Combination of AI & Radiologists more Accurately Identified Breast Cancer

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.

Nan Wu, Jason Phang, Jungkyu Park, Yiqiu Shen, Zhe Huang, Masha Zorin, Stanisław Jastrzębski, Thibault Févry, Joe Katsnelson, Eric Kim, Stacey Wolfson, Ujas Parikh, Sushma Gaddam, Leng Leng Young Lin, Kara Ho, Joshua D. Weinstein, Beatriu Reig, Yiming Gao, Hildegard Toth Kristine Pysarenko, Alana Lewin, Jiyon Lee, Krystal Airola, Eralda Mema, Stephanie Chung, Esther Hwang, Naziya Samreen, S Gene Kim, Laura Heacock, Linda Moy, Kyunghyun Cho.
Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening.
IEEE Transactions on Medical Imaging. doi: 10.1109/TMI.2019.2945514.

Most Popular Now

Philips Launches HealthSuite Clinical Tr…

Royal Philips (NYSE: PHG, AEX: PHIA), a global leader in health technology, announced Clinical Trial Accelerator on Philips HealthSuite. This new tailored set of capabilities allows life science organizations to...

New AI Diagnostic can Predict COVID-19 w…

Researchers at King's College London, Massachusetts General Hospital and health science company ZOE have developed an artificial intelligence diagnostic that can predict whether someone is likely to have COVID-19 based...

Biomax Provides AI-Based Semantic Search…

The bioinformatics company Biomax, headquartered in Planegg, Germany, makesitssemantic search platform AILANI available free of charge to research institutes around the world in order to support the rapid and successful...

COVID-19 and Health Tech: Building on th…

Highland Marketing's advisory board met to discuss the health tech response to the coronavirus outbreak. In many areas, this has been hugely impressive: but there are gaps, and there will...

InsurTech Hub Munich and dmac/Digital He…

InsurTech Hub Munich (ITHM) and dmac - Medical Valley Digital Health Application Center part of the Digital Health Hub Nuremberg/Erlangen announce a new cross-industry accelerator for the second half of...

Viveo Health Offers Free Telemedicine So…

Viveo Health, a global e-Health innovator, is making its 'Virtual Office for Doctors' platform free of charge to doctors and other medical professionals worldwide in light of the surge in...

Telemedicine Transforms Response to COVI…

A rapid increase in "virtual" visits during the COVID-19 pandemic could transform the way physicians provide care in the United States going forward, according to a new study led by...

The Dedalus Group, Participated by Ardia…

The Dedalus Group, a leading European company, and one of the worldwide main ones, active in clinical healthcare information systems to support clinical professionals and organizations in order to improve...

Supercomputer Simulations Present Potent…

Several drugs approved for treating hepatitis C viral infection were identified as potential candidates against COVID-19, a new disease caused by the SARS-CoV-2 coronavirus. This is the result of research...

The COVID-19 pandemic reveals the potent…

Two new articles provide insights on the use of telehealth or virtual care in the age of COVID-19 and beyond, pointing to its value to not only prevent contagious diseases...

DigiConnect: e-healthcare - 24/7 Health …

Given the current outbreak of COVID-19, healthcare providers in the Middle East along with the rest of the world are currently putting relentless efforts to provide an innovative offering that...

WiFi SPARK Works with Visionable to Conn…

Seven NHS Trusts are using technology developed by WiFi SPARK in response to an urgent request from leading NHS Trusts to find a way to connect hospital patients with their...