A NEW dataset developed by researchers at, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany, could pave the way for breakthroughs in precision medicine for head and neck cancers.
Head and neck cancers comprise a group of cancers that develop in the head and neck region, commonly including the oral cavity, pharynx, or larynx. They are currently the seventh most common malignancy worldwide. In the UK alone, approximately 12,800 new cases were reported annually between 2017 and 2019, with 10-year survival rates ranging from 19% to 59%, according to Cancer Research UK.
Despite their prevalence, head and neck cancers remain poorly understood at the molecular level. Additionally, there is currently a lack of large, multimodal, publicly available datasets which has hindered the discovery of novel biomarkers, to help personalise treatment for patients and predict disease progression.
To address this issue, Dörrich M and colleagues, built a comprehensive dataset comprising monocentric, retrospective data, from 763 patients diagnosed with oral cavity, oropharyngeal, hypopharyngeal, and laryngeal cancer, named HANCOCK (Head And Neck Cancer Dataset). The data included information on demographics, blood data, surgery reports, pathological data, and histological images.
“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” the authors stated.
Reference
Dörrich M et al. A multimodal dataset for precision oncology in head and neck cancer. Nature Communications. 2025;16:7163.
