AI predicts lung cancer mutations from scans using multi-label learning

Researchers have developed a multi-label learning approach using deep learning to predict specific gene mutations (EGFR, TP53, and KRAS) in non-small cell lung cancer (NSCLC) from PET/CT scans. The study, conducted on a UK-based cohort, found that the effectiveness of multi-label learning varied depending on the gene mutation pairs, with joint prediction of KRAS and TP53 showing improved AUC scores. These findings suggest that mutation-specific modeling strategies may be more beneficial for PET/CT radiogenomic prediction. AI

IMPACT This research could lead to less invasive methods for identifying key genetic mutations in lung cancer, potentially improving treatment selection and patient outcomes.

RANK_REASON Academic paper detailing a novel machine learning approach for medical image analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• EGFR
• Kras
• PET-CT
• tumor protein p53
• Tumour protein 53 is linked with type 2 diabetes mellitus
• UK

• paper
• product

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