Scientists develop new way to identify telltale markers for breast cancer tumors

September 6, 2018, University of Southern California
An imaging technique that takes advantage of machine learning technology allows scientists to obtain results quickly, in contrast to traditional, more expensive methods that could take weeks. Credit: Rishi Rabat

A research team led by USC scientists has developed a new way to identify molecular markers of breast cancer tumors, a potentially life-saving breakthrough that could lead to better treatment for millions of women.

Aided by machine learning, the researchers taught a computer to rapidly sort images of breast tumors to identify which ones had estrogen receptors, a key to determining prognosis and treatment options. That's a big step forward from microscopes and cell biopsies in use for more than a century, according to the scientists.

The work opens a new pathway for that promises faster results for less cost for more people worldwide, said David B. Agus, professor at the Keck School of Medicine of USC and the USC Viterbi School of Engineering. He is also CEO of the Lawrence J. Ellison Institute for Transformative Medicine of USC.

The findings appear this week in npj Breast Cancer.

"It's the beginning of a revolution to use machine learning to get new information about breast to the physician," Agus said. "We can use it to detect better treatments, get information to patients faster and help more people. We're unleashing this power to give new information to physicians and help treat cancer."

Except for skin cancer, breast cancer is the most common cancer in women in the United States. While deaths have declined, it remains the second-leading cause of cancer death among women and the leading cause of cancer death among Hispanic women.

About 237,000 cases of cancer are diagnosed in U.S. women and about 41,000 die from the disease each year, according to the U.S. Centers for Disease Control and Prevention.

The key to identifying and treating cancer is knowing the nature of the tumor. Cancer cells that contain receptors for estrogen and other hormones respond differently to cancer drugs that target these mechanisms. While doctors use these characteristics to classify tumors and select treatments, testing for markers is a slow and inefficient process.

For example, assays can be inconsistent depending on the laboratory doing the testing. They're also expensive, take weeks to do and are unavailable in many developing countries.

"If you're diagnosed with cancer, it'll be a few weeks before you get a call from the doctor saying they've identified a marker," said Dan Ruderman, one of the study authors and assistant professor of research medicine at the Keck School of Medicine. "With machine learning technology, we can tell you the same day, so there's less delay, less stress and potentially better outcomes. It's going to enable us to identify the right drug and dose more quickly. It's a big step toward personalized medicine."

While machine learning has been used before for cancer detection, the USC study adapted the technology to more clearly focus on telltale markers of a cell's nucleus. The key was to extract parameters describing the shape of nuclei, and feeding these into a large neural network that could learn relationships between nucleus shape and .

The scientists used publicly available hematoxylin-eosin (H&E) stained histopathology images. the cell-stained slides doctors have been using for more than a century. Next, they ascertained clinical status for 113 cancer patients, then split the patients into two groups, using one group to train a convolutional neural network algorithm, which is used to enhance visual imagery, and another to test the machine. When they compared the two sets, they found a strong correlation, providing high confidence that an algorithm can predict the estrogen receptor status of the tumor.

"We can use this technology to identify the molecular markers of the tumor and in the future will identify which therapeutics the tumor will respond to. Machine learning helps us get this information to patients sooner and may transform cancer care in the developing world where precise marker assessment is in short supply," said Rishi Rawat, a graduate student in the Keck School of Medicine and first author of the study.

So far, the research findings demonstrate that the new technology has the potential to improve clinical care. Validation studies are under way—an important step before it's ready for use in the doctor's office

Explore further: Researchers advocate for single-cell diagnostics for breast cancer

More information: Rishi R. Rawat et al. Correlating nuclear morphometric patterns with estrogen receptor status in breast cancer pathologic specimens, npj Breast Cancer (2018). DOI: 10.1038/s41523-018-0084-4

Related Stories

Researchers advocate for single-cell diagnostics for breast cancer

October 24, 2017
Women diagnosed with breast cancer may benefit from having the molecular subtype of different cells within their tumors identified, argue two researchers in an opinion article published October 24 in the journal Trends in ...

Prognostic role of elevated mir-24-3p in breast cancer

March 1, 2018
Despite improvements in local, regional and systemic therapies for breast cancer, 40,610 women are expected to die from metastatic breast cancer in the US in 2017.

How do hormones affect tumor DNA in men with breast cancer?

February 14, 2018
Breast cancer in men is rare, and men with breast cancer receive the same anti-hormonal therapy as women. Often with effect, but there was no scientific basis for it before now. Cancer researchers led by Wilbert Zwart from ...

Soybean consumption may be beneficial for some women with breast cancer

June 21, 2017
It can be confusing to know what to eat to lower your risk of breast cancer. Research is mixed, for example, on whether women should avoid soy foods, such as tofu and soybeans, or try to eat more of them. The question is ...

Novel therapeutic target discovered for estrogen receptor positive (ER+) breast cancer

November 17, 2017
Researchers at the Icahn School of Medicine at Mount Sinai have identified a protein that can be targeted to suppress growth of a common type of breast cancer known as "estrogen receptor positive" (ER+), including ER+ cancers ...

Discovery of potential treatment for aggressive form of breast cancer

November 2, 2016
A new drug could be used to treat one of the most aggressive forms of breast cancer, a research centre based at University College Dublin and St Vincent's Hospital has discovered.

Recommended for you

DNA vaccine leads to immune responses in HPV-related head and neck cancer

September 21, 2018
A therapeutic vaccine can boost antibodies and T cells, helping them infiltrate tumors and fight off human papillomavirus (HPV)-related head and neck cancer. Researchers from the Abramson Cancer Center of the University of ...

In zebrafish, a way to find new cancer therapies, targeting tumor modulators

September 21, 2018
The lab of Leonard Zon, MD, at Boston Children's Hospital has long been interested in making blood stem cells in quantity for therapeutic purposes. Looking for a way to test for their presence in zebrafish, their go-to research ...

What can salad dressing tell us about cancer? Think oil and vinegar

September 20, 2018
Researchers led by St. Jude Children's Research Hospital scientists have identified another way the process that causes oil to form droplets in water may contribute to solid tumors, such as prostate and breast cancer. The ...

Novel biomarker found in ovarian cancer patients can predict response to therapy

September 20, 2018
Despite months of aggressive treatment involving surgery and chemotherapy, about 85 percent of women with high-grade wide-spread ovarian cancer will have a recurrence of their disease. This leads to further treatment, but ...

Testing fluorescent tracers used to help surgeons determine edges of breast cancer tumors

September 20, 2018
A team of researchers with members from institutions in The Netherlands and China has conducted a test of fluorescent tracers meant to aid surgeons performing tumor removal in breast cancer patients. In their paper published ...

Cancer immunotherapy might benefit from previously overlooked immune players

September 20, 2018
Cancer immunotherapy—efforts to boost a patient's own immune system, allowing it to better fight cancer cells on its own—has shown great promise for some previously intractable cancers. Yet immunotherapy doesn't work ...


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.