Predicting benefit from PARP inhibitors using deep learning on H&E-stained ovarian cancer slides
Year: 2024
Type: article
Abstract: PURPOSE: Ovarian cancer patients with a Homologous Recombination Deficiency (HRD) often benefit from polyadenosine diphosphate-ribose polymerase (PARP) inhibitor maintenance therapy after response to platinum-based chemotherapy. HR status is currently analyzed via complex molecular tests. Predicting benefit from PARP inhibitors directly on histological whole slide images (WSIs) could be a fast and cheap alternative. PATIENTS AND METHODS: We trained a Deep Learning (DL) model on H&E stained WSIs with "shrunken centroid" (SC) based HRD ground truth using the AGO-TR1 cohort (n = 208: 108 training, 100 test) and tested its ability to predict HRD as evaluated by the Myriad classifier and the benefit from olaparib in the PAOLA-1 cohort (n = 447) in a blinded manner. RESULTS: In contrast to the HRD prediction AUROC of 72 % on hold-out, our model only yielded an AUROC of 57 % external. Kaplan-Meier analysis showed that progression free survival (PFS) in the PARP inhibitor treated PAOLA-1 patients was significantly improved in the HRD positive group as defined by our model, but not in the HRD negative group. PFS improvement in PARP inhibitor-treated patients was substantially longer in our HRD positive group, hinting at a biologically meaningful prediction of benefit from PARP inhibitors. CONCLUSION: Together, our results indicate that it might be possible to generate a predictor of benefit from PARP inhibitors based on the DL-mediated analysis of WSIs. However, further studies with larger cohorts and further methodological improvements will be necessary to generate a predictor with clinically useful accuracy across independent patient cohorts.
Source: European Journal of Cancer
Authors: Frederik Marmé, Eva I. Krieghoff-Henning, Lennard Kiehl, Christoph Wies, Jan Hauke, Eric Hahnen, Philipp Harter, Philip C. Schouten, Tobias Brodkorb, Mohamad Kayali, Florian Heitz, Claudio Zamagni, Antonio González-Martin, Isabelle Treilleux, Stefan Kommoss, Katharina Prieske, Timo Gaiser, Stefan Fröhling, Isabelle Ray-Coquard, Eric Pujade-Lauraine, Titus J. Brinker
Institutions: German Cancer Research Center, Heidelberg University, University Medical Centre Mannheim, Medizinische Fakultät Mannheim, University Hospital Cologne, Arbeitsgemeinschaft Gynäkologische Onkologie Studiengruppe, Kliniken Essen-Mitte, Cambridge University Hospitals NHS Foundation Trust, The Netherlands Cancer Institute, Addenbrooke's Hospital, IRCCS Azienda Ospedliero-Universitaria di Bologna Policlinico di Sant'Orsola, Clinica Universidad de Navarra, Spanish Ovarian Cancer Research Group, Centre Léon Bérard, Universitätsklinikum Tübingen, University Medical Center Hamburg-Eppendorf, University Hospital Heidelberg, National Center for Tumor Diseases, Deutsches Konsortium für Translationale Krebsforschung, Arcagy Gineco
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,840
OpenAlex ID: W4405808237