AI models improve lung cancer survival prediction from PET/CT scans

Researchers have developed two new models, ATCS and MTS, to improve the prediction of overall survival in lung cancer patients using PET/CT scans. These models, which incorporate temporal data, outperformed a baseline model, achieving mean AUCs of 0.794 and 0.793 respectively. The study found that ATCS was better for short-term predictions, while MTS excelled at longer-term estimates, and combining different types of imaging features further enhanced accuracy. AI

IMPACT These models offer improved risk stratification and clinical decision-making support for lung cancer patients.

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

Read on arXiv cs.CV →

• lung cancer
• PET/CT
• TCS

• paper
• model release

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