Predicting HPV association using deep learning and regular H&E stains allows granular stratification of oropharyngeal cancer patients
Human Papilloma Virus (HPV)-associated oropharyngeal squamous cell cancer (OPSCC) represents an OPSCC subgroup with an overall good prognosis with a rising incidence in Western countries. Multiple lines of evidence suggest that HPV-associated tumors are not a homogeneous tumor entity, underlining th...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
19 Aug 2023
|
| In: |
npj digital medicine
Year: 2023, Volume: 6, Issue: 1, Pages: 1-11 |
| ISSN: | 2398-6352 |
| DOI: | 10.1038/s41746-023-00901-z |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.1038/s41746-023-00901-z Verlag, kostenfrei, Volltext: https://www.nature.com/articles/s41746-023-00901-z 
|
| Author Notes: | Sebastian Klein, Nora Wuerdemann, Imke Demers, Christopher Kopp, Jennifer Quantius, Arthur Charpentier, Yuri Tolkach, Klaus Brinker, Shachi Jenny Sharma, Julie George, Jochen Hess, Fabian Stögbauer, Martin Lacko, Marijn Struijlaart, Mari F.C.M. van den Hout, Steffen Wagner, Claus Wittekindt, Christine Langer, Christoph Arens, Reinhard Buettner, Alexander Quaas, Hans Christian Reinhardt, Ernst-Jan Speel and Jens Peter Klussmann |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1891238892 | ||
| 003 | DE-627 | ||
| 005 | 20250117011205.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240613s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1038/s41746-023-00901-z |2 doi | |
| 035 | |a (DE-627)1891238892 | ||
| 035 | |a (DE-599)KXP1891238892 | ||
| 035 | |a (OCoLC)1475298151 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Klein, Sebastian |d 1982- |e VerfasserIn |0 (DE-588)1123960135 |0 (DE-627)877604606 |0 (DE-576)482183918 |4 aut | |
| 245 | 1 | 0 | |a Predicting HPV association using deep learning and regular H&E stains allows granular stratification of oropharyngeal cancer patients |c Sebastian Klein, Nora Wuerdemann, Imke Demers, Christopher Kopp, Jennifer Quantius, Arthur Charpentier, Yuri Tolkach, Klaus Brinker, Shachi Jenny Sharma, Julie George, Jochen Hess, Fabian Stögbauer, Martin Lacko, Marijn Struijlaart, Mari F.C.M. van den Hout, Steffen Wagner, Claus Wittekindt, Christine Langer, Christoph Arens, Reinhard Buettner, Alexander Quaas, Hans Christian Reinhardt, Ernst-Jan Speel and Jens Peter Klussmann |
| 264 | 1 | |c 19 Aug 2023 | |
| 300 | |b Illustrationen | ||
| 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 13.06.2024 | ||
| 520 | |a Human Papilloma Virus (HPV)-associated oropharyngeal squamous cell cancer (OPSCC) represents an OPSCC subgroup with an overall good prognosis with a rising incidence in Western countries. Multiple lines of evidence suggest that HPV-associated tumors are not a homogeneous tumor entity, underlining the need for accurate prognostic biomarkers. In this retrospective, multi-institutional study involving 906 patients from four centers and one database, we developed a deep learning algorithm (OPSCCnet), to analyze standard H&E stains for the calculation of a patient-level score associated with prognosis, comparing it to combined HPV-DNA and p16-status. When comparing OPSCCnet to HPV-status, the algorithm showed a good overall performance with a mean area under the receiver operator curve (AUROC) = 0.83 (95% CI = 0.77-0.9) for the test cohort (n = 639), which could be increased to AUROC = 0.88 by filtering cases using a fixed threshold on the variance of the probability of the HPV-positive class - a potential surrogate marker of HPV-heterogeneity. OPSCCnet could be used as a screening tool, outperforming gold standard HPV testing (OPSCCnet: five-year survival rate: 96% [95% CI = 90-100%]; HPV testing: five-year survival rate: 80% [95% CI = 71-90%]). This could be confirmed using a multivariate analysis of a three-tier threshold (OPSCCnet: high HR = 0.15 [95% CI = 0.05-0.44], intermediate HR = 0.58 [95% CI = 0.34-0.98] p = 0.043, Cox proportional hazards model, n = 211; HPV testing: HR = 0.29 [95% CI = 0.15-0.54] p < 0.001, Cox proportional hazards model, n = 211). Collectively, our findings indicate that by analyzing standard gigapixel hematoxylin and eosin (H&E) histological whole-slide images, OPSCCnet demonstrated superior performance over p16/HPV-DNA testing in various clinical scenarios, particularly in accurately stratifying these patients. | ||
| 700 | 1 | |a Wuerdemann, Nora |e VerfasserIn |4 aut | |
| 700 | 1 | |a Demers, Imke |e VerfasserIn |4 aut | |
| 700 | 1 | |a Kopp, Christopher |e VerfasserIn |4 aut | |
| 700 | 1 | |a Quantius, Jennifer |e VerfasserIn |4 aut | |
| 700 | 1 | |a Charpentier, Arthur |e VerfasserIn |4 aut | |
| 700 | 1 | |a Tolkach, Yuri |e VerfasserIn |4 aut | |
| 700 | 1 | |a Brinker, Klaus |e VerfasserIn |4 aut | |
| 700 | 1 | |a Sharma, Shachi Jenny |e VerfasserIn |4 aut | |
| 700 | 1 | |a George, Julie |e VerfasserIn |4 aut | |
| 700 | 1 | |a Heß, Jochen |d 1971- |e VerfasserIn |0 (DE-588)121902390 |0 (DE-627)705696057 |0 (DE-576)292983417 |4 aut | |
| 700 | 1 | |8 1\p |a Stögbauer, Fabian |d 1983- |e VerfasserIn |0 (DE-588)140241493 |0 (DE-627)618241841 |0 (DE-576)31658827X |4 aut | |
| 700 | 1 | |a Lacko, Martin |e VerfasserIn |4 aut | |
| 700 | 1 | |a Struijlaart, Marijn |e VerfasserIn |4 aut | |
| 700 | 1 | |a van den Hout, Mari F. C. M. |e VerfasserIn |4 aut | |
| 700 | 1 | |8 2\p |a Wagner, Steffen |e VerfasserIn |0 (DE-588)133263126 |0 (DE-627)539646415 |0 (DE-576)29973420X |4 aut | |
| 700 | 1 | |a Wittekindt, Claus |e VerfasserIn |4 aut | |
| 700 | 1 | |a Langer, Christine |e VerfasserIn |4 aut | |
| 700 | 1 | |8 3\p |a Arens, Christoph |d 1966- |e VerfasserIn |0 (DE-588)1166983145 |0 (DE-627)1030832579 |0 (DE-576)510980015 |4 aut | |
| 700 | 1 | |a Büttner, Reinhard |d 1960- |e VerfasserIn |0 (DE-588)171994825 |0 (DE-627)696891301 |0 (DE-576)132870975 |4 aut | |
| 700 | 1 | |a Quaas, Alexander |d 1972- |e VerfasserIn |0 (DE-588)132015374 |0 (DE-627)516841084 |0 (DE-576)298894319 |4 aut | |
| 700 | 1 | |a Reinhardt, Hans Christian |e VerfasserIn |4 aut | |
| 700 | 1 | |a Speel, Ernst-Jan |e VerfasserIn |4 aut | |
| 700 | 1 | |a Klussmann, Jens Peter |e VerfasserIn |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t npj digital medicine |d [Basingstoke] : Macmillan Publishers Limited, 2016 |g 6(2023), 1, Artikel-ID 152, Seite 1-11 |h Online-Ressource |w (DE-627)1016587104 |w (DE-600)2925182-5 |w (DE-576)501513582 |x 2398-6352 |7 nnas |a Predicting HPV association using deep learning and regular H&E stains allows granular stratification of oropharyngeal cancer patients |
| 773 | 1 | 8 | |g volume:6 |g year:2023 |g number:1 |g elocationid:152 |g pages:1-11 |g extent:11 |a Predicting HPV association using deep learning and regular H&E stains allows granular stratification of oropharyngeal cancer patients |
| 856 | 4 | 0 | |u https://doi.org/10.1038/s41746-023-00901-z |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://www.nature.com/articles/s41746-023-00901-z |x Verlag |z kostenfrei |3 Volltext |
| 883 | |8 1\p |a cgwrk |d 20241001 |q DE-101 |u https://d-nb.info/provenance/plan#cgwrk | ||
| 883 | |8 2\p |a cgwrk |d 20241001 |q DE-101 |u https://d-nb.info/provenance/plan#cgwrk | ||
| 883 | |8 3\p |a cgwrk |d 20241001 |q DE-101 |u https://d-nb.info/provenance/plan#cgwrk | ||
| 951 | |a AR | ||
| 992 | |a 20240613 | ||
| 993 | |a Article | ||
| 994 | |a 2023 | ||
| 998 | |g 121902390 |a Heß, Jochen |m 121902390:Heß, Jochen |d 910000 |d 911000 |d 50000 |e 910000PH121902390 |e 911000PH121902390 |e 50000PH121902390 |k 0/910000/ |k 1/910000/911000/ |k 0/50000/ |p 11 | ||
| 999 | |a KXP-PPN1891238892 |e 4538716634 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"recId":"1891238892","relHost":[{"origin":[{"publisherPlace":"[Basingstoke]","dateIssuedDisp":"[2016]-","publisher":"Macmillan Publishers Limited"}],"note":["Gesehen am 06. September 2019"],"pubHistory":["2016-"],"recId":"1016587104","language":["eng"],"id":{"issn":["2398-6352"],"eki":["1016587104"],"zdb":["2925182-5"]},"type":{"bibl":"periodical","media":"Online-Ressource"},"title":[{"title":"npj digital medicine","title_sort":"npj digital medicine"}],"part":{"issue":"1","extent":"11","volume":"6","text":"6(2023), 1, Artikel-ID 152, Seite 1-11","pages":"1-11","year":"2023"},"disp":"Predicting HPV association using deep learning and regular H&E stains allows granular stratification of oropharyngeal cancer patientsnpj digital medicine","physDesc":[{"extent":"Online-Ressource"}]}],"origin":[{"dateIssuedDisp":"19 Aug 2023","dateIssuedKey":"2023"}],"note":["Gesehen am 13.06.2024"],"title":[{"title":"Predicting HPV association using deep learning and regular H&E stains allows granular stratification of oropharyngeal cancer patients","title_sort":"Predicting HPV association using deep learning and regular H&E stains allows granular stratification of oropharyngeal cancer patients"}],"person":[{"role":"aut","display":"Klein, Sebastian","given":"Sebastian","family":"Klein"},{"family":"Wuerdemann","display":"Wuerdemann, Nora","given":"Nora","role":"aut"},{"family":"Demers","role":"aut","given":"Imke","display":"Demers, Imke"},{"family":"Kopp","role":"aut","given":"Christopher","display":"Kopp, Christopher"},{"given":"Jennifer","display":"Quantius, Jennifer","role":"aut","family":"Quantius"},{"display":"Charpentier, Arthur","given":"Arthur","role":"aut","family":"Charpentier"},{"given":"Yuri","display":"Tolkach, Yuri","role":"aut","family":"Tolkach"},{"family":"Brinker","display":"Brinker, Klaus","given":"Klaus","role":"aut"},{"role":"aut","given":"Shachi Jenny","display":"Sharma, Shachi Jenny","family":"Sharma"},{"family":"George","role":"aut","display":"George, Julie","given":"Julie"},{"role":"aut","given":"Jochen","display":"Heß, Jochen","family":"Heß"},{"family":"Stögbauer","role":"aut","display":"Stögbauer, Fabian","given":"Fabian"},{"family":"Lacko","role":"aut","given":"Martin","display":"Lacko, Martin"},{"role":"aut","given":"Marijn","display":"Struijlaart, Marijn","family":"Struijlaart"},{"display":"van den Hout, Mari F. C. M.","given":"Mari F. C. M.","role":"aut","family":"van den Hout"},{"family":"Wagner","role":"aut","display":"Wagner, Steffen","given":"Steffen"},{"family":"Wittekindt","role":"aut","given":"Claus","display":"Wittekindt, Claus"},{"family":"Langer","given":"Christine","display":"Langer, Christine","role":"aut"},{"family":"Arens","given":"Christoph","display":"Arens, Christoph","role":"aut"},{"family":"Büttner","given":"Reinhard","display":"Büttner, Reinhard","role":"aut"},{"given":"Alexander","display":"Quaas, Alexander","role":"aut","family":"Quaas"},{"family":"Reinhardt","given":"Hans Christian","display":"Reinhardt, Hans Christian","role":"aut"},{"family":"Speel","given":"Ernst-Jan","display":"Speel, Ernst-Jan","role":"aut"},{"family":"Klussmann","given":"Jens Peter","display":"Klussmann, Jens Peter","role":"aut"}],"physDesc":[{"noteIll":"Illustrationen","extent":"11 S."}],"id":{"eki":["1891238892"],"doi":["10.1038/s41746-023-00901-z"]},"name":{"displayForm":["Sebastian Klein, Nora Wuerdemann, Imke Demers, Christopher Kopp, Jennifer Quantius, Arthur Charpentier, Yuri Tolkach, Klaus Brinker, Shachi Jenny Sharma, Julie George, Jochen Hess, Fabian Stögbauer, Martin Lacko, Marijn Struijlaart, Mari F.C.M. van den Hout, Steffen Wagner, Claus Wittekindt, Christine Langer, Christoph Arens, Reinhard Buettner, Alexander Quaas, Hans Christian Reinhardt, Ernst-Jan Speel and Jens Peter Klussmann"]},"language":["eng"],"type":{"bibl":"article-journal","media":"Online-Ressource"}} | ||
| SRT | |a KLEINSEBASPREDICTING1920 | ||