Study Finds Robots can Detect Breast Cancer as well as Radiologists

Breast cancer is the most common cancer in women, and despite important improvements in therapy, it is still a major cause for cancer-related mortality, accounting for approximately 500,000 annual deaths worldwide. Breast cancer screening programs using mammography are effective in reducing breast cancer-related mortality. However, current screening programs are highly labor intensive due to the large number of women that have to be screened. Considering the increasing scarcity of breast screening radiologists in some countries, many researchers believe other screening methods may be worth investigating.

A new paper in the Journal of the National Cancer Institute suggests that artificial intelligence systems may be able to perform as accurately as radiologists in the evaluation of digital mammography in breast cancer screening.

Since the 1990s, computer-aided detection systems have been developed to detect and classify breast lesions in mammograms automatically. However, no studies to date have found that these systems directly improve screening performance or cost effectiveness. This has precluded their use as a method for screening mammography.

In this study researchers compare, at a case level, the cancer detection performance of a commercially available AI system to that of 101 radiologists who scored nine different cohorts of mammography examinations from four different manufacturers as part of studies previously performed for other purposes.

Each dataset consisted of mammography exams acquired with systems from four different vendors, multiple radiologists' assessments per exam, yielding a total of 2,652 exams (653 malignant) and interpretations by 101 radiologists (28,296 independent interpretations).

The performance of the artificial intelligence system was statistically not-inferior to that of the average of the 101 radiologists. The evaluated system achieved a cancer detection accuracy comparable to an average breast radiologist in this retrospective setting.

"Before we could decide what is the best way for AI systems to be introduced in the realm of breast cancer screening with mammography, we wanted to know how good can these systems really be," said Ioannis Sechopoulos, one of the paper's authors. "It was exciting to see that these systems have reached the level of matching the performance of not just radiologists, but of radiologists who spend at least a substantial portion of their time reading screening mammograms."

Alejandro Rodriguez-Ruiz, Kristina Lång, Albert Gubern-Merida, Mireille Broeders, Gisella Gennaro, Paola Clauser, Thomas H Helbich, Margarita Chevalier, Tao Tan, Thomas Mertelmeier, Matthew G Wallis, Ingvar Andersson, Sophia Zackrisson, Ritse M Mann, Ioannis Sechopoulos.
Stand-Alone Artificial Intelligence for Breast Cancer Detection in Mammography: Comparison With 101 Radiologists.
JNCI: Journal of the National Cancer Institute, djy222. doi: 10.1093/jnci/djy222.

Most Popular Now

What the Radiologist should Know about A…

This paper aims to provide a review of the basis for application of AI in radiology, to discuss the immediate ethical and professional impact in radiology, and to consider possible...

The Mobile Game that can Detect Alzheime…

A specially designed mobile phone game can detect people at risk of Alzheimer's - according to new research from the University of East Anglia. Researchers studied gaming data from an...

Hospital Diagnoses Critically Ill Childr…

The Rady Children’s Hospital (San Diego, USA) used Moon, software developed by the Leuven-based (Belgium) company Diploid. Moon is the first software worldwide to use Artificial Intelligence (AI) for the...

AstraZeneca Starts Artificial Intelligen…

AstraZeneca and BenevolentAI began a long-term collaboration to use artificial intelligence (AI) and machine learning for the discovery and development of new treatments for chronic kidney disease (CKD) and idiopathic...

Novartis Presents First-of-its-Kind Algo…

Novartis today announced results from a validation study of the innovative, algorithm-based digital solution MS Progression Discussion Tool, or MSProDiscussTM. The tool aims to support and facilitate a discussion between...

Bayer Joins Sensyne Health Consortium Wo…

Sensyne Health plc (LSE: SENS), the British clinical AI technology company, and Bayer, the life sciences company, announce that Bayer has become Sensyne Health's preferred pharmaceutical partner to work together...

Red Hat Helps Public Health England Use …

Red Hat, Inc. (NYSE: RHT), the world's leading provider of open source solutions, announced that Public Health England (PHE), an executive agency of the Department of Health and Social Care...

Chipmunk Health Chooses Philips HealthSu…

Royal Philips (NYSE: PHG, AEX: PHIA), a global leader in health technology, announced that telehealth service provider Chipmunk Health, with locations in the Netherlands and Canada, is leveraging the capabilities...

Siemens Healthineers and European Societ…

With their first course under the heading "Intelligence. Innovation. Imaging - The perfect vision of AI," held in Barcelona on April 5-6, Siemens Healthineers and the European Society of Radiology...

Mobile Prenatal App Shown to Reduce in-P…

Using the mobile app Babyscripts reduced in-person prenatal care visits while maintaining patient and provider satisfaction, according to research published in JMIR mHealth and uHealth by physician researchers from the...