Research at the MGH is interwoven throughout more than 30 departments, centers and units, and is conducted with the support and guidance of the MGH Research Institute. The Research Roundup is a monthly series highlighting studies, news and events.
Researchers Use Machine Learning to Improve Breast Cancer Screening Techniques
The current standard treatment for high-risk breast lesions – areas of tissue that appear suspicious on a mammogram and have abnormal but not cancerous cells when tested by needle biopsy – is surgical removal. However, after undergoing this painful procedure, many women learn their surgery was unnecessary, as 90 percent of lesions end up being benign.
A change in the standard of care could be on the horizon thanks to a team of researchers at the MGH and MIT Computer Science and Artificial Intelligence Laboratory. They have harnessed the power of artificial intelligence (AI) to develop a more accurate and less invasive screening method for high-risk lesions.
The team developed an AI system that uses machine learning to distinguish between high-risk lesions that need to be surgically removed and those that should just be watched over time. This is the first study to apply machine learning to the task of distinguishing high-risk lesions.
The system correctly diagnosed 97 percent of 335 high-risk breast lesions as malignant and reduced the number of unnecessary surgeries by more than 30 percent, compared to existing approaches. These results recently were published in Radiology.
MGH radiologists will begin incorporating the model into their clinical practice throughout the next year.
Liquid Biopsies Give Clues on When and Why Cancer Treatments Lose their Efficacy
Many cancer patients eventually develop resistance to their treatments. To help oncologists quickly and accurately identify early signs of treatment resistance, researchers have developed a new liquid biopsy diagnostic tool. A team from the MGH Cancer Center is providing confirmatory data that may help to move liquid biopsies into clinical practice. These data were presented at the ESMO 19th World Congress on Gastrointestinal Cancer.
One type of liquid biopsy detects circulating tumor DNA (ctDNA) – genetic material released by dying tumor cells that flows through the bloodstream. ctDNA can provide early evidence that a treatment is no longer working. It also offers a more complete picture of the genetic changes in tumor cells that are driving the resistance to treatment, which could guide new treatment courses.
To test the efficacy of ctDNA testing, the Cancer Center investigators followed nearly 40 patients with various forms of gastrointestinal cancers who had experienced initial success with targeted therapies, but then began to show signs of treatment resistance. Using liquid biopsies, researchers identified one or more mutations or mechanisms that contributed to treatment resistance in 31 of the 40 patients, and 14 patients had multiple mutations contributing to resistance.
“Identifying what specific mutations are responsible for treatment resistance is very important in helping clinicians choose what treatment path a patient should try next,” said study investigator Aparna Parikh, MD, of the MGH Cancer Center.
Parikh says the next step is to study how best to use this new technology in daily practice.
Read more articles from the 12/15/17 Hotline issue.