Home »
Academic Articles »
Art »
Prediction of homologous recombination deficiency from routine histology with attention-based multiple instance learning in nine different tumor types
Prediction of homologous recombination deficiency from routine histology with attention-based multiple instance learning in nine different tumor types
Chiara Maria Lavinia Loeffler
(Department of Medicine III, University Hospital RWTH Aachen)
Omar S. M. El Nahhas
(Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden)
Hannah Sophie Muti
(Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden)
Zunamys I. Carrero
(Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden)
Tobias Seibel
(Department of Medicine III, University Hospital RWTH Aachen)
Marko van Treeck
(Department of Medicine III, University Hospital RWTH Aachen)
Didem Cifci
(Department of Medicine III, University Hospital RWTH Aachen)
Marco Gustav
(Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden)
Kevin Bretz
(Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden)
Nadine T. Gaisa
(Institute of Pathology, University Hospital RWTH Aachen)
Kjong-Van Lehmann
(Institute of Pathology, University Hospital RWTH Aachen)
Alexandra Leary
(Gynecological Cancer Unit, Department of Medicine, Institut Gustave Roussy)
Pier Selenica
(Experimental Pathology, Department of Pathology, Memorial Sloan Kettering Cancer Center)
Jorge S. Reis-Filho
(Experimental Pathology, Department of Pathology, Memorial Sloan Kettering Cancer Center)
Nadina Ortiz-Bruechle
(Institute of Pathology, University Hospital RWTH Aachen)
Jakob Nikolas Kather
(Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden)
Journal: BMC Biology
•
• BMC
• ISSN: 1741-7007
Abstract
Abstract Background 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. Methods 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. Results 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. Conclusions This study establishes that HRD can be directly predicted from H&E slides using attMIL, demonstrating its applicability across nine different tumor types.
Chiara Maria Lavinia Loeffler, Omar S. M. El Nahhas, Hannah Sophie Muti, et al. (2024). "Prediction of homologous recombination deficiency from routine histology with attention-based multiple instance learning in nine different tumor types". BMC Biology. https://doi.org/10.1186/s12915-024-02022-9