IRISeg
Intuitive Surgical Inc.IRISeg is a software application developed by Intuitive Surgical that utilizes machine learning to assist with the segmentation of contrast-enhanced kidney CT scans and generates 3D models for preoperative surgical planning and intraoperative display. It provides both automatic and manual tools to segment kidney structures, helping clinicians visualize anatomy more efficiently and accurately for better patient management.
Intended Use
IRISeg is intended for use as a software application that receives DICOM compliant contrast-enhanced CT images, provides manual and machine learning-enabled tools for image analysis and segmentation, and creates an output file that can be used to render a 3D model for preoperative surgical planning and intraoperative display. The use of IRISeg may include the generation of preliminary segmentations using machine learning algorithms. IRISeg is intended for use by qualified professionals. The output file is meant for visual, non-diagnostic use and shall be reviewed by clinicians who are responsible for all final patient management decisions. The machine learning enabled kidney CT auto-segmentation tool is intended for use for adult patients with contrast-enhanced, axial kidney CT images with slice thickness 3mm or less.
Technology
IRISeg is a standalone software application for segmentation of contrast-enhanced kidney CT images and generation of 3D virtual models. It uses neural network-based machine learning algorithms trained on clinical kidney CT data for automatic segmentation of four kidney structures (parenchyma, artery, vein, collecting system) and allows manual editing with various tools. It inputs DICOM CT images and outputs binary masks and files for 3D rendering. The ML algorithm output is an initial estimate refined manually. The software is designed following FDA guidance and includes manual and ML-based workflows.
Performance
Performance validation included software verification and validation per IEC 62304, machine learning auto-segmentation testing on 81 independent clinical kidney CT scans, cybersecurity testing per FDA guidance, and design validation. Algorithm performance was measured against radiologist segmentations using Sørensen–Dice Coefficient and Mean Distance to Agreement metrics, achieving artery DSC between 0.87-0.90, parenchyma DSC 0.95-0.97, vein DSC 0.87-0.89, and collecting system MDA 1.3-1.9. Testing demonstrated substantial equivalence to the predicate device and met acceptance criteria.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
8/19/2024
3 months - 2
FDA Approval
12/10/2024
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.