News | Breast Imaging | April 29, 2022

Analysis points to potential of human-tech complementary approach to detecting cancer

In these three examples of soft tissue lesions, the images are unperturbed on the left column and blurred on the right column. The AI system was sensitive to the blurring, while the radiologists were not. This showed that the AI system relies on details in soft tissue lesions that are considered irrelevant by the radiologists. Image courtesy of Taro Makino, NYU’s Center for Data Science

In these three examples of soft tissue lesions, the images are unperturbed on the left column and blurred on the right column. The AI system was sensitive to the blurring, while the radiologists were not. This showed that the AI system relies on details in soft tissue lesions that are considered irrelevant by the radiologists. Image courtesy of Taro Makino, NYU’s Center for Data Science


April 29, 2022 — Radiologists and artificial intelligence systems yield significant differences in breast cancer screenings, a team of researchers has found. Its work, which appears in the journal Nature Scientific Reports, reveals the potential value of using both human and AI methods in making medical diagnoses. 

“While AI may offer benefits in healthcare, its decision-making is still poorly understood,” explains Taro Makino, a doctoral candidate in NYU’s Center for Data Science and the paper’s lead author. “Our findings take an important step in better comprehending how AI yields medical assessments and, with it, offer a way forward in enhancing cancer detection.”

The analysis centered on a specific AI tool: Deep neural networks (DNNs), which are layers of computing elements—“neurons”—simulated on a computer. A network of such neurons can be trained to “learn” by building many layers and configuring how calculations are performed based on data input—a process called “deep learning.” 

In the Nature Scientific Reports work, the scientists compared breast-cancer screenings read by radiologists with those analyzed by DNNs. 

The researchers, who also included Krzysztof Geras, Ph.D., Laura Heacock, MD, and Linda Moy, MD, faculty in NYU Grossman School of Medicine’s Department of Radiology, found that DNNs and radiologists diverged significantly in how they diagnose a category of malignant breast cancer called soft tissue lesions.

“In these breast-cancer screenings, AI systems consider tiny details in mammograms that are seen as irrelevant by radiologists,” explains Geras. “This divergence in readings must be understood and corrected before we can trust AI systems to help make life-critical medical decisions.”

More specifically, while radiologists primarily relied on brightness and shape, the DNNs used tiny details scattered across the images. These details were also concentrated outside of the regions deemed most important by radiologists.

By revealing such differences between human and machine perception in medical diagnosis, the researchers moved to close the gap between academic study and clinical practice.

“Establishing trust in DNNs for medical diagnosis centers on understanding whether and how their perception is different from that of humans,” says Moy. “With more insights into how they function, we can both better recognize the limits of DNNs and anticipate their failures.” 

“The major bottleneck in moving AI systems into the clinical workflow is in understanding their decision-making and making them more robust,” adds Makino. “We see our research as advancing the precision of AI’s capabilities in making health-related assessments by illuminating, and then addressing, its current limitations.”

For more information: www.nyu.edu

Related Breast Imaging with AI Content:

AI Shows Potential in Breast Cancer Screening Programs

Artificial Intelligence Tool Improves Accuracy of Breast Cancer Imaging

Southwest Diagnostic Imaging Center Uses Artificial Intelligence to Optimize Breast Tomosynthesis Interpretations

AI Provides Accurate Breast Density Classification


Related Content

Feature | Radiology Imaging

View the September/October digital edition of Imaging Technology News (ITN), including links to videos, comparison ...

Time September 29, 2022
arrow
News | Radiation Oncology

September 28, 2022 — Populations in U.S. counties defined as more vulnerable based on social factors including ...

Time September 28, 2022
arrow
News | Breast Imaging

September 26, 2022 — The U.S. Food and Drug Administration (FDA) has granted QT Imaging, Inc. 510(K) clearance to ...

Time September 26, 2022
arrow
News | Breast Density

September 22, 2022 — DenseBreast-info.org (DB-i) announced that it will host the inaugural #WorldDenseBreastDay on ...

Time September 22, 2022
arrow
Feature | Information Technology | By Jef Williams

I took my family to Blockbuster this weekend to pick out a movie, hoping there would be something good left to rent ...

Time September 21, 2022
arrow
News | Ultrasound Women's Health

September 21, 2022 — Butterfly Network, Inc. (NYSE: BFLY), a digital health company transforming care through the power ...

Time September 21, 2022
arrow
Feature | Breast Imaging | By Christine Book

Findings from a clinical trial that used artificial intelligence (AI) in an effort to reduce false positives on breast ...

Time September 21, 2022
arrow
Feature | Digital Pathology | By Michael Valante

With digital pathology now being adopted by institutions around the globe, it is not surprising that we are seeing a ...

Time September 21, 2022
arrow
News | MRI Breast

September 16, 2022 — According to ARRS’ American Journal of Roentgenology (AJR), the contrast-enhanced in-phase Dixon ...

Time September 16, 2022
arrow
Feature | Artificial Intelligence | By Christine Book

What follows is the second part of our coverage of the “Radiology: Artificial Intelligence Fireside Chat” conducted at ...

Time September 16, 2022
arrow
Subscribe Now