Nav: Home

Combination of AI & radiologists more accurately identified breast cancer

October 17, 2019

An artificial intelligence (AI) tool--trained on roughly a million screening mammography images--identified breast cancer with approximately 90 percent accuracy when combined with analysis by radiologists, a new study finds.

Led by researchers from NYU School of Medicine and the NYU Center for Data Science, the study examined the ability of a type of AI, a machine learning computer program, to add value to the diagnoses reached by a group of 14 radiologists as they reviewed 720 mammogram images.

"Our study found that AI identified cancer-related patterns in the data that radiologists could not, and vice versa," says senior study author Krzysztof J. Geras, PhD, assistant professor in the Department of Radiology at NYU Langone.

"AI detected pixel-level changes in tissue invisible to the human eye, while humans used forms of reasoning not available to AI," adds Dr. Geras, also an affiliated faculty member at the NYU Center for Data Science. "The ultimate goal of our work is to augment, not replace, human radiologists."

In 2014, more than 39 million mammography exams were performed in the United States to screen women (without symptoms) for breast cancer and determine those in need of closer follow-up. Women whose test results yield abnormal mammography findings are referred for biopsy, a procedure that removes a small sample of breast tissue for laboratory testing.

A New Tool to Identify Breast Cancer

In the new study, the research team designed statistical techniques that let their program "learn" how to get better at a task without being told exactly how. Such programs build mathematical models that enable decision-making based on data examples fed into them, with the program getting "smarter" as it reviews more and more data.

Modern AI approaches, inspired by the human brain, use complex circuits to process information in layers, with each step feeding information into the next, and assigning more or less importance to each piece of information along the way.

Published online recently by the journal IEEE Transactions on Medical Imaging, the current study authors trained their AI tool on many images matched with the results of biopsies performed in the past. Their goal was to enable the tool to help radiologists reduce the number biopsies needed moving forward. This can only be achieved, says Dr. Geras, by increasing the confidence that physicians have in the accuracy of assessments made for screening exams (for example, reducing false-positive and false-negative results).

For the current study, the research team analyzed images that had been collected as part of routine clinical care at NYU Langone Health over seven years, sifting through the collected data and connecting the images with biopsy results. This effort created an extraordinarily large dataset for their AI tool to train on, say the authors, consisting of 229,426 digital screening mammography exams and 1,001,093 images. Most databases used in studies to date have been limited to 10,000 images or fewer.

Thus, the researchers trained their neural network by programming it to analyze images from the database for which cancer diagnoses had already been determined. This meant that researchers knew the "truth" for each mammography image (cancer or not) as they tested the tool's accuracy, while the tool had to guess. Accuracy was measured in the frequency of correct predictions.

In addition, the researchers designed the study AI model to first consider very small patches of the full resolution image separately to create a heat map, a statistical picture of disease likelihood. Then the program considers the entire breast for structural features linked to cancer, paying closer attention to the areas flagged in the pixel-level heat map.

Rather than have the researchers identify image features for their AI to search for, the tool is discovering on its own which image features increase prediction accuracy. Moving forward, the team plans to further increase this accuracy by training the AI program on more data, perhaps even identifying changes in breast tissue that are not yet cancerous but have the potential to be.

"The transition to AI support in diagnostic radiology should proceed like the adoption of self-driving cars--slowly and carefully, building trust, and improving systems along the way with a focus on safety," says first author Nan Wu, a doctoral candidate at the NYU Center for Data Science.
-end-
Along with Dr. Geras, study authors from the Department of Radiology at NYU Langone were Eric Kim, Stacey Wolfson, Ujas Parikh, Sushma Gaddam, Leng Young Lin, Joshua Weinstein, Krystal Airola, Eralda Mema, Stephanie H. Chung, Esther Hwang, Naziya Samreen, Beatriu Reig, Yiming Gao, Hildegard B. Toth, Kristine M. Pysarenko, Alana A. Lewin, Jiyon Lee, S. Gene Kim, Laura Heacock, and Linda Moy. Authors from the NYU Center for Data Science were Nan Wu, Jason Phang, Jungkyu Park, Yiqiu Shen, Zhe Huang, Thibault Févry, and Kyunghyun Cho, who is also on the faculty of NYU Courant Institute of Mathematical Sciences. Other authors were Kara Ho at SUNY Downstate College of Medicine; Masha Zorin in the Department of Computer Science and Technology at the University of Cambridge; Stanisław Jastrzębski from Jagiellonian University; and Joe Katsnelson in the Department of Information Technology at NYU Langone.

The model used in this study is available to the field at https://github.com/nyukat/breast_cancer_classifier.

NYU Langone Health / NYU School of Medicine

Related Breast Cancer Articles:

Breast cancer: AI predicts which pre-malignant breast lesions will progress to advanced cancer
New research at Case Western Reserve University in Cleveland, Ohio, could help better determine which patients diagnosed with the pre-malignant breast cancer commonly as stage 0 are likely to progress to invasive breast cancer and therefore might benefit from additional therapy over and above surgery alone.
Partial breast irradiation effective treatment option for low-risk breast cancer
Partial breast irradiation produces similar long-term survival rates and risk for recurrence compared with whole breast irradiation for many women with low-risk, early stage breast cancer, according to new clinical data from a national clinical trial involving researchers from The Ohio State University Comprehensive Cancer Center - Arthur G.
Breast screening linked to 60 per cent lower risk of breast cancer death in first 10 years
Women who take part in breast screening have a significantly greater benefit from treatments than those who are not screened, according to a study of more than 50,000 women.
More clues revealed in link between normal breast changes and invasive breast cancer
A research team, led by investigators from Georgetown Lombardi Comprehensive Cancer Center, details how a natural and dramatic process -- changes in mammary glands to accommodate breastfeeding -- uses a molecular process believed to contribute to survival of pre-malignant breast cells.
Breast tissue tumor suppressor PTEN: A potential Achilles heel for breast cancer cells
A highly collaborative team of researchers at the Medical University of South Carolina and Ohio State University report in Nature Communications that they have identified a novel pathway for connective tissue PTEN in breast cancer cell response to radiotherapy.
Computers equal radiologists in assessing breast density and associated breast cancer risk
Automated breast-density evaluation was just as accurate in predicting women's risk of breast cancer, found and not found by mammography, as subjective evaluation done by radiologists, in a study led by researchers at UC San Francisco and Mayo Clinic.
Blood test can effectively rule out breast cancer, regardless of breast density
A new study published in PLOS ONE demonstrates that Videssa® Breast, a multi-protein biomarker blood test for breast cancer, is unaffected by breast density and can reliably rule out breast cancer in women with both dense and non-dense breast tissue.
Study shows influence of surgeons on likelihood of removal of healthy breast after breast cancer dia
Attending surgeons can have a strong influence on whether a patient undergoes contralateral prophylactic mastectomy after a diagnosis of breast cancer, according to a study published by JAMA Surgery.
Young breast cancer patients undergoing breast conserving surgery see improved prognosis
A new analysis indicates that breast cancer prognoses have improved over time in young women treated with breast conserving surgery.
Does MRI plus mammography improve detection of new breast cancer after breast conservation therapy?
A new article published by JAMA Oncology compares outcomes for combined mammography and MRI or ultrasonography screenings for new breast cancers in women who have previously undergone breast conservation surgery and radiotherapy for breast cancer initially diagnosed at 50 or younger.
More Breast Cancer News and Breast Cancer Current Events

Top Science Podcasts

We have hand picked the top science podcasts of 2019.
Now Playing: TED Radio Hour

In & Out Of Love
We think of love as a mysterious, unknowable force. Something that happens to us. But what if we could control it? This hour, TED speakers on whether we can decide to fall in — and out of — love. Guests include writer Mandy Len Catron, biological anthropologist Helen Fisher, musician Dessa, One Love CEO Katie Hood, and psychologist Guy Winch.
Now Playing: Science for the People

#542 Climate Doomsday
Have you heard? Climate change. We did it. And it's bad. It's going to be worse. We are already suffering the effects of it in many ways. How should we TALK about the dangers we are facing, though? Should we get people good and scared? Or give them hope? Or both? Host Bethany Brookshire talks with David Wallace-Wells and Sheril Kirschenbaum to find out. This episode is hosted by Bethany Brookshire, science writer from Science News. Related links: Why Climate Disasters Might Not Boost Public Engagement on Climate Change on The New York Times by Andrew Revkin The other kind...
Now Playing: Radiolab

An Announcement from Radiolab