Prediction of homologous recombination deficiency from routine histology with attention-based multiple instance learning in nine different tumor types

Homologous recombination deficiency (HRD) is recognized as a pan-cancer predictive biomarker that potentially indicates who could benefit from treatment with PARP inhibitors (PARPi). Despite its clinical significance, HRD testing is highly complex. Here, we investigated in a proof-of-concept study w...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Löffler, Chiara (VerfasserIn) , El Nahhas, Omar S. M. (VerfasserIn) , Muti, Hannah Sophie (VerfasserIn) , Carrero, Zunamys I. (VerfasserIn) , Seibel, Tobias Julian (VerfasserIn) , van Treeck, Marko (VerfasserIn) , Cifci, Didem (VerfasserIn) , Gustav, Marco (VerfasserIn) , Bretz, Kevin (VerfasserIn) , Gaisa, Nadine (VerfasserIn) , Lehmann, Kjong-Van (VerfasserIn) , Leary, Alexandra (VerfasserIn) , Selenica, Pier (VerfasserIn) , Reis-Filho, Jorge S. (VerfasserIn) , Ortiz-Bruechle, Nadina (VerfasserIn) , Kather, Jakob Nikolas (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 08 October 2024
In: BMC biology
Year: 2024, Jahrgang: 22, Heft: 1, Pages: 1-14
ISSN:1741-7007
DOI:10.1186/s12915-024-02022-9
Online-Zugang:Verlag, kostenfrei, Volltext: https://doi.org/10.1186/s12915-024-02022-9
Verlag, kostenfrei, Volltext: https://bmcbiol.biomedcentral.com/articles/10.1186/s12915-024-02022-9
Volltext
Verfasserangaben:Chiara Maria Lavinia Loeffler, Omar S.M. El Nahhas, Hannah Sophie Muti, Zunamys I. Carrero, Tobias Seibel, Marko van Treeck, Didem Cifci, Marco Gustav, Kevin Bretz, Nadine T. Gaisa, Kjong-Van Lehmann, Alexandra Leary, Pier Selenica, Jorge S. Reis-Filho, Nadina Ortiz-Bruechle and Jakob Nikolas Kather

MARC

LEADER 00000caa a2200000 c 4500
001 1923073524
003 DE-627
005 20250717010451.0
007 cr uuu---uuuuu
008 250416s2024 xx |||||o 00| ||eng c
024 7 |a 10.1186/s12915-024-02022-9  |2 doi 
035 |a (DE-627)1923073524 
035 |a (DE-599)KXP1923073524 
035 |a (OCoLC)1528044741 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 32  |2 sdnb 
100 1 |a Löffler, Chiara  |e VerfasserIn  |0 (DE-588)1254183493  |0 (DE-627)1796796646  |4 aut 
245 1 0 |a Prediction of homologous recombination deficiency from routine histology with attention-based multiple instance learning in nine different tumor types  |c Chiara Maria Lavinia Loeffler, Omar S.M. El Nahhas, Hannah Sophie Muti, Zunamys I. Carrero, Tobias Seibel, Marko van Treeck, Didem Cifci, Marco Gustav, Kevin Bretz, Nadine T. Gaisa, Kjong-Van Lehmann, Alexandra Leary, Pier Selenica, Jorge S. Reis-Filho, Nadina Ortiz-Bruechle and Jakob Nikolas Kather 
264 1 |c 08 October 2024 
300 |b Illustrationen 
300 |a 14 
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 16.04.2025 
520 |a Homologous recombination deficiency (HRD) is recognized as a pan-cancer predictive biomarker that potentially indicates who could benefit from treatment with PARP inhibitors (PARPi). Despite its clinical significance, HRD testing is highly complex. Here, we investigated in a proof-of-concept study whether Deep Learning (DL) can predict HRD status solely based on routine hematoxylin & eosin (H&E) histology images across nine different cancer types. We developed a deep learning pipeline with attention-weighted multiple instance learning (attMIL) to predict HRD status from histology images. As part of our approach, we calculated a genomic scar HRD score by combining loss of heterozygosity (LOH), telomeric allelic imbalance (TAI), and large-scale state transitions (LST) from whole genome sequencing (WGS) data of n = 5209 patients across two independent cohorts. The model’s effectiveness was evaluated using the area under the receiver operating characteristic curve (AUROC), focusing on its accuracy in predicting genomic HRD against a clinically recognized cutoff value. Our study demonstrated the predictability of genomic HRD status in endometrial, pancreatic, and lung cancers reaching cross-validated AUROCs of 0.79, 0.58, and 0.66, respectively. These predictions generalized well to an external cohort, with AUROCs of 0.93, 0.81, and 0.73. Moreover, a breast cancer-trained image-based HRD classifier yielded an AUROC of 0.78 in the internal validation cohort and was able to predict HRD in endometrial, prostate, and pancreatic cancer with AUROCs of 0.87, 0.84, and 0.67, indicating that a shared HRD-like phenotype occurs across these tumor entities. This study establishes that HRD can be directly predicted from H&E slides using attMIL, demonstrating its applicability across nine different tumor types. 
700 1 |a El Nahhas, Omar S. M.  |e VerfasserIn  |0 (DE-588)1341939367  |0 (DE-627)190253512X  |4 aut 
700 1 |a Muti, Hannah Sophie  |e VerfasserIn  |0 (DE-588)1246552256  |0 (DE-627)1779610890  |4 aut 
700 1 |a Carrero, Zunamys I.  |e VerfasserIn  |4 aut 
700 1 |a Seibel, Tobias Julian  |e VerfasserIn  |0 (DE-588)142856657  |0 (DE-627)640547559  |0 (DE-576)333730747  |4 aut 
700 1 |a van Treeck, Marko  |e VerfasserIn  |4 aut 
700 1 |a Cifci, Didem  |e VerfasserIn  |0 (DE-588)1290186758  |0 (DE-627)1845902726  |4 aut 
700 1 |a Gustav, Marco  |e VerfasserIn  |0 (DE-588)134925567X  |0 (DE-627)1909426776  |4 aut 
700 1 |a Bretz, Kevin  |e VerfasserIn  |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 Lehmann, Kjong-Van  |e VerfasserIn  |4 aut 
700 1 |a Leary, Alexandra  |e VerfasserIn  |4 aut 
700 1 |a Selenica, Pier  |e VerfasserIn  |4 aut 
700 1 |a Reis-Filho, Jorge S.  |e VerfasserIn  |4 aut 
700 1 |a Ortiz-Bruechle, Nadina  |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 BMC biology  |d Berlin : Springer, 2003  |g 22(2024), 1, Seite 1-14  |h Online-Ressource  |w (DE-627)377757241  |w (DE-600)2133020-7  |w (DE-576)121896404  |x 1741-7007  |7 nnas  |a Prediction of homologous recombination deficiency from routine histology with attention-based multiple instance learning in nine different tumor types 
773 1 8 |g volume:22  |g year:2024  |g number:1  |g pages:1-14  |g extent:14  |a Prediction of homologous recombination deficiency from routine histology with attention-based multiple instance learning in nine different tumor types 
856 4 0 |u https://doi.org/10.1186/s12915-024-02022-9  |x Verlag  |x Resolving-System  |z kostenfrei  |3 Volltext 
856 4 0 |u https://bmcbiol.biomedcentral.com/articles/10.1186/s12915-024-02022-9  |x Verlag  |z kostenfrei  |3 Volltext 
951 |a AR 
992 |a 20250416 
993 |a Article 
994 |a 2024 
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 16  |y j 
999 |a KXP-PPN1923073524  |e 4706057965 
BIB |a Y 
SER |a journal 
JSO |a {"type":{"bibl":"article-journal","media":"Online-Ressource"},"physDesc":[{"extent":"14 S.","noteIll":"Illustrationen"}],"relHost":[{"pubHistory":["1.2003 -"],"physDesc":[{"extent":"Online-Ressource"}],"title":[{"title":"BMC biology","title_sort":"BMC biology"}],"type":{"bibl":"periodical","media":"Online-Ressource"},"id":{"eki":["377757241"],"issn":["1741-7007"],"zdb":["2133020-7"]},"origin":[{"dateIssuedDisp":"2003-","publisher":"Springer ; BioMed Central","dateIssuedKey":"2003","publisherPlace":"Berlin ; Heidelberg ; London"}],"part":{"extent":"14","volume":"22","text":"22(2024), 1, Seite 1-14","year":"2024","pages":"1-14","issue":"1"},"note":["Gesehen am 22.05.20"],"language":["eng"],"recId":"377757241","disp":"Prediction of homologous recombination deficiency from routine histology with attention-based multiple instance learning in nine different tumor typesBMC biology"}],"title":[{"title":"Prediction of homologous recombination deficiency from routine histology with attention-based multiple instance learning in nine different tumor types","title_sort":"Prediction of homologous recombination deficiency from routine histology with attention-based multiple instance learning in nine different tumor types"}],"id":{"eki":["1923073524"],"doi":["10.1186/s12915-024-02022-9"]},"person":[{"role":"aut","given":"Chiara","family":"Löffler","display":"Löffler, Chiara"},{"role":"aut","given":"Omar S. M.","family":"El Nahhas","display":"El Nahhas, Omar S. M."},{"role":"aut","given":"Hannah Sophie","family":"Muti","display":"Muti, Hannah Sophie"},{"given":"Zunamys I.","role":"aut","display":"Carrero, Zunamys I.","family":"Carrero"},{"given":"Tobias Julian","role":"aut","display":"Seibel, Tobias Julian","family":"Seibel"},{"display":"van Treeck, Marko","family":"van Treeck","given":"Marko","role":"aut"},{"given":"Didem","role":"aut","display":"Cifci, Didem","family":"Cifci"},{"given":"Marco","role":"aut","display":"Gustav, Marco","family":"Gustav"},{"family":"Bretz","display":"Bretz, Kevin","role":"aut","given":"Kevin"},{"role":"aut","given":"Nadine","family":"Gaisa","display":"Gaisa, Nadine"},{"family":"Lehmann","display":"Lehmann, Kjong-Van","role":"aut","given":"Kjong-Van"},{"family":"Leary","display":"Leary, Alexandra","role":"aut","given":"Alexandra"},{"family":"Selenica","display":"Selenica, Pier","role":"aut","given":"Pier"},{"role":"aut","given":"Jorge S.","family":"Reis-Filho","display":"Reis-Filho, Jorge S."},{"display":"Ortiz-Bruechle, Nadina","family":"Ortiz-Bruechle","given":"Nadina","role":"aut"},{"role":"aut","given":"Jakob Nikolas","family":"Kather","display":"Kather, Jakob Nikolas"}],"origin":[{"dateIssuedDisp":"08 October 2024","dateIssuedKey":"2024"}],"language":["eng"],"note":["Gesehen am 16.04.2025"],"recId":"1923073524","name":{"displayForm":["Chiara Maria Lavinia Loeffler, Omar S.M. El Nahhas, Hannah Sophie Muti, Zunamys I. Carrero, Tobias Seibel, Marko van Treeck, Didem Cifci, Marco Gustav, Kevin Bretz, Nadine T. Gaisa, Kjong-Van Lehmann, Alexandra Leary, Pier Selenica, Jorge S. Reis-Filho, Nadina Ortiz-Bruechle and Jakob Nikolas Kather"]}} 
SRT |a LOEFFLERCHPREDICTION0820