Article Contents
ARTICLE   Open Access     Cite

Multimodal deep learning model for predicting homologous recombination deficiency in prostate cancer: A multi-cohort study

    Show all affliationsShow less
More Information
  • DownLoad: Full size image
    1. A model combined clinical data, tissue images, and magnetic resonance imaging in prostate cancer.

      Image-based models showed predictive signal for homologous recombination deficiency.

      Combined imaging showed a favorable trend in a small internal validation set.

      Larger prospective cohorts are needed before clinical use.

  • Accurate prediction of homologous recombination deficiency (HRD) status is crucial for effective management of prostate cancer (PCa). However, genetic testing is expensive and inaccessible. We propose a multimodal deep learning approach that integrates clinical information, Hematoxylin & Eosin (H&E)-stained whole-slide images (WSIs), and multiparametric magnetic resonance imaging (MRI) to predict the HRD status of patients with PCa. Patients from The Cancer Genome Atlas (TCGA; n=486) and three Chinese hospitals (n=210) were used to develop and evaluate the prediction models. The Pathology Signature, Radiology Signature, and Patho-Radiology Signature showed predictive performance for HRD status in external validation or internal held-out evaluation (area under the receiver operating characteristic curve [AUC]=0.815, 0.833, and 0.900, respectively). Notably, four interpretable pathological features were identified in the Pathology Signature. These signatures may serve as a prescreening tool to select patients for confirmatory genetic testing. This multimodal framework may be adaptable to the prediction of molecular alterations in other malignancies, subject to independent validation. Because radiology and multimodal models were evaluated in small modality-complete subsets, these estimates should be interpreted as exploratory trends.
  • 加载中
  • [1] Siegel R.L., Miller K.D., Wagle N.S., et al. (2023). Cancer statistics, 2023. CA Cancer J. Clin. 73:17−48. DOI:10.3322/caac.21763

    View in Article CrossRef Google Scholar

    [2] Mitchell T. and Neal D.E. (2015). The genomic evolution of human prostate cancer. Br. J. Cancer 113:193−198. DOI:10.1038/bjc.2015.234

    View in Article CrossRef Google Scholar

    [3] Nguyen L., Martens J.W.M., Van Hoeck A., et al. (2020). Pan-cancer landscape of homologous recombination deficiency. Nat. Commun. 11:5584. DOI:10.1038/s41467-020-19406-4

    View in Article CrossRef Google Scholar

    [4] Hoeijmakers J.H. (2001). Genome maintenance mechanisms for preventing cancer. Nature 411:366−374. DOI:10.1038/35077232

    View in Article CrossRef Google Scholar

    [5] Groelly F.J., Fawkes M., Dagg R.A., et al. (2023). Targeting DNA damage response pathways in cancer. Nat. Rev. Cancer 23:78−94. DOI:10.1038/s41568-022-00535-5

    View in Article CrossRef Google Scholar

    [6] ESMO. (2019). ESMO 2019: PROfound: Phase 3 study of olaparib vs. enzalutamide or abiraterone for metastatic castration-resistant prostate cancer with homologous recombination repair gene alterations. UroToday. https://www.urotoday.com/conference-highlights/esmo-2019/esmo-2019-prostate-cancer/115401-esmo-2019-profound-phase-3-study-of-olaparib-vs-enzalutamide-or-abiraterone-for-metastatic-castration-resistant-prostate-cancer-with-homologous-recombination-repair-gene-alterations.html (Accessed June 3, 2023

    View in Article Google Scholar

    [7] de Luca X.M., Newell F., Kazakoff S.H., et al. (2020). Using whole-genome sequencing data to derive the homologous recombination deficiency scores. npj Breast Cancer 6:33. DOI:10.1038/s41523-020-0172-0

    View in Article CrossRef Google Scholar

    [8] Sztupinszki Z., Diossy M., Krzystanek M., et al. (2020). Detection of molecular signatures of homologous recombination deficiency in prostate cancer with or without BRCA1/2 mutations. Clin. Cancer Res. 26:2673−2680. DOI:10.1158/1078-0432.CCR-19-2135

    View in Article CrossRef Google Scholar

    [9] Coudray N. and Tsirigos A. (2020). Deep learning links histology, molecular signatures and prognosis in cancer. Nat. Cancer 1:755−757. DOI:10.1038/s43018-020-0099-2

    View in Article CrossRef Google Scholar

    [10] Kather J.N., Pearson A.T., Halama N., et al. (2019). Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat. Med. 25:1054−1056. DOI:10.1038/s41591-019-0462-y

    View in Article CrossRef Google Scholar

    [11] Yamashita R., Long J., Longacre T., et al. (2021). Deep learning model for the prediction of microsatellite instability in colorectal cancer: A diagnostic study. Lancet Oncol. 22:132−141. DOI:10.1016/S1470-2045(20)30535-0

    View in Article CrossRef Google Scholar

    [12] Cifci D., Foersch S. and Kather J.N. (2022). Artificial intelligence to identify genetic alterations in conventional histopathology. J. Pathol. 257:430−444. DOI:10.1002/path.5898

    View in Article CrossRef Google Scholar

    [13] Dadhania V., Gonzalez D., Yousif M., et al. (2022). Leveraging artificial intelligence to predict ERG gene fusion status in prostate cancer. BMC Cancer 22:494. DOI:10.1186/s12885-022-09559-4

    View in Article CrossRef Google Scholar

    [14] Schaumberg A.J., Rubin M.A. and Fuchs T.J. (2016). H&E-stained whole slide image deep learning predicts SPOP mutation state in prostate cancer. bioRxiv. DOI:10.1101/064279.

    View in Article Google Scholar

    [15] Houlahan K.E., Salmasi A., Sadun T.Y., et al. (2019). Molecular hallmarks of multiparametric magnetic resonance imaging visibility in prostate cancer. Eur. Urol. 76:18−23. DOI:10.1016/j.eururo.2018.12.036

    View in Article CrossRef Google Scholar

    [16] Boehm K.M., Aherne E.A., Ellenson L., et al. (2022). Multimodal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer. Nat. Cancer 3:723−733. DOI:10.1038/s43018-022-00388-9

    View in Article CrossRef Google Scholar

    [17] Vanguri R.S., Luo J., Aukerman A.T., et al. (2022). Multimodal integration of radiology, pathology and genomics for prediction of response to PD-(L)1 blockade in patients with non-small cell lung cancer. Nat. Cancer 3:1151−1164. DOI:10.1038/s43018-022-00416-8

    View in Article CrossRef Google Scholar

    [18] Fremond S., Andani S., Barkey Wolf J., et al. (2023). Interpretable deep learning model to predict the molecular classification of endometrial cancer from haematoxylin and eosin-stained whole-slide images: A combined analysis of the PORTEC randomised trials and clinical cohorts. Lancet Digit. Health 5:e71−e82. DOI:10.1016/S2589-7500(22)00210-2

    View in Article CrossRef Google Scholar

    [19] Li J., Xu C., Lee H.J., et al. (2020). A genomic and epigenomic atlas of prostate cancer in Asian populations. Nature 580:93−99. DOI:10.1038/s41586-020-2135-x

    View in Article CrossRef Google Scholar

    [20] Cancer Genome Atlas Research Network. (2015). The molecular taxonomy of primary prostate cancer. Cell 163:1011−1025. DOI:10.1016/j.cell.2015.10.025

    View in Article CrossRef Google Scholar

    [21] Clarke N., Wiechno P., Alekseev B., et al. (2018). Olaparib combined with abiraterone in patients with metastatic castration-resistant prostate cancer: A randomised, double-blind, placebo-controlled, phase 2 trial. Lancet Oncol. 19:975−986. DOI:10.1016/S1470-2045(18)30365-6

    View in Article CrossRef Google Scholar

    [22] Wu K., Liang J., Shao Y., et al. (2021). Evaluation of the efficacy of PARP inhibitors in metastatic castration-resistant prostate cancer: A systematic review and meta-analysis. Front. Pharmacol. 12:777663. DOI:10.3389/fphar.2021.777663

    View in Article CrossRef Google Scholar

    [23] De Bono J.S., Hussain M., Thiery-Vuillemin A., et al. (2017). PROfound: A randomized Phase III trial evaluating olaparib in patients with metastatic castration-resistant prostate cancer and a deleterious homologous recombination DNA repair aberration. J. Clin. Oncol. 35:TPS5091−TPS5091. DOI:10.1200/JCO.2017.35.15_suppl.TPS5091

    View in Article CrossRef Google Scholar

    [24] Milbury C.A., Creeden J., Yip W.-K., et al. (2022). Clinical and analytical validation of FoundationOne®CDx, a comprehensive genomic profiling assay for solid tumors. PLoS One 17:e0264138. DOI:10.1371/journal.pone.0264138

    View in Article CrossRef Google Scholar

    [25] Woodhouse R., Li M., Hughes J., et al. (2020). Clinical and analytical validation of FoundationOne Liquid CDx, a novel 324-gene cfDNA-based comprehensive genomic profiling assay for cancers of solid tumor origin. PLoS One 15:e0237802. DOI:10.1371/journal.pone.0237802

    View in Article CrossRef Google Scholar

    [26] U.S. Food and Drug Administration. (2021). Device classification under Section 513(f)(2) (De Novo): Paige Prostate (DEN200080). FDA. https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm?id=DEN200080 (Accessed October 15, 2026

    View in Article Google Scholar

    [27] Feng C., Zhang Y., Wu F., et al. (2023). Relationship between homologous recombination deficiency and clinical features of breast cancer based on genomic scar score. Breast 69:392−400. DOI:10.1016/j.breast.2023.04.002

    View in Article CrossRef Google Scholar

    [28] Fu Y., Jung A.W., Torne R.V., et al. (2020). Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis. Nat. Cancer 1:800−810. DOI:10.1038/s43018-020-0085-8

    View in Article CrossRef Google Scholar

    [29] Kim M., Jung S.Y., Park J.E., et al. (2020). Diffusion- and perfusion-weighted MRI radiomics model may predict isocitrate dehydrogenase (IDH) mutation and tumor aggressiveness in diffuse lower grade glioma. Eur. Radiol. 30:2142−2151. DOI:10.1007/s00330-019-06548-3

    View in Article CrossRef Google Scholar

    [30] Zhang J., Zhao X., Zhao Y., et al. (2020). Value of pre-therapy 18F-FDG PET/CT radiomics in predicting EGFR mutation status in patients with non-small cell lung cancer. Eur. J. Nucl. Med. Mol. Imaging 47:1137−1146. DOI:10.1007/s00259-019-04592-1

    View in Article CrossRef Google Scholar

    [31] Sammut S.-J., Crispin-Ortuzar M., Chin S.-F., et al. (2022). Multi-omic machine learning predictor of breast cancer therapy response. Nature 601:623−629. DOI:10.1038/s41586-021-04278-5

    View in Article CrossRef Google Scholar

    [32] Lipkova J., Chen R.J., Chen B., et al. (2022). Artificial intelligence for multimodal data integration in oncology. Cancer Cell 40:1095−1110. DOI:10.1016/j.ccell.2022.09.012

    View in Article CrossRef Google Scholar

    [33] Muti H.S., Heij L.R., Keller G., et al. (2021). Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer: A retrospective multicentre cohort study. Lancet Digit. Health 3:e654−e664. DOI:10.1016/S2589-7500(21)00133-3

    View in Article CrossRef Google Scholar

    [34] Mohanty S.K., Lobo A. and Cheng L. (2023). The 2022 revision of the World Health Organization classification of tumors of the urinary system and male genital organs: Advances and challenges. Hum. Pathol. 136:123−143. DOI:10.1016/j.humpath.2022.08.006

    View in Article CrossRef Google Scholar

    [35] van Leenders G.J.L.H., van der Kwast T.H., Grignon D.J., et al. (2020). The 2019 International Society of Urological Pathology (ISUP) consensus conference on grading of prostatic carcinoma. Am. J. Surg. Pathol. 44:e87−e99. DOI:10.1097/PAS.0000000000001497

    View in Article CrossRef Google Scholar

    [36] Bilal M., Raza S.E.A., Azam A., et al. (2021). Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: A retrospective study. Lancet Digit. Health 3:e763−e772. DOI:10.1016/S2589-7500(21)00180-1

    View in Article CrossRef Google Scholar

    [37] Loeffler C.M.L., El Nahhas O.S.M., Muti H.S., et al. (2023). Direct prediction of homologous recombination deficiency from routine histology in ten different tumor types with attention-based multiple instance learning: A development and validation study. medRxiv 2023.03.08.23286975. DOI:10.1101/2023.03.08.23286975.

    View in Article Google Scholar

  • Cite this article:

    Deng L., Song Z., Zhang Q., et al. (2026). Multimodal deep learning model for predicting homologous recombination deficiency in prostate cancer: A multi-cohort study. The Innovation Oncology 1:100043. https://doi.org/10.59717/j.xinn-oncol.2026.100043
    Deng L., Song Z., Zhang Q., et al. (2026). Multimodal deep learning model for predicting homologous recombination deficiency in prostate cancer: A multi-cohort study. The Innovation Oncology 1:100043. https://doi.org/10.59717/j.xinn-oncol.2026.100043

Welcome!

To request copyright permission to republish or share portions of our works, please visit Copyright Clearance Center's (CCC) Marketplace website at marketplace.copyright.com.

Figures(6)     Tables(1)

Share

  • Share the QR code with wechat scanning code to friends and circle of friends.

Article Metrics

Article views(494) PDF downloads(257)

Relative Articles

Cited by

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint