AI may reduce unnecessary chest X-rays by 30%

by John R. Fischer, Senior Reporter | August 13, 2021
Artificial Intelligence X-Ray
Lunit's deep learning-based AI system can help radiologists reduce unnecessary CT scans and help radiologist residents recommend more proper CT scans for potential lung cancer patients
Lunit’s deep learning-based AI algorithm could help do away with 30% of chest X-rays that are unnecessary.

The South Korean company and researchers at Massachusetts General Hospital said this in a new study, which found that Lunit INSIGHT CXR’s high specificity helped radiologists tamp down unnecessary CT scans. Its high sensitivity also helped radiologist residents properly recommend more CT exams for potential lung cancer patients.

The multi-reader study is titled AI-based improvement in lung cancer detection on chest radiographs: results of a multi-reader study in NLST data set.
DOTmed text ad

Reveal Mobi Pro now available for sale in the US

Reveal Mobi Pro integrates the Reveal 35C detector with SpectralDR technology into a modern mobile X-ray solution. Mobi Pro allows for simultaneous acquisition of conventional & dual-energy images with a single exposure. Contact us for a demo at no cost.

"According to various studies, Lunit INSIGHT CXR and Lunit INSIGHT MMG - another product of ours - can increase the earlier detection of the disease by up to 20%(chest and breast). It also helps the cost reduction by reducing the reading time by 40%," Lunit told HCB News.

These capabilities, according to LUnit, can help avoid unnecessary radiation exposure for patients and eliminate excessive medical costs for healthcare systems.

The AI algorithm was used to assess 519 images of cancer-positive and cancer-negative patients. Three radiology residents and five board-certified radiologists participated as readers. Due to the sensitivity of the algorithm, radiology residents were able to recommend 28% more appropriate CT exams for patients with potential cases of lung cancer. Radiologists were able to reduce unnecessary CT exams by 30% due to its specificity.

Lunit INSIGHT CXR was trained on more than 3.5 million medical data and can detect 10 major chest diseases, including lung nodules, pneumothorax and tuberculosis with 97%-99% accuracy. Used in over 300 hospitals and medical centers in more than 30 countries, the software is CE marked and approved for commercial sales in around 35 countries. Lunit expects it to gain FDA approval within the year.

"An accurate analysis through Lunit INSIGHT CXR can help medical professionals provide diagnosis to patients with increased efficiency — preventing potential cancer at an early stage, while saving time and cost for those who do not need a further examination,” said Brandon Suh, CEO of Lunit.

The study is a follow-up to a previous study that validated the accuracy of AI and proved that Lunit Insight CXR, used to analyze chest X-rays, can accurately detect malignant pulmonary nodules, which lead to lung cancer.

You Must Be Logged In To Post A Comment