Researchers train computer to evaluate breast cancer

November 9, 2011

Since 1928, the way breast cancer characteristics are evaluated and categorized has remained largely unchanged. It is done by hand, under a microscope. Pathologists examine the tumors visually and score them according to a scale first developed eight decades ago. These scores help doctors assess the type and severity of the cancer and, accordingly, to calculate the patient's prognosis and course of treatment.

In a paper to be published Nov. 9 in , at the Stanford School of Engineering and pathologists at the Stanford School of Medicine report their collaboration to train computers to analyze breast cancer microscopic images. The computer analyses were more accurate than those conducted by humans.

Their model is called Computational Pathologist, or 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 taken from patients whose was known. The computers pored over images, measuring various tumor 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.

"In essence, the computer learns," said Daphne Koller, PhD, professor of computer science and senior author of the paper.

Medical science has long used three specific features for evaluating — what percentage of the tumor is comprised of tube-like , the diversity of the nuclei in the outermost (epithelial) cells of the tumor and the frequency with which those cells divide (a process known as mitosis). These three factors are judged by sight with a microscope and scored qualitatively to stratify breast cancer patients into three groups that predict survival rates.

"Pathologists have been trained to look at and evaluate specific cellular structures of known clinical importance, which get incorporated into the grade. However, tumors contain innumerable additional features, whose clinical significance has not previously been evaluated," said Andrew Beck, MD, a doctoral candidate in biomedical informatics and the paper's first author.

"The computer strips away that bias and looks at thousands of factors to determine which matter most in predicting survival," said Koller.

C-Path, in fact, 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.

What's more, the computers identified structural features in cancers that matter as much or more than those that pathologists have focused on traditionally. In fact, they discovered that the characteristics of the cancer cells and the surrounding cells, known as the stroma, were both important in predicting patient survival.

"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," said Beck. "The stromal model was as predictive as the model built from both stromal and epithelial features."

In the end, 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 tumor microenvironment.

"Through machine learning, we are coming to think of cancer more holistically, as a complex system rather than as a bunch of bad cells in a tumor," said Matt van de Rijn, MD, PhD, a professor of pathology and co-author of the study. "The computers are pointing us to what is significant, not the other way around."

Van de Rijn does not see computers replacing pathologists. "We're looking at a future where computers and humans collaborate to improve results for patients across the world," he said.

The impact of the Stanford work will be felt broadly and individually, the researchers said. In the widest sense, 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 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.

"If we can teach computers to look at a tumor tissue sample and predict survival, why not train them to predict from the same sample which courses of treatment or drugs a given patient might respond to best? Or even to look at samples of non-malignant cells to predict whether these benign tissues will turn cancerous," said Koller. "This is personalized medicine."

Explore further: New biomarker that predicts breast cancer relapse found

Related Stories

New biomarker that predicts breast cancer relapse found

May 16, 2011
Researchers from Virginia Commonwealth University Massey Cancer Center have discovered a new biomarker related to the body's immune system that can predict a breast cancer patients' risk of cancer recurrence. This breakthrough ...

Will my breast cancer spread? Discovery may predict probability of metastasis

October 23, 2011
Researchers from Huntsman Cancer Institute (HCI) at the University of Utah have discovered a new way to model human breast cancer that could lead to new tools for predicting which breast cancers will spread and new ways to ...

Cellular origin of a rare form of breast cancer identified

September 22, 2011
Identifying the cellular origins of breast cancer might lead to earlier diagnosis and more efficient management of the disease. New research led by Charlotte Kuperwasser of Tufts University School of Medicine (TUSM) has determined ...

Recommended for you

Study provides insight into link between two rare tumor syndromes

August 22, 2017
UCLA researchers have discovered that timing is everything when it comes to preventing a specific gene mutation in mice from developing rare and fast-growing cancerous tumors, which also affects young children. This mutation ...

Retaining one normal BRCA gene in breast, ovarian cancers influences patient survival

August 22, 2017
Determining which cancer patients are likely to be resistant to initial treatment is a major research effort of oncologists and laboratory scientists. Now, ascertaining who might fall into that category may become a little ...

Study identifies miR122 target sites in liver cancer and links a gene to patient survival

August 22, 2017
A new study of a molecule that regulates liver-cell metabolism and suppresses liver-cancer development shows that the molecule interacts with thousands of genes in liver cells, and that when levels of the molecule go down, ...

Zebrafish larvae could be used as 'avatars' to optimize personalized treatment of cancer

August 21, 2017
Portuguese scientists have for the first time shown that the larvae of a tiny fish could one day become the preferred model for predicting, in advance, the response of human malignant tumors to the various therapeutic drugs ...

Scientists discover vitamin C regulates stem cell function, curbs leukemia development

August 21, 2017
Not much is known about stem cell metabolism, but a new study from the Children's Medical Center Research Institute at UT Southwestern (CRI) has found that stem cells take up unusually high levels of vitamin C, which then ...

Searching for the 'signature' causes of BRCAness in breast cancer

August 21, 2017
Breast cancer cells with defects in the DNA damage repair-genes BRCA1 and BRCA2 have a mutational signature (a pattern of base swaps—e.g., Ts for Gs, Cs for As—throughout a genome) known in cancer genomics as "Signature ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.