Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer: a retrospective multicentre cohort study

Background - Response to immunotherapy in gastric cancer is associated with microsatellite instability (or mismatch repair deficiency) and Epstein-Barr virus (EBV) positivity. We therefore aimed to develop and validate deep learning-based classifiers to detect microsatellite instability and EBV stat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Muti, Hannah Sophie (VerfasserIn) , Heij, Lara Rosaline (VerfasserIn) , Keller, Gisela (VerfasserIn) , Kohlruss, Meike (VerfasserIn) , Langer, Rupert (VerfasserIn) , Dislich, Bastian (VerfasserIn) , Cheong, Jae-Ho (VerfasserIn) , Kim, Young-Woo (VerfasserIn) , Kim, Hyunki (VerfasserIn) , Kook, Myeong-Cherl (VerfasserIn) , Cunningham, David (VerfasserIn) , Allum, William H (VerfasserIn) , Langley, Ruth E (VerfasserIn) , Nankivell, Matthew G (VerfasserIn) , Quirke, Philip (VerfasserIn) , Hayden, Jeremy D (VerfasserIn) , West, Nicholas P (VerfasserIn) , Irvine, Andrew J (VerfasserIn) , Yoshikawa, Takaki (VerfasserIn) , Oshima, Takashi (VerfasserIn) , Huss, Ralf (VerfasserIn) , Grosser, Bianca (VerfasserIn) , Roviello, Franco (VerfasserIn) , d'Ignazio, Alessia (VerfasserIn) , Quaas, Alexander (VerfasserIn) , Alakus, Hakan (VerfasserIn) , Tan, Xiuxiang (VerfasserIn) , Pearson, Alexander T (VerfasserIn) , Luedde, Tom (VerfasserIn) , Ebert, Matthias (VerfasserIn) , Jäger, Dirk (VerfasserIn) , Trautwein, Christian (VerfasserIn) , Gaisa, Nadine (VerfasserIn) , Grabsch, Heike I (VerfasserIn) , Kather, Jakob Nikolas (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 17 August 2021
In: The lancet. Digital health
Year: 2021, Jahrgang: 3, Heft: 10, Pages: e654-e664
ISSN:2589-7500
DOI:10.1016/S2589-7500(21)00133-3
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1016/S2589-7500(21)00133-3
Verlag, lizenzpflichtig, Volltext: https://www.sciencedirect.com/science/article/pii/S2589750021001333
Volltext
Verfasserangaben:Hannah Sophie Muti, Lara Rosaline Heij, Gisela Keller, Meike Kohlruss, Rupert Langer, Bastian Dislich, Jae-Ho Cheong, Young-Woo Kim, Hyunki Kim, Myeong-Cherl Kook, David Cunningham, William H. Allum, Ruth E. Langley, Matthew G. Nankivell, Philip Quirke, Jeremy D. Hayden, Nicholas P. West, Andrew J. Irvine, Takaki Yoshikawa, Takashi Oshima, Ralf Huss, Bianca Grosser, Franco Roviello, Alessia d'Ignazio, Alexander Quaas, Hakan Alakus, Xiuxiang Tan, Alexander T. Pearson, Tom Luedde, Matthias P. Ebert, Dirk Jäger, Christian Trautwein, Nadine Therese Gaisa, Heike I. Grabsch, Jakob Nikolas Kather

MARC

LEADER 00000caa a2200000 c 4500
001 1779610491
003 DE-627
005 20220820083020.0
007 cr uuu---uuuuu
008 211126s2021 xx |||||o 00| ||eng c
024 7 |a 10.1016/S2589-7500(21)00133-3  |2 doi 
035 |a (DE-627)1779610491 
035 |a (DE-599)KXP1779610491 
035 |a (OCoLC)1341434442 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Muti, Hannah Sophie  |e VerfasserIn  |0 (DE-588)1246552256  |0 (DE-627)1779610890  |4 aut 
245 1 0 |a Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer  |b a retrospective multicentre cohort study  |c Hannah Sophie Muti, Lara Rosaline Heij, Gisela Keller, Meike Kohlruss, Rupert Langer, Bastian Dislich, Jae-Ho Cheong, Young-Woo Kim, Hyunki Kim, Myeong-Cherl Kook, David Cunningham, William H. Allum, Ruth E. Langley, Matthew G. Nankivell, Philip Quirke, Jeremy D. Hayden, Nicholas P. West, Andrew J. Irvine, Takaki Yoshikawa, Takashi Oshima, Ralf Huss, Bianca Grosser, Franco Roviello, Alessia d'Ignazio, Alexander Quaas, Hakan Alakus, Xiuxiang Tan, Alexander T. Pearson, Tom Luedde, Matthias P. Ebert, Dirk Jäger, Christian Trautwein, Nadine Therese Gaisa, Heike I. Grabsch, Jakob Nikolas Kather 
264 1 |c 17 August 2021 
300 |a 11 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 26.11.2021 
520 |a Background - Response to immunotherapy in gastric cancer is associated with microsatellite instability (or mismatch repair deficiency) and Epstein-Barr virus (EBV) positivity. We therefore aimed to develop and validate deep learning-based classifiers to detect microsatellite instability and EBV status from routine histology slides. - Methods - In this retrospective, multicentre study, we collected tissue samples from ten cohorts of patients with gastric cancer from seven countries (South Korea, Switzerland, Japan, Italy, Germany, the UK and the USA). We trained a deep learning-based classifier to detect microsatellite instability and EBV positivity from digitised, haematoxylin and eosin stained resection slides without annotating tumour containing regions. The performance of the classifier was assessed by within-cohort cross-validation in all ten cohorts and by external validation, for which we split the cohorts into a five-cohort training dataset and a five-cohort test dataset. We measured the area under the receiver operating curve (AUROC) for detection of microsatellite instability and EBV status. Microsatellite instability and EBV status were determined to be detectable if the lower bound of the 95% CI for the AUROC was above 0·5. - Findings - Across the ten cohorts, our analysis included 2823 patients with known microsatellite instability status and 2685 patients with known EBV status. In the within-cohort cross-validation, the deep learning-based classifier could detect microsatellite instability status in nine of ten cohorts, with AUROCs ranging from 0·597 (95% CI 0·522-0·737) to 0·836 (0·795-0·880) and EBV status in five of eight cohorts, with AUROCs ranging from 0·819 (0·752-0·841) to 0·897 (0·513-0·966). Training a classifier on the pooled training dataset and testing it on the five remaining cohorts resulted in high classification performance with AUROCs ranging from 0·723 (95% CI 0·676-0·794) to 0·863 (0·747-0·969) for detection of microsatellite instability and from 0·672 (0·403-0·989) to 0·859 (0·823-0·919) for detection of EBV status. - Interpretation - Classifiers became increasingly robust when trained on pooled cohorts. After prospective validation, this deep learning-based tissue classification system could be used as an inexpensive predictive biomarker for immunotherapy in gastric cancer. - Funding - German Cancer Aid and German Federal Ministry of Health. 
700 1 |a Heij, Lara Rosaline  |e VerfasserIn  |4 aut 
700 1 |a Keller, Gisela  |e VerfasserIn  |4 aut 
700 1 |a Kohlruss, Meike  |e VerfasserIn  |4 aut 
700 1 |a Langer, Rupert  |e VerfasserIn  |4 aut 
700 1 |a Dislich, Bastian  |e VerfasserIn  |4 aut 
700 1 |a Cheong, Jae-Ho  |e VerfasserIn  |4 aut 
700 1 |a Kim, Young-Woo  |e VerfasserIn  |4 aut 
700 1 |a Kim, Hyunki  |e VerfasserIn  |4 aut 
700 1 |a Kook, Myeong-Cherl  |e VerfasserIn  |4 aut 
700 1 |a Cunningham, David  |e VerfasserIn  |4 aut 
700 1 |a Allum, William H  |e VerfasserIn  |4 aut 
700 1 |a Langley, Ruth E  |e VerfasserIn  |4 aut 
700 1 |a Nankivell, Matthew G  |e VerfasserIn  |4 aut 
700 1 |a Quirke, Philip  |e VerfasserIn  |4 aut 
700 1 |a Hayden, Jeremy D  |e VerfasserIn  |4 aut 
700 1 |a West, Nicholas P  |e VerfasserIn  |4 aut 
700 1 |a Irvine, Andrew J  |e VerfasserIn  |4 aut 
700 1 |a Yoshikawa, Takaki  |e VerfasserIn  |4 aut 
700 1 |a Oshima, Takashi  |e VerfasserIn  |4 aut 
700 1 |a Huss, Ralf  |e VerfasserIn  |4 aut 
700 1 |a Grosser, Bianca  |e VerfasserIn  |4 aut 
700 1 |a Roviello, Franco  |e VerfasserIn  |4 aut 
700 1 |a d'Ignazio, Alessia  |e VerfasserIn  |4 aut 
700 1 |a Quaas, Alexander  |e VerfasserIn  |4 aut 
700 1 |a Alakus, Hakan  |e VerfasserIn  |4 aut 
700 1 |a Tan, Xiuxiang  |e VerfasserIn  |4 aut 
700 1 |a Pearson, Alexander T  |e VerfasserIn  |4 aut 
700 1 |a Luedde, Tom  |e VerfasserIn  |4 aut 
700 1 |a Ebert, Matthias  |d 1968-  |e VerfasserIn  |0 (DE-588)1030133522  |0 (DE-627)734827083  |0 (DE-576)377938432  |4 aut 
700 1 |a Jäger, Dirk  |d 1964-  |e VerfasserIn  |0 (DE-588)1032507535  |0 (DE-627)738505323  |0 (DE-576)380074125  |4 aut 
700 1 |a Trautwein, Christian  |d 1940-  |e VerfasserIn  |0 (DE-588)130954128  |0 (DE-627)507254333  |0 (DE-576)298406969  |4 aut 
700 1 |a Gaisa, Nadine  |d 1978-  |e VerfasserIn  |0 (DE-588)130814229  |0 (DE-627)506011534  |0 (DE-576)298354942  |4 aut 
700 1 |a Grabsch, Heike I  |e VerfasserIn  |4 aut 
700 1 |a Kather, Jakob Nikolas  |d 1989-  |e VerfasserIn  |0 (DE-588)1064064914  |0 (DE-627)812897587  |0 (DE-576)423589091  |4 aut 
773 0 8 |i Enthalten in  |t The lancet. Digital health  |d London : The Lancet, 2019  |g 3(2021), 10, Seite e654-e664  |h Online-Ressource  |w (DE-627)1665782404  |w (DE-600)2972368-1  |x 2589-7500  |7 nnas  |a Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer a retrospective multicentre cohort study 
773 1 8 |g volume:3  |g year:2021  |g number:10  |g pages:e654-e664  |g extent:11  |a Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer a retrospective multicentre cohort study 
856 4 0 |u https://doi.org/10.1016/S2589-7500(21)00133-3  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u https://www.sciencedirect.com/science/article/pii/S2589750021001333  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20211126 
993 |a Article 
994 |a 2021 
998 |g 1064064914  |a Kather, Jakob Nikolas  |m 1064064914:Kather, Jakob Nikolas  |d 910000  |d 910100  |e 910000PK1064064914  |e 910100PK1064064914  |k 0/910000/  |k 1/910000/910100/  |p 35  |y j 
998 |g 1032507535  |a Jäger, Dirk  |m 1032507535:Jäger, Dirk  |d 910000  |e 910000PJ1032507535  |k 0/910000/  |p 31 
998 |g 1030133522  |a Ebert, Matthias  |m 1030133522:Ebert, Matthias  |d 60000  |d 61100  |e 60000PE1030133522  |e 61100PE1030133522  |k 0/60000/  |k 1/60000/61100/  |p 30 
999 |a KXP-PPN1779610491  |e 4008306412 
BIB |a Y 
SER |a journal 
JSO |a {"type":{"bibl":"article-journal","media":"Online-Ressource"},"language":["eng"],"note":["Gesehen am 26.11.2021"],"title":[{"subtitle":"a retrospective multicentre cohort study","title_sort":"Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer","title":"Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer"}],"origin":[{"dateIssuedDisp":"17 August 2021","dateIssuedKey":"2021"}],"person":[{"role":"aut","given":"Hannah Sophie","family":"Muti","display":"Muti, Hannah Sophie"},{"family":"Heij","given":"Lara Rosaline","role":"aut","display":"Heij, Lara Rosaline"},{"role":"aut","given":"Gisela","family":"Keller","display":"Keller, Gisela"},{"display":"Kohlruss, Meike","role":"aut","given":"Meike","family":"Kohlruss"},{"display":"Langer, Rupert","given":"Rupert","role":"aut","family":"Langer"},{"display":"Dislich, Bastian","role":"aut","given":"Bastian","family":"Dislich"},{"display":"Cheong, Jae-Ho","role":"aut","given":"Jae-Ho","family":"Cheong"},{"family":"Kim","given":"Young-Woo","role":"aut","display":"Kim, Young-Woo"},{"display":"Kim, Hyunki","role":"aut","given":"Hyunki","family":"Kim"},{"family":"Kook","given":"Myeong-Cherl","role":"aut","display":"Kook, Myeong-Cherl"},{"given":"David","role":"aut","family":"Cunningham","display":"Cunningham, David"},{"display":"Allum, William H","family":"Allum","role":"aut","given":"William H"},{"given":"Ruth E","role":"aut","family":"Langley","display":"Langley, Ruth E"},{"family":"Nankivell","given":"Matthew G","role":"aut","display":"Nankivell, Matthew G"},{"family":"Quirke","given":"Philip","role":"aut","display":"Quirke, Philip"},{"family":"Hayden","role":"aut","given":"Jeremy D","display":"Hayden, Jeremy D"},{"given":"Nicholas P","role":"aut","family":"West","display":"West, Nicholas P"},{"role":"aut","given":"Andrew J","family":"Irvine","display":"Irvine, Andrew J"},{"display":"Yoshikawa, Takaki","role":"aut","given":"Takaki","family":"Yoshikawa"},{"role":"aut","given":"Takashi","family":"Oshima","display":"Oshima, Takashi"},{"role":"aut","given":"Ralf","family":"Huss","display":"Huss, Ralf"},{"given":"Bianca","role":"aut","family":"Grosser","display":"Grosser, Bianca"},{"role":"aut","given":"Franco","family":"Roviello","display":"Roviello, Franco"},{"display":"d'Ignazio, Alessia","family":"d'Ignazio","given":"Alessia","role":"aut"},{"display":"Quaas, Alexander","given":"Alexander","role":"aut","family":"Quaas"},{"role":"aut","given":"Hakan","family":"Alakus","display":"Alakus, Hakan"},{"role":"aut","given":"Xiuxiang","family":"Tan","display":"Tan, Xiuxiang"},{"family":"Pearson","role":"aut","given":"Alexander T","display":"Pearson, Alexander T"},{"given":"Tom","role":"aut","family":"Luedde","display":"Luedde, Tom"},{"display":"Ebert, Matthias","given":"Matthias","role":"aut","family":"Ebert"},{"display":"Jäger, Dirk","role":"aut","given":"Dirk","family":"Jäger"},{"display":"Trautwein, Christian","given":"Christian","role":"aut","family":"Trautwein"},{"family":"Gaisa","role":"aut","given":"Nadine","display":"Gaisa, Nadine"},{"role":"aut","given":"Heike I","family":"Grabsch","display":"Grabsch, Heike I"},{"display":"Kather, Jakob Nikolas","role":"aut","given":"Jakob Nikolas","family":"Kather"}],"relHost":[{"language":["eng"],"type":{"bibl":"periodical","media":"Online-Ressource"},"id":{"zdb":["2972368-1"],"eki":["1665782404"],"issn":["2589-7500"]},"part":{"extent":"11","text":"3(2021), 10, Seite e654-e664","issue":"10","pages":"e654-e664","volume":"3","year":"2021"},"title":[{"title_sort":"lancet","title":"The lancet","partname":"Digital health"}],"origin":[{"dateIssuedDisp":"[2019]-","publisherPlace":"London","publisher":"The Lancet"}],"pubHistory":["Volume 1, issue 1 (May 2019)-"],"disp":"Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer a retrospective multicentre cohort studyThe lancet. Digital health","physDesc":[{"extent":"Online-Ressource"}],"recId":"1665782404"}],"physDesc":[{"extent":"11 S."}],"recId":"1779610491","id":{"doi":["10.1016/S2589-7500(21)00133-3"],"eki":["1779610491"]},"name":{"displayForm":["Hannah Sophie Muti, Lara Rosaline Heij, Gisela Keller, Meike Kohlruss, Rupert Langer, Bastian Dislich, Jae-Ho Cheong, Young-Woo Kim, Hyunki Kim, Myeong-Cherl Kook, David Cunningham, William H. Allum, Ruth E. Langley, Matthew G. Nankivell, Philip Quirke, Jeremy D. Hayden, Nicholas P. West, Andrew J. Irvine, Takaki Yoshikawa, Takashi Oshima, Ralf Huss, Bianca Grosser, Franco Roviello, Alessia d'Ignazio, Alexander Quaas, Hakan Alakus, Xiuxiang Tan, Alexander T. Pearson, Tom Luedde, Matthias P. Ebert, Dirk Jäger, Christian Trautwein, Nadine Therese Gaisa, Heike I. Grabsch, Jakob Nikolas Kather"]}} 
SRT |a MUTIHANNAHDEVELOPMEN1720