The HECKTOR 2025 challenge established a benchmark for automated head and neck cancer analysis using PET/CT imaging and electronic health records. Building on previous iterations, this challenge involved over 1,100 patients and tasked 35 registered teams with segmenting tumor volumes, predicting recurrence-free survival, and classifying HPV status. The top-performing algorithms achieved a mean Dice similarity coefficient of 0.75 for segmentation, a concordance index of 0.66 for survival prediction, and a balanced accuracy of 0.56 for HPV classification. AI
IMPACT Establishes new benchmarks for AI in oncology, potentially improving radiotherapy planning and patient outcome prediction.
RANK_REASON The item is a research paper detailing a challenge and benchmark for medical image analysis. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
