Riverain Technologies is touting study results showing their ClearRead Bone Suppression software may improve radiologists’ pneumonia diagnosis rates.
Riverain Technologies is touting study results showing their ClearRead Bone Suppression software may improve radiologists’ pneumonia diagnosis rates. The tool makes lung tissue more visible by decreasing the appearance of bones on chest X-rays.
Through an algorithm that analyzes the lungs for structures resembling ribs and clavicles, ClearRead Bone Suppression creates an estimated bone image for use in the X-ray. That reduced image boosts the appearance of soft lung tissue, and with less obvious images of ribs and clavicles, radiologists can more easily spot small lung opacities that indicate the presence of pneumonia, according to the company.
Treating pneumonia early is often critical to patient survival. The Centers for Disease Control and Prevention estimates 50,000 people die annually from the illness. However, spots of pneumonia can hide behind bone, often limiting treatment capabilities. Company research, published online by European Radiology, indicates using ClearRead Bone Suppression results in a statistically significant increase in pneumonia diagnoses.
In the study, radiologists reviewed chest X-rays of 36 patients with 46 focal densities due to pneumonia, and X-rays of 20 patients without pneumonia. They then reviewed them using ClearRead Bone Suppression and observations were compared using the receiver operating characteristic (ROC) curve. The mean value of the area under the ROC curve was 0.844 using standard chest X-ray, and 0.880 with the addition of the software, the company said.
The improvement was statistically significant, which a study co-author said will “translate into significant improvement in actual practice.”
Other companies, such as FujiFilm Medical Systems USA, are using dual-energy imaging to better identify pneumonia spots. Dual-energy uses images taken at different energy levels to differentiate between bone and soft tissue.
AI Mammography Platform Shows Promising Results for Detecting Subclinical Breast Cancer
October 3rd 2024Mean artificial intelligence (AI) scoring for breasts developing cancer was double that of contralateral breasts at initial biennial screening and was 16 times higher at the third biennial screening, according to a study involving over 116,000 women with no prior history of breast cancer.
FDA Clears Software for Enhancing CCTA Assessment of Atherosclerosis
October 1st 2024Through analysis of coronary computed tomography angiography (CCTA) images, the PlaqueIQ software provides quantification and classification of atherosclerosis, a common cause of myocardial infarction (MI) and ischemic stroke.