Register Now: Image-Based Risk: The Next Frontier in Breast Cancer Screening
|Articles|December 1, 2003

CAD system screens for SARS

Deus Technologies has adapted its RapidScreen computer-aided detection system to find early signs of severe acute respiratory syndrome. Keying off its film-based CAD system for detecting lung lesions, Deus developed an automated method for identifying subtle initial SARS abnormalities that can be easily overlooked on chest x-rays.

 

Deus Technologies has adapted its RapidScreen computer-aided detection system to find early signs of severe acute respiratory syndrome. Keying off its film-based CAD system for detecting lung lesions, Deus developed an automated method for identifying subtle initial SARS abnormalities that can be easily overlooked on chest x-rays.

SARS in its advanced state is similar in appearance to disseminated pneumonia, which is easy to spot, according to Deus CEO Dr. Michael Yeh. At onset, however, the disease is confined to focal areas, and differences between small white areas that fill with water and black air-filled spaces are less clear.

The RapidScreen system has been programmed to detect early SARS on the basis of data gathered from Hong Kong, one of the major sites of the epidemic. In preliminary testing, the SARS system had a sensitivity close to 90% and an average false positive rate per image of 1.2%.

Related to this article

See the Real-World Impact of AI in Radiology
AI has to do more than show potential. It has to deliver measurable results.The Rad AI Outcomes and Market Impact Compendium brings together real-world clinical, operational and financial evidence from health systems, academic medical centers and radiology practices using Rad AI Reporting, Impressions and Continuity.Explore results including 60+ minutes saved per radiologist shift, a 47% reduction in report error rates, 70%+ patient follow-up adherence and >7x ROI — plus, case studies showing how organizations are translating AI into greater capacity, quality and financial performance.See what AI built specifically for radiology can deliver in practice.