Head and Neck Cancer Staging and Radiotherapy planning

AISTAT H&N integrates a pre-trained U-Net deep learning model with a statistical contour-based framework to deliver semi-automated, interpretable segmentation tailored for Head & Neck cancer radiotherapy planning. Unlike conventional voxel-level approaches, it produces clinically actionable contour-level outputs compatible with IMRT and VMAT workflows, enabling consistent, reproducible delineations across complex anatomical regions.

The tool incorporates built-in uncertainty quantification, allowing clinicians to assess segmentation reliability and make confident adjustments during treatment planning.

Building on prior validation in lung and lymphoma datasets, this product focuses on H&N cancers, using both the publicly available HECKTOR dataset and a real-world cohort of 200 patients from NHSGGC. The goal is to demonstrate clinical utility in authentic radiotherapy environments — providing a robust foundation for future commercial development and investment.