We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress
Sign In
Advertise with Us
GLOBETECH PUBLISHING LLC

Download Mobile App




Study Reveals Value of Using Both Human and AI in Detecting Breast Cancer

By MedImaging International staff writers
Posted on 29 Apr 2022
Print article
Image: Radiologists and AI systems show differences in breast-cancer screenings (Photo courtesy of Unsplash)
Image: Radiologists and AI systems show differences in breast-cancer screenings (Photo courtesy of Unsplash)

Radiologists and artificial intelligence (AI) systems yield significant differences in breast-cancer screenings, according to a new study, revealing the potential value of using both human and AI methods in making medical diagnoses.

The analysis by a team of researchers at New York University (New York, NY, USA) 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.” The scientists compared breast-cancer screenings read by radiologists with those analyzed by DNNs.

The researchers found that DNNs and radiologists diverged significantly in how they diagnose a category of malignant breast cancer called soft tissue lesions. 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.

“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 major bottleneck in moving AI systems into the clinical workflow is in understanding their decision-making and making them more robust,” added 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.”

“In these breast-cancer screenings, AI systems consider tiny details in mammograms that are seen as irrelevant by radiologists,” explained Krzysztof Geras, Ph.D., faculty in NYU Grossman School of Medicine’s Department of Radiology. “This divergence in readings must be understood and corrected before we can trust AI systems to help make life-critical medical decisions.”

Related Links:
New York University 

New
Gold Supplier
Electrode Solution and Skin Prep
Signaspray
Gold Supplier
Ultrasound System
FUTUS LE
New
Body Array Coil
12-Channel Body Array Coil 1.5 / 3.0 T
New
X-Ray System
Leonardo DR mini III

Print article
Radcal

Channels

Radiography

view channel
Image: The new reporting style (A) vs. the standard dictaction style (B) (Photo courtesy of FIU)

New Reporting Style Improves Accuracy and Speed of Reading Radiology Scans

Certain health issues, such as calcified arteries, infections, minor bone fractures, or cancerous tumors, often remain hidden within our bodies. Special imaging techniques like X-rays, MRIs, or CT scans... Read more

MRI

view channel
Image: Self-folding mechanism leads to enhanced contrast in MRI scans (Photo courtesy of Tokyo Tech)

Breakthrough in Nanosized Contrast Agents to Enhance Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) plays a vital role in cancer diagnosis by capturing detailed images of soft tissues. For enhanced tumor visibility in MRI scans, doctors often administer contrast agents to patients.... Read more

Ultrasound

view channel
Image: A schematic diagram of the experimental setup (Photo courtesy of Moslem Sadeghi Goughari)

First AI-Powered Ultrasound Technique Destroys Wide Range of Deadly Cancerous Tumors

Focused ultrasound treatment, which employs high-frequency sound waves to generate a strong beam that heats and destroys cancer cells, has been a treatment option since the 1970s. It's been applied to... Read more

Nuclear Medicine

view channel
Image: Radiotherapy may improve heart function by reducing inflammatory immune cells (Photo courtesy of 123RF)

Low-Dose Radiation Therapy Demonstrates Potential for Treatment of Heart Failure

Millions of people are living with heart failure, a condition where the heart progressively loses its capacity to effectively circulate oxygenated blood throughout the body. Heart failure can arise from... Read more

Imaging IT

view channel
Image: The new Medical Imaging Suite makes healthcare imaging data more accessible, interoperable and useful (Photo courtesy of Google Cloud)

New Google Cloud Medical Imaging Suite Makes Imaging Healthcare Data More Accessible

Medical imaging is a critical tool used to diagnose patients, and there are billions of medical images scanned globally each year. Imaging data accounts for about 90% of all healthcare data1 and, until... Read more

Industry News

view channel
Image: Attendees can discover innovative products and technology in the RSNA 2023 Technical Exhibits (Photo courtesy of RSNA)

RSNA 2023 Technical Exhibits to Offer Innovations in AI, 3D Printing and More

The 109th Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA, Oak Brook, IL, USA) to be held in Chicago, Nov. 26 to 30 is all set to offer a vast array of medical... Read more
Copyright © 2000-2023 Globetech Media. All rights reserved.