Artificial intelligence is not designed to replace doctors (at least not in the near-future) however it can assist with medical examinations. New research suggests artificial intelligence is a reliable tool for use with 3D mammography, or digital breast tomosynthesis (DBT). This is to accurately detect breast cancer earlier, when it may be more easily treated.
The advantage with 3D mammography is that, unlike 2D mammography, which only produces 4 images, 3D tomosynthesis creates hundreds of images. This provides doctors with more information. However, in doing so this substantially increases the workload of medics when reading the scans, and the associated time delays can have a negative impact on patient care.
The opportunity to speed up the processing of image analysis is where artificial intelligence can assist. New software can quickly and accurately analyze each 3D mammography image to detect both malignant tumors.
An example of such technology is Profound AI™ for DBT. The new system is the first U.S. Food and Drug Administration (FDA) cleared DBT software using artificial intelligence. The technology can aid doctors to more accurately locate breast cancers sooner, when they may be more easily treated. The consequential time saving enables medics to ten spend more time with patients, rather than reading and assessing the mammography.
Based on successful clinical results, drawn from a large reader study involving ProFound AI for DBT, the system has been tested for its effectiveness. The results of the trial have been published in the journal Radiology: Artificial Intelligence. The research paper is titled “Improving Accuracy and Efficiency with Concurrent Use of Artificial Intelligence for Digital Breast Tomosynthesis.”
The study found ProFound AI for DBT increased sensitivity by 8 percent, reduced the rate of false positives and unnecessary recalls by 7.2 percent, and decreased reading time for radiologists by 52.7 percent. The platform therefore showed suitable sensitivity and specificity.