Communications of the ACM
Stanford Team Trains Computer to Evaluate Breast Cancer
Photo courtesy of Stanford University
Stanford University researchers have developed Computational Pathologist (C-Path), a machine learning-based method for automatically analyzing images of cancerous tissues and predicting patient survival.
To train C-Path, the researchers used existing tissue samples taken from patients whose prognosis was known. By comparing new results against the known data, the software learned those features that can better predict survival. In total, C-Path assesses 6,642 cellular factors before determining the chance of patient survival.
In testing, C-Path produced results that were a statistically significant improvement over human-based evaluation. "We built a model based on features of the stroma--the microenvironment between cancer cells--that was a stronger predictor of outcome than one built exclusively from features of epithelial cells," says Stanford Ph.D. candidate Andrew Beck.
The researchers say the development of computers that can evaluate cancers will bring world-class pathology to underserved areas where trained professionals have traditionally been scarce, improving the prognosis and treatment of breast cancer for millions in developing areas of the world.
From Stanford University
View Full Article
Abstracts Copyright © 2011 Information Inc. 
, Bethesda, Maryland, USA
No entries found