Intended Use

Analyze scanned histopathology whole slide images from prostate core needle biopsies to identify cases initially diagnosed as benign for further pathological review by flagging tissue suspicious for prostate adenocarcinoma with heatmaps.

Technology

The device is a cloud-hosted software using a deterministic deep convolutional neural network architecture developed to analyze digitized whole slide images from H&E-stained prostate biopsies. It processes WSIs scanned by Philips Ultra Fast Scanner, delivering binary likelihood classification for presence of prostate adenocarcinoma and generates heatmaps highlighting suspicious regions, intended to augment pathologist review.

Performance

Performance testing included analytical studies demonstrating high precision and localization accuracy in identifying prostate adenocarcinoma in WSIs, and clinical validation showing improved detection sensitivity by pathologists assisted by the device. Sensitivity of the AI tool at slide level was around 81%, and pathologists using the tool showed sensitivity improvement versus standard care.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    5/2/2024

    8 months
  • 2

    FDA Approval

    1/24/2025

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.