A multimodal dataset for precision oncology in head and neck cancer

Dörrich M, Balk M, Heusinger T, Beyer S, Mirbagheri M, Fischer DJ, Kanso H, Matek C, Hartmann A, Iro H, Eckstein M, Gostian AO, Kist A (2025)

Publication Language: English

Publication Type: Journal article

Publication year: 2025

Journal

Nature Communications Nature Publishing Group: Nature Communications

Book Volume: 16

Article Number: 7163

Journal Issue: 1

DOI: 10.1038/s41467-025-62386-6

Abstract

Head and neck cancer is a common disease and is associated with a poor prognosis. A promising approach to improving patient outcomes is personalized treatment, which uses information from a variety of modalities. However, only little progress has been made due to the lack of large public datasets. We present a multimodal dataset, HANCOCK, that comprises monocentric, real-world data of 763 head and neck cancer patients. Our dataset contains demographical, pathological, and blood data as well as surgery reports and histologic images, that can be explored in a low-dimensional representation. We can show that combining these modalities using machine learning is superior to a single modality and the integration of imaging data using foundation models helps in endpoint prediction. We believe that HANCOCK will not only open new insights into head and neck cancer pathology but also serve as a major source for researching multimodal machine-learning methodologies in precision oncology.

Authors with CRIS profile

Marion Dörrich Professur für Artificial Intelligence in Biomedical Speech Processing (Stiftungsprofessur) Matthias Balk Department of Otorhinolaryngology – Head and Neck Surgery (HNO-Klinik) Tatjana Heusinger Department of Otorhinolaryngology – Head and Neck Surgery (HNO-Klinik) Sandra Beyer Department of Oral and Cranio-Maxillofacial Surgery Mohammadhamed Mirbagheri Juniorprofessur für Artificial Intelligence in Communication Disorders Hassan Kanso Department of Otorhinolaryngology – Head and Neck Surgery (HNO-Klinik) Christian Matek Institute of Pathology Arndt Hartmann Lehrstuhl für Allgemeine Pathologie und Pathologische Anatomie Heinrich Iro Lehrstuhl für Hals-Nasen-Ohrenheilkunde Markus Eckstein Institute of Pathology Antoniu-Oreste Gostian Department of Otorhinolaryngology – Head and Neck Surgery (HNO-Klinik) Andreas Kist Juniorprofessur für Artificial Intelligence in Communication Disorders

How to cite

APA:

Dörrich, M., Balk, M., Heusinger, T., Beyer, S., Mirbagheri, M., Fischer, D.J.,... Kist, A. (2025). A multimodal dataset for precision oncology in head and neck cancer. Nature Communications, 16(1). https://doi.org/10.1038/s41467-025-62386-6

MLA:

Dörrich, Marion, et al. "A multimodal dataset for precision oncology in head and neck cancer." Nature Communications 16.1 (2025).

BibTeX: Download