Optellum Virtual Nodule Clinic, Optellum software, Optellum platform
Optellum LtdOptellum Virtual Nodule Clinic is an AI-powered software that helps medical professionals track, assess, and characterize pulmonary nodules detected incidentally in CT scans. It provides a malignancy likelihood score using a convolutional neural network to support clinical decision making, improving diagnostic accuracy and patient management workflows for lung nodules.
Intended Use
Virtual Nodule Clinic (VNC) is a software device used in the tracking, assessment and characterization of incidentally detected pulmonary nodules. It includes a CADx function for pulmonologists and radiologists that automatically analyzes user-selected ROIs in lung CT data to provide volumetric and computer analysis based on morphological characteristics. The AI calculates a LCP-CNN score indicating likelihood of malignancy, used as one input in clinical decision making, indicated for solid and semi-solid nodules 5-30mm in patients 35 years or older.
Technology
The device includes a web application and an LCP-CNN AI module deployed on GPU-equipped servers. The LCP-CNN is a convolutional neural network trained on CT images of solid and semi-solid nodules, outputting a malignancy score (1 to 10) based on imaging features extracted from user-selected regions of interest. The system connects to hospital PACS and RIS for image and report retrieval, displaying DICOM images without modification and allowing user interaction. The software runs on Linux servers and interfaces via web browsers.
Performance
Performance testing includes a clinical reader study with 12 readers (radiologists and pulmonologists) interpreting CT scans of 300 patients with incidental lung nodules. Use of the LCP-CNN score improved average diagnostic accuracy (AUC) by 6.85 points significantly (p<.001), with all readers improving consistency and decision-making accuracy. Standalone AI model testing showed an AUC of 0.867 for malignancy classification on a separate dataset. Usability, cybersecurity, and software validation testing demonstrated the device is safe and effective for intended clinical use.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
8/13/2020
6 months - 2
FDA Approval
3/5/2021
Ready to Sharpen Your Edge?
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.