HANCOCK, A MULTIMODAL DATASET FOR PRECISION ONCOLOGY IN HEAD AND NECK CANCER

HANCOCK is another important piece of AI research applied to the treatment of head and neck cancer.
Three years of hard work led to an open #multimodal dataset for Precision Oncology in Head And Neck Cancer (HNSCC): HANCOCK (n=763) spans histology images, immune cell data, clinical follow up data, lab data, pathology and surgery reports.

The researchers integrated all this data with ML + foundation models and achieved superior outcome predictions compared to traditional clinical or pathological classifications. This represents a huge step forward for patients with HNSCC.

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. HANCOCK a multimodal dataset, comprises monocentric, real-world data of 763 head and neck cancer patients.

HANCOCK contains demographical, pathological, and blood data as well as surgery reports and histologic images, that can be explored in a low-dimensional representation. Combining these modalities using machine learning is superior to a single modality. 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.

Full article: https://www.nature.com/articles/s41467-025-62386-6