Integrating Artificial Intelligence-Driven Digital Pathology and Genomics to Establish Patient-Derived Organoids as a Novel Alternative Model for Drug Response in Head and Neck Cancer

Abstract Patient-derived organoids (PDOs) are emerging as advanced 3D ex vivo novel alternative method (NAM) preclinical models, offering significant advantages over traditional cell lines and monolayer cultures for therapeutic development. In this study, we established PDOs from surgically resected fresh tissues of human papillomavirus (HPV)-negative head and neck squamous cell carcinoma (HNSCC) across anatomical sites, tumor T-categories, and sample types. These PDOs faithfully recapitulate the tumor’s pathology, mutational profile, and drug response. To enable rapid classification of PDO identity, we developed a new convolutional neural network (CNN) model, TransferNet-PDO, which accurately distinguished tumor versus normal PDOs in culture using digital histopathology images (AUC≥0.88). PDOs maintained stable cultures and were cryopreserved between passages 5 and 12. Immunohistochemistry (IHC) staining (PanCK, p63, Cytokeratin 13, Ki67) confirmed squamous phenotype and histologic aggression of the original tumor. For tumors harboring TP53 mutations by whole-exome sequencing (WES), PDOs retained the corresponding p53 functional status as confirmed by IHC (enhanced or loss of expression). Somatic mutational landscape revealed that PDOs preserved driver somatic mutations, copy number variations (CNVs), and clonal architecture including low-prevalence subclones. Drug sensitivity assessment of PDOs showed that cisplatin reduced cell viability, whereas cetuximab and lenvatinib had minimal effects. Chemoradiation led to greater tumor organoid killing compared to radiation or chemotherapy alone. This study presents an integrated HNSCC PDO platform combining tissue biobanking, organoid establishment, multi-omics characterization, functional drug screening, and AI-driven histopathologic classification, providing a comprehensive and scalable system for translational cancer research. Competing Interest Statement R.B. declares PCT/US15/612657 (Cancer Immunotherapy), PCT/US18/36052 (Microbiome Biomarkers for Anti-PD-1/PD-L1 Responsiveness: Diagnostic, Prognostic and Therapeutic Uses Thereof), PCT/US63/055227 (Methods and Compositions for Treating Autoimmune and Allergic Disorders). J.J.L. declares DSMB: Abbvie, Immutep; Scientific Advisory Board: (no stock) 7 Hills, Fstar, Inzen, RefleXion, Xilio (stock) Actym, Alphamab Oncology, Arch Oncology, Kanaph, Mavu, Onc.AI, Pyxis, Tempest; Consultancy with compensation: Abbvie, Alnylam, Avillion, Bayer, Bristol-Myers Squibb, Checkmate, Codiak, Crown, Day One, Eisai, EMD Serono, Flame, Genentech, Gilead, HotSpot, Kadmon, KSQ, Janssen, Ikena, Immunocore, Incyte, Macrogenics, Merck, Mersana, Nektar, Novartis, Pfizer, Regeneron, Ribon, Rubius, Silicon, Synlogic, Synthekine, TRex, Werewolf, Xencor; Research Support: (all to institution for clinical trials unless noted) AbbVie, Agios (IIT), Astellas, Astrazeneca, Bristol-Myers Squibb (IIT & industry), Corvus, Day One, EMD Serono, Fstar, Genmab, Ikena, Immatics, Incyte, Kadmon, KAHR, Macrogenics, Merck, Moderna, Nektar, Next Cure, Numab, Pfizer (IIT & industry) Replimmune, Rubius, Scholar Rock, Synlogic, Takeda, Trishula, Tizona, Xencor; Patents: (both provisional) Serial #15/612,657 (Cancer Immunotherapy), PCT/US18/36052 (Microbiome Biomarkers for Anti-PD-1/PD-L1 Responsiveness: Diagnostic, Prognostic and Therapeutic Uses Thereof). L.V. declares patent US 10,543,264 B2 (Cancer prevention and therapy by inhibiting soluble tumor necrosis factor). R.L.F. declares Adagene Incorporated: Consulting; Aduro Biotech, Inc: Consulting; Astra-Zeneca/MedImmune: Clinical Trial, Research Funding; Bicara Therapeutics, Inc: Consultant ; Bristol-Myers Squibb: Advisory Board, Clinical Trial, Research Funding ; Brooklyn Immunotherapeutics LLC: Consultant; Catenion: Consultant; Coherus BioSciences, Inc.: Advisory Board; Eisai Europe Limited: Advisory Board; EMD Serono: Consultant; Everest Clinical Research Corporation: Consultant; F. Hoffmann-La Roche Ltd: Consultant; Federation Bio, Inc: Consultant; Genocea Biosciences, Inc: Consultant; Genmab: Advisory Board; Hookipa Biotech GmbH: Advisory Board; Instil Bio, Inc: Advisory Board; Kowa Research Institute, Inc.: Consultant ; Lifescience Dynamics Limited: Advisory Board; MacroGenics, Inc.: Advisory Board; MeiraGTx, LLC: Advisory Board; Merck: Advisory Board, Clinical Trial; Merus N.V: Advisory Board; Mirati Therapeutics, Inc: Consultant ; Mirror Biologics Inc: Data Safety Monitoring Board ; Nanobiotix: Consultant; Novartis Pharmaceutical Corporation: Consulting; Novasenta: Consulting, Stock, Research Funding ; Numab Therapeutics AG: Advisory Board; OncoCyte Corporation: Advisory Board; Pfizer: Advisory Board; PPD Development, L.P.: Consultant; Rakuten Medical, Inc: Advisory Board; Sanofi: Consultant; Seagen, Inc: Advisory Board; SIRPant Immunotherapeutics, Inc: Advisory Board; Tesaro: Research Funding; Vir Biotechnology, Inc: Advisory Board; Zymeworks, Inc.: Consultant. J.P.Z declares Droplet Biosciences: founder and equity shareholder. The other authors declare that they have no competing financial interests. Correspondence and requests for materials should be addressed to R.B. (baor{at}upmc.edu) and J.J.L. (lukejj{at}upmc.edu). Footnotes Removed an incorrectly included funding source from acknowledgments. https://github.com/HCC-data-sciences-pub/HNSCC-PDO-integrative-analysis