About Careers MedBlog Contact us
Medindia LOGIN REGISTER
Advertisement

Artificial Intelligence Can Detect Breast Cancer Accurately as Radiologists

by Iswarya on March 6, 2019 at 11:08 AM
Font : A-A+

Artificial Intelligence Can Detect Breast Cancer Accurately as Radiologists

Artificial intelligence (AI) systems may be able to perform as precisely as radiologists in the evaluation of digital mammography in breast cancer screening, reports a new study. The findings of the study are published in the Journal of the National Cancer Institute.

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.

Advertisement


Breast cancer screening programs using mammography are effective in reducing breast cancer-related mortality. However, current screening programs are highly labor intensive due to a 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.

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.
Advertisement

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."

Source: Eurekalert
Advertisement

Advertisement
Advertisement

Recommended Reading

Latest Cancer News

Could TKI Cancer Drugs Lead to Inflammatory Side Effects?
The mechanism by which the kinases cause inflammation has been discovered by scientists.
Are Biomarkers the Key to Identifying Early Pancreatic Risk?
Pancreatic cancer cases are on the rise. The biomarker approach could reduce the chance of developing pancreatic cancer.
How Does New Drugs Work Together to Reduce Lung Tumors?
New combination of medications trametinib and entinostat were found to decrease lung cancer in mice.
New Combination Therapy Proves Effective Against Prostate Cancer
Combination treatment with TALZENNA and XTANDI was found to benefit prostate cancer patients, revealed study.
Can Vitamin A Rich Diet Help Reduce Pancreatitis Risk
In leukemia patients, reduced amounts of dietary vitamin A is associated with a higher risk and severity of pancreatitis.
View All
This site uses cookies to deliver our services.By using our site, you acknowledge that you have read and understand our Cookie Policy, Privacy Policy, and our Terms of Use  Ok, Got it. Close
×

Artificial Intelligence Can Detect Breast Cancer Accurately as Radiologists Personalised Printable Document (PDF)

Please complete this form and we'll send you a personalised information that is requested

You may use this for your own reference or forward it to your friends.

Please use the information prudently. If you are not a medical doctor please remember to consult your healthcare provider as this information is not a substitute for professional advice.

Name *

Email Address *

Country *

Areas of Interests