyeong Hun organization: Department of Dermatology, Dongtan Sacred Heart Hospital, Hallym University College of Medicine, Dongtan, Korea – sequence: 7 givenname: Je Byeong surname: Chae fullname: Chae, Je Byeong organization: Department of Dermatology, Seoul National University Bundang Hospital, Seongnam, Korea – sequence: 8 givenname: Chang Hun surname: Huh fullname: Huh, Chang Hun organization: Department of Dermatology, Seoul National University Bundang Hospital, Seongnam, Korea – sequence: 9 givenname: Jung-Im surname: Na fullname: Na, Jung-Im email: jina1@snu.ac.kr organization: Department of Dermatology, Seoul National University Bundang Hospital, Seongnam, Korea. Electronic address: jina1@snu.ac.kr
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/32243882$$D View this record in MEDLINE/PubMed
BookMark	eNpNUMlKBDEQDaK4f4AXydHLjFm604k3mXEDN1DPQyapaTJ2J23Sjfg3nv0Mv8yMCwhFVT1evUfxdtC6Dx4QOqBkTAkVx8vx0tkxI4yMCc2l1tA2LRkf0aqo1v_tW2gnpSXJmqKUm2iLM1ZwKdk2-jgd6hZ8DxZf5d40rgZvAE8htroPTajfTjKADt_CEHWTR_8a4nPCZ20XXiHiG7DOZOI-hgWk5ILXTcLO46nTtQ_J-Ro_PGc80dk4Yu3t5_t9XKn6FfcYQferF_Bd12d1wosQMeXFt-rzfepSiBZi2kMbi2wN-79zFz2dnz1OLkfXdxdXk9PrkeEl70eVKiwIKihjCqCSyghTGjKnVlApFQcBpQLFS1pxUVhlFZkXQkgwhlFu5mwXHf34djG8DJD6WeuSydFoD2FIM8alYFJyovLp4e_pMG_BzrroWh3fZn_5si-gAoMb
CitedBy_id	crossref_primary_10_1111_ics_12786 crossref_primary_10_1111_jdv_18541 crossref_primary_10_1038_s41598_022_20632_7 crossref_primary_10_1111_srt_13153 crossref_primary_10_1016_j_jid_2023_09_289 crossref_primary_10_3390_bioengineering11080758 crossref_primary_10_1109_ACCESS_2021_3054403 crossref_primary_10_1016_j_smhl_2025_100540 crossref_primary_10_1111_ijd_17981 crossref_primary_10_3390_jpm12111859 crossref_primary_10_1007_s00403_022_02492_3 crossref_primary_10_1186_s12909_023_04698_z crossref_primary_10_3389_fmed_2023_1114362 crossref_primary_10_3389_fmed_2022_946937 crossref_primary_10_1007_s42600_024_00392_1 crossref_primary_10_1016_j_media_2022_102647 crossref_primary_10_1002_ima_22880 crossref_primary_10_1016_j_ejca_2022_04_015 crossref_primary_10_1111_jdv_18814 crossref_primary_10_1007_s42979_024_03072_0 crossref_primary_10_1016_j_det_2025_05_004 crossref_primary_10_1111_srt_13037 crossref_primary_10_2196_44030 crossref_primary_10_3390_diagnostics12051233 crossref_primary_10_3390_diagnostics11030451 crossref_primary_10_1089_pop_2024_0222 crossref_primary_10_1002_qute_202500234 crossref_primary_10_1080_1206212X_2024_2385923 crossref_primary_10_17116_klinderma202423031246 crossref_primary_10_1371_journal_pone_0260895 crossref_primary_10_3390_cosmetics10050120 crossref_primary_10_7759_cureus_65122 crossref_primary_10_3389_fmed_2023_1241484 crossref_primary_10_1007_s13671_024_00440_0 crossref_primary_10_1007_s00330_022_09165_9 crossref_primary_10_3390_ai5040144 crossref_primary_10_1001_jamadermatol_2021_1685 crossref_primary_10_1109_ACCESS_2023_3296792 crossref_primary_10_1001_jamanetworkopen_2021_7249 crossref_primary_10_3390_diagnostics15070939 crossref_primary_10_1007_s40257_023_00777_5 crossref_primary_10_3390_diagnostics13152531 crossref_primary_10_1016_j_ejca_2022_07_002 crossref_primary_10_1038_s41746_020_00380_6 crossref_primary_10_1016_j_compbiomed_2020_103980 crossref_primary_10_1111_jdv_20849 crossref_primary_10_2196_43832 crossref_primary_10_38124_ijisrt_24jul1574 crossref_primary_10_1016_j_ejca_2021_06_049 crossref_primary_10_1111_jdv_18354 crossref_primary_10_3389_fmed_2024_1331895 crossref_primary_10_3390_jimaging9020035 crossref_primary_10_1016_j_ejca_2021_06_047 crossref_primary_10_1016_j_health_2023_100259 crossref_primary_10_1109_JBHI_2023_3237875 crossref_primary_10_1001_jamanetworkopen_2021_1276 crossref_primary_10_32604_cmc_2024_052548 crossref_primary_10_1111_jdv_16979 crossref_primary_10_1186_s12880_023_01078_3 crossref_primary_10_1111_srt_13257 crossref_primary_10_1001_jamadermatol_2023_5550 crossref_primary_10_1016_j_jid_2022_03_019 crossref_primary_10_1111_jocd_16640 crossref_primary_10_3389_fmed_2021_670300 crossref_primary_10_1177_00031348241269430 crossref_primary_10_1111_ajd_13690 crossref_primary_10_1001_jamadermatol_2023_3521 crossref_primary_10_1007_s00105_020_04657_5 crossref_primary_10_3390_app15147856 crossref_primary_10_1177_11769351251349891 crossref_primary_10_1111_jdv_20319 crossref_primary_10_3390_cancers15041183 crossref_primary_10_1038_s41746_024_01031_w crossref_primary_10_1016_j_xjidi_2025_100404 crossref_primary_10_1159_000530225 crossref_primary_10_1016_j_compbiomed_2024_108742 crossref_primary_10_1001_jamadermatol_2021_3129 crossref_primary_10_1007_s11831_023_09910_3 crossref_primary_10_1016_j_cie_2023_109754 crossref_primary_10_3389_fmed_2020_00318 crossref_primary_10_1016_j_jid_2021_12_033 crossref_primary_10_1287_mnsc_2023_01845 crossref_primary_10_1007_s40009_023_01319_7 crossref_primary_10_1007_s43621_024_00575_x crossref_primary_10_1097_JD9_0000000000000404 crossref_primary_10_1007_s10489_024_05520_z crossref_primary_10_1016_j_jid_2022_02_003 crossref_primary_10_3390_diagnostics10100803 crossref_primary_10_1007_s11831_025_10275_y crossref_primary_10_1038_s41746_024_01103_x crossref_primary_10_1016_j_jid_2020_08_024 crossref_primary_10_3390_jcm14092873 crossref_primary_10_1145_3555634 crossref_primary_10_1016_j_ejca_2020_11_020 crossref_primary_10_1007_s11912_023_01407_3 crossref_primary_10_1186_s12911_021_01596_6 crossref_primary_10_3389_fmed_2024_1420152 crossref_primary_10_1038_s41598_021_87064_7 crossref_primary_10_3390_jcm11226826 crossref_primary_10_1111_srt_13690 crossref_primary_10_1038_s41551_023_01160_9 crossref_primary_10_2196_39143 crossref_primary_10_1007_s11517_021_02321_1 crossref_primary_10_3390_s25020394 crossref_primary_10_1186_s12909_025_07321_5 crossref_primary_10_2196_20708 crossref_primary_10_1177_20552076231205736 crossref_primary_10_1111_pde_15298 crossref_primary_10_3390_life13112123 crossref_primary_10_1080_14737167_2023_2279107 crossref_primary_10_1097_SCS_0000000000011498 crossref_primary_10_1016_j_seminoncol_2025_152349 crossref_primary_10_3390_a15110438 crossref_primary_10_1016_j_jid_2020_06_040 crossref_primary_10_1007_s13555_022_00833_8 crossref_primary_10_1038_s41591_020_0942_0 crossref_primary_10_7717_peerj_cs_2530 crossref_primary_10_1038_s41467_024_50043_3 crossref_primary_10_1038_s41591_023_02225_7
ContentType	Journal Article
Copyright	Copyright © 2020 The Authors. Published by Elsevier Inc. All rights reserved.
Copyright_xml	– notice: Copyright © 2020 The Authors. Published by Elsevier Inc. All rights reserved.
DBID	CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1016/j.jid.2020.01.019
DatabaseName	Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic
DatabaseTitle	MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic
DatabaseTitleList	MEDLINE MEDLINE - Academic
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	no_fulltext_linktorsrc
Discipline	Medicine
EISSN	1523-1747
ExternalDocumentID	32243882
Genre	Research Support, Non-U.S. Gov't Journal Article
GroupedDBID	--- --K .55 .GJ 0R~ 1B1 29K 2WC 36B 3O- 4.4 457 53G 5GY 5RE 5VS 7X7 88E 8AO 8FI 8FJ 8R4 8R5 AAEDW AAFWJ AALRI AAXUO AAYWO ABAWZ ABJNI ABLJU ABMAC ABUWG ACGFO ACGFS ACPRK ACVFH ADBBV ADCNI ADEZE ADFRT ADVLN AENEX AEUPX AEXQZ AFEBI AFETI AFFNX AFJKZ AFKRA AFPUW AFTJW AGCQF AGHFR AHMBA AI. AIGII AITUG AKBMS AKRWK AKYEP ALIPV ALMA_UNASSIGNED_HOLDINGS AMRAJ APXCP BAWUL BENPR BFHJK BPHCQ BVXVI CAG CCPQU CGR COF CS3 CUY CVF D-I DIK E3Z EBS ECM EFKBS EIF EJD F5P FDB FRP FYUFA GX1 HMCUK HZ~ IH2 IHE J5H JSO KQ8 L7B LH4 LW6 M1P M41 MVM NPM NQ- O9- OK1 P2P PHGZM PHGZT PJZUB PPXIY PQQKQ PROAC PSQYO Q2X R9- RIG RNS ROL RPZ SSZ TR2 UKHRP VH1 W2D X7M Y6R YFH YOC YUY ZGI 7X8
ID	FETCH-LOGICAL-c353t-794de6161229ee789c6c5c0b1d618893e6e59e93517364d9d90b4668ecc213cb2
IEDL.DBID	7X8
ISICitedReferencesCount	136
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000560065800015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1523-1747
IngestDate	Sun Sep 28 03:10:16 EDT 2025 Mon Jul 21 05:57:50 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	9
Language	English
License	Copyright © 2020 The Authors. Published by Elsevier Inc. All rights reserved.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c353t-794de6161229ee789c6c5c0b1d618893e6e59e93517364d9d90b4668ecc213cb2
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
PMID	32243882
PQID	2386288309
PQPubID	23479
ParticipantIDs	proquest_miscellaneous_2386288309 pubmed_primary_32243882
PublicationCentury	2000
PublicationDate	2020-09-00 20200901
PublicationDateYYYYMMDD	2020-09-01
PublicationDate_xml	– month: 09 year: 2020 text: 2020-09-00
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	Journal of investigative dermatology
PublicationTitleAlternate	J Invest Dermatol
PublicationYear	2020
SSID	ssj0016458
Score	2.6583884
Snippet	Although deep learning algorithms have demonstrated expert-level performance, previous efforts were mostly binary classifications of limited disorders. We...
SourceID	proquest pubmed
SourceType	Aggregation Database Index Database
StartPage	1753
SubjectTerms	Adolescent Adult Aged Anti-Bacterial Agents - therapeutic use Antifungal Agents - therapeutic use Antiviral Agents - therapeutic use Clinical Competence - statistics & numerical data Datasets as Topic Deep Learning Dermatologists - statistics & numerical data Dermatology - methods Dermoscopy - methods Drug Therapy, Computer-Assisted Feasibility Studies Female Glucocorticoids - therapeutic use Humans Image Interpretation, Computer-Assisted Internship and Residency - statistics & numerical data Male Middle Aged Photography - methods ROC Curve Skin - diagnostic imaging Skin Diseases - diagnosis Skin Diseases - drug therapy Skin Diseases - microbiology Skin Neoplasms - diagnosis Young Adult
Title	Augmented Intelligence Dermatology: Deep Neural Networks Empower Medical Professionals in Diagnosing Skin Cancer and Predicting Treatment Options for 134 Skin Disorders
URI	https://www.ncbi.nlm.nih.gov/pubmed/32243882 https://www.proquest.com/docview/2386288309
Volume	140
WOSCitedRecordID	wos000560065800015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings	1
isFullTextHit
isPrint
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEA6-EC--H-uLEbwW2yZNEy-y-EAPrntQ2NvSJqmsYHfdquA_8mc6k7boSQQvhUJTSjOZ-ZL5-D7GjlWqDVdOBVlObUasqUFWpLhVKQTCfyOV1YU3m0h7PTUY6H5z4FY1tMo2J_pEbceGzshPsLR4Z9xQn01eAnKNou5qY6Exy-Y5QhmK6nTw3UWQwvtzYokiGU6Rtl1Nz-96GpFQaBx61c7oF4TpK83Vyn-_cZUtNxgTunVQrLEZV66zxdumi77BPrtvj16L08LND0VOuKAs7f1sP07xxk2ApDvwTb2aK17B5fOEXNWgae9A_4ewRwWjEi5q5h7WQyBbLzinoJpCVlp8lgYRyxruW3Y73NWcGkDoDBEX9aBWEbTaZA9Xl_fn10Hj2BAYnvDXABe3dRJBZBxr51KljTSJCfPIykghMnLSJdppnkQpl8Jqq8NcSKkwjuKImzzeYnPluHQ7DJRLiH0rsqxwwsZ5xlOFaKnIQ53hxjrvsKN2Doa4IqjNkZVu_FYNv2ehw7briRxOaumOIaYvwXFTsfuH0XtsieKjJpTts_kC_6Q7YAvm_XVUTQ99qOG117_9ApY8344
linkProvider	ProQuest
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=Augmented+Intelligence+Dermatology%3A+Deep+Neural+Networks+Empower+Medical+Professionals+in+Diagnosing+Skin+Cancer+and%C2%A0Predicting+Treatment+Options+for+134+Skin%C2%A0Disorders&rft.jtitle=Journal+of+investigative+dermatology&rft.au=Han%2C+Seung+Seog&rft.au=Park%2C+Ilwoo&rft.au=Eun+Chang%2C+Sung&rft.au=Lim%2C+Woohyung&rft.date=2020-09-01&rft.eissn=1523-1747&rft.volume=140&rft.issue=9&rft.spage=1753&rft_id=info:doi/10.1016%2Fj.jid.2020.01.019&rft_id=info%3Apmid%2F32243882&rft_id=info%3Apmid%2F32243882&rft.externalDocID=32243882
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1523-1747&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1523-1747&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1523-1747&client=summon