A new deep learning model using histopathology images identifies recurrence risk in stage II colorectal cancer more effectively than standard clinical predictors.
Key Details
- 1Researchers developed a deep learning model (SurvFinder) trained on whole slide histopathology images from stage II colorectal cancer patients.
- 2The study retrospectively analyzed multi-center data from patients in China and the United States.
- 3The AI model identified features associated with risk of recurrence at a higher success rate than traditional clinical prognostic tools.
- 4Study details and results are published in PLOS Medicine, open access.
Why It Matters
Digital pathology AI models can enhance prognostic accuracy and help personalize treatment plans for cancer patients. Outperforming current clinical tools could enable better risk stratification and improved outcomes in stage II colorectal cancer.
Source
EurekAlert
Related News
•EurekAlert
Deep Learning Boosts ICD-11 Coding Accuracy for Chinese EMRs
Researchers developed a deep learning model achieving high accuracy in automatic ICD-11 coding of Chinese electronic medical records.
•EurekAlert
Dual-Branch Graph Attention Network Predicts ECT Success in Teen Depression
Researchers developed a dual-branch graph attention network that uses structural and functional MRI data to accurately predict individual responses to electroconvulsive therapy in adolescents with major depressive disorder.
•EurekAlert
Stanford's SleepFM AI Predicts 130 Disease Risks from Polysomnography
Stanford researchers have developed SleepFM, an AI model that predicts over 100 diseases using one night of sleep study data.