Computers 'better breast cancer evaluators'

Wednesday 9th November 2011

Computers have the ability to become more accurate scanners of microscopic breast cancer images than humans, according to research published today (November 9) in Science Translational Medicine.

Researchers from Stanford, USA, have created a model called Computational Pathologist (C-Path), a machine-learning-based method for automatically analysing 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. 

The computers pored over images, measuring various tumour structures and trying to use those structures to predict patient survival. 

By comparing results against the known data, the computers adapted their models to better predict survival and gradually figured out what features of the cancers matter most and which matter less in predicting survival.

"Pathologists have been trained to look at and evaluate specific cellular structures of known clinical importance, which get incorporated into the grade," explained lead author Andrew Beck.

"However, tumours contain innumerable additional features, whose clinical significance has not previously been evaluated."

C-Path assesses 6,642 cellular factors. Once trained using one group of patients, C-Path was asked to evaluate tissues of cancer patients it had not checked before and the result was compared against known data. 

Ultimately, C-Path yielded results that were a statistically significant improvement over human-based evaluation.

The Stanford findings add weight to what many scientists have been contending for some time: that cancer is an "ecosystem," and that clinically significant information can be obtained by careful analysis of the complete tumour microenvironment.

Beck et al believe the impact of the Stanford work will be felt broadly and individually.

Having 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.

At the personal level, machine learning may reduce the variability in results. C-Path could improve the accuracy of prognoses for all breast cancer victims. 

It could, likewise, improve the screening of pre-cancerous cells that could help many women avoid cancer altogether. It might even be applied to predict the effectiveness of various forms of treatment and drug therapies.

Science Translational Medicine