HERMES AI system achieves high scores in head-and-neck tumor analysis

Researchers have developed HERMES, a hybrid ensemble algorithm designed for head-and-neck tumor analysis on PET/CT scans. This system integrates tumor segmentation, TN staging, and recurrence-free survival prediction into a single containerized solution. HERMES utilizes a 10-fold ensemble of STU-Net Small networks for segmentation, deriving geometry features that improve N-stage balanced accuracy. The system also combines deep and clinical risk models for prognosis, achieving a weighted score of 0.6454 on the HECKTOR 2026 validation leaderboard and qualifying for the testing phase. AI

IMPACT This research demonstrates an integrated AI approach for complex medical imaging tasks, potentially improving diagnostic accuracy and treatment planning for head-and-neck cancers.

RANK_REASON The cluster contains a research paper detailing a new AI model for medical image analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• AJCC/UICC
• AMC_HNC
• HECKTOR 2026
• HERMES
• STU-Net Small

• paper
• model release
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →