New computational pipeline analyzes tumor images, may help predict response to cancer therapy

February 1, 2013 by Dan Krotz
A tumor’s organizational complexity is revealed. The center image is a whole-slide image of a Glioblastoma Multiforme tumor. The arrows indicate enlarged, distinct regions. Berkeley Lab scientists have developed an automated way to analyze large sets of tumor images.

(Medical Xpress)—How's this for big data: A whole-slide image of a tumor section can be ten billion pixels. There can be thousands of such images in the tumor cohorts maintained by The Cancer Genome Atlas project, which are collected from a large pool of patients.

The are a potential for the emerging field of precision medicine. Hidden in those billions of pixels is a story of how organize themselves, the that influence these structural traits, and what it all means for patients. Unfortunately, culling this information from numerous images is difficult. That's because no two tumors are alike, and there are myriad technical variations in how samples are prepared.

This analysis could soon get much easier. Berkeley Lab scientists have developed an algorithm and a computational pipeline that combs through large sets of images and identifies subtypes. It also identifies , or the extent to which a tumor comprises different organizational structures. The pipeline then uses clinical data to rank cellular signatures that are predictive of patient outcome. It also uses large-scale genomic data to identify molecular correlates of each subtype.

The resulting information will help scientists learn more about the genetic and that control tumor signatures. It will also shed light on whether tumor subtype can predict the effectiveness of therapies.

"Our goals are to identify morphometric and architectural traits that can be predictive of a therapy. We'd also like to learn about the molecular signatures that lead to architectural ," says Bahram Parvin of Berkeley Lab's Life Sciences Division. The development of the core computational module and the pipeline were led by Hang Chang and Gerald Fontenay, respectively, in Parvin's Lab in the Life Sciences Division.

The core computational module works by extracting each cell from an image, and then profiling properties of each cell such as size, shape, and organization. In this way, the telltale characteristics of a specific tumor subtype are gleaned from a large cohort of images.

As recently reported, the scientists validated their pipeline by applying it to 377 whole-slide images from 146 patients who have an aggressive brain cancer called Glioblastoma Multiforme. The pipeline identified several tumor subtypes based on a range of cellular profiles. It also determined whether each subtype is predictive of a patient's response to alternative therapy. Although the pipeline was developed in a high-performance computer language, it is compute intensive and required extensive use of the Lawrencium cluster operated by Berkeley Lab's IT Division.

The scientists also created an online repository for these images, which also includes images of low-grade glial and kidney renal carcinoma tumor sections. The website allows for Google-map style zooming and panning of the tissue sections. The scientists next hope to layer more information onto the images, in addition to cellular structure, to provide a broader representation of the tumors' characteristics and interactions between different components of tumor histology.

Explore further: Molecular subtypes and genetic alterations may determine response to lung cancer therapy

Related Stories

Molecular subtypes and genetic alterations may determine response to lung cancer therapy

May 11, 2012
Cancer therapies targeting specific molecular subtypes of the disease allow physicians to tailor treatment to a patient's individual molecular profile. But scientists are finding that in many types of cancer the molecular ...

Online archive to link tumor scans, genetic data

June 24, 2011
The National Cancer Institute (NCI) has chosen Washington University School of Medicine in St. Louis to create an innovative, Internet-accessible database of millions of cancer images.

Uncovering the spread of deadly cancer

August 26, 2011
For the first time, scientists can see pathways to stop a deadly brain cancer in its tracks. Researchers at Case Western Reserve University School of Medicine have imaged individual cancer cells and the routes they travel ...

Researchers create cellular automation model to study complex tumor-host role in cancer

March 27, 2012
Cancer remains a medical mystery – despite all of the research efforts devoted to understanding and controlling it. The most sought-after tumor model is one that would be able to formulate theoretical and computational ...

New subtype of ovarian cancer may be vulnerable to anti-angiogenic drugs

February 14, 2012
BOSTON--Scientists at Dana-Farber Cancer Institute have identified a subtype of ovarian cancer able to build its own blood vessels, suggesting that such tumors might be especially susceptible to "anti-angiogenic" drugs that ...

Recommended for you

Stem cell therapy attacks cancer by targeting unique tissue stiffness

July 26, 2017
A stem cell-based method created by University of California, Irvine scientists can selectively target and kill cancerous tissue while preventing some of the toxic side effects of chemotherapy by treating the disease in a ...

Understanding cell segregation mechanisms that help prevent cancer spread

July 26, 2017
Scientists have uncovered how cells are kept in the right place as the body develops, which may shed light on what causes invasive cancer cells to migrate.

Study uncovers potential 'silver bullet' for preventing and treating colon cancer

July 26, 2017
In preclinical experiments, researchers at VCU Massey Cancer Center have uncovered a new way in which colon cancer develops, as well as a potential "silver bullet" for preventing and treating it. The findings may extend to ...

Compound shows promise in treating melanoma

July 26, 2017
While past attempts to treat melanoma failed to meet expectations, an international team of researchers are hopeful that a compound they tested on both mice and on human cells in a petri dish takes a positive step toward ...

Study may explain failure of retinoic acid trials against breast cancer

July 25, 2017
Estrogen-positive breast cancers are often treated with anti-estrogen therapies. But about half of these cancers contain a subpopulation of cells marked by the protein cytokeratin 5 (CK5), which resists treatment—and breast ...

Breaking the genetic resistance of lung cancer and melanoma

July 25, 2017
Researchers from Monash University and the Memorial Sloan Kettering Cancer Center (MSKCC, New York) have discovered why some cancers – particularly lung cancer and melanoma – are able to quickly develop deadly resistance ...


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.