AI software detects lung cancer on CT scans with 95% accuracy

Melissa Rohman | | Health Imaging | Artificial Intelligence

Engineers at the University of Central Florida (UCF)'s Center for Research in Computer Vision have developed an artificial intelligence (AI)-based system that can detect lung cancer in CT scans with 95 percent accuracy, according to a UCF news release.  

The engineers used strengthened connections created between brain neurons to help the system look for patterns and malignancies in the imaging scans, according to the release.  

More than 1,000 CT scans provided by a collaboration between the National Institutes (NIH) of Health and Mayo Clinic were used to train the software.  

The system is currently being fine-tuned to identify cancerous versus benign tumors. The team will present its research in September at the 2018 International Conference on Medical Imaging Computing and Computer Assisted Intervention (MICCAI) in Spain, according to the release.  

""
Melissa Rohman

A recent graduate from Dominican University (IL) with a bachelor’s in journalism, Melissa joined TriMed’s Chicago team in 2017 covering all aspects of health imaging. She’s a fan of singing and playing guitar, elephants, a good cup of tea, and her golden retriever Cooper.

Related Content

AI-based 3D CTA reconstruction solution scores FDA clearance
Overview of the regulatory landscape of AI in radiology
Medical imaging trends to watch in 2025
GPT-4 helps ensure recommendations for additional imaging aren't overlooked in reports
GPT-4 can proofread radiology reports for a penny apiece
Deep learning model halves lung tumor segmentation times

Around the web

Radiology Business
Medical imaging trends to watch in 2025

The healthcare market analysis firm Signify Research released a list of predictions in radiology its analysts expect to see in 2025. 

Radiology Business
Ultrasound-first strategy for noncalcified lesions in DBT proves cost-effective

Jessica Porembka, MD, of the breast imaging division at University of Texas Southwestern Medical Center, said an ultrasound-first strategy for these lesions in DBT is cost-effective and improves efficiency. 

Radiology Business
Concerns about private equity's growing influence in radiology

Melissa Davis, MD, vice chair of medical informatics and associate professor at Yale University’s Department of Radiology and Biomedical Imaging, shares her findings from research on private equity market penetration.