Pulmonary embolism AI tool from Aidoc obtains CE Mark

Artificial intelligence software to identify and prioritize pulmonary embolism (PE) in computed tomography pulmonary angiograms (CTPAs) from Aidoc has received CE Mark approval for sale in the Europe. By flagging obstructions in blood-flow to the lungs, the PE AI tool is designed to prioritize diagnostic workstation worklists and help radiologists detect critical conditions more rapidly, according to the Tel Aviv-based company.

The tool works automatically when images arrive for interpretation at a diagnostic workstation, independently prioritizing cases that require immediate attention. The Israeli company said that because PE diagnosis can be highly challenging due to its variable and non-specific presentation, AI-driven workflow triage is beneficial.

Radiologists at the University Hospital Basel in Switzerland conducted a validation study of the performance of deep convolutional neural networks to detect PE on CTPAs, which they discussed in a scientific session of the 2019 European Congress of Radiology held in Vienna in late February. T. J. Weikert, MD, and colleagues in the Department of Radiology tested prototype algorithms from Aidoc using a data set of 232 positive and 1,204 negative exams that were performed at the hospital in 2017. They reported that this type of PE AI tool was capable of detecting PEs with a high sensitivity and specificity.

“In a clinical setting, this can complement conventional workflows with a worklist prioritization and has the potential to improve the quality of healthcare by accelerating the diagnostic process and communication,” the authors wrote in an abstract. “We plan to further test the algorithm and finally implement it in the clinical routine to perform prospective evaluations.”¹

1. Weikert TJ, Winkel DJ, Bremerich J, et al. AI-powered detection of pulmonary embolism in CT pulmonary angiograms: a validation study of the diagnostic performance of prototype algorithms. ECR Online 2019 Programme.