(93 days)
EndoNaut provides image guidance by overlaying preoperative 3D vessel anatomy onto live fluoroscopic images in order to assist in the positioning of the guidewires, catheters and other endovascular devices.
EndoNaut is intended to assist endovascular procedures in the thorax, abdomen, neck, pelvis and lower limbs. Suitable procedures include (but not limited to) endovascular aortic aneurysm repair (AAA and TAA), angioplasty, stenting and embolization in iliac arteries and corresponding veins.
EndoNaut is not intended for use in the X-ray guided procedures in the liver, kidneys or pelvic organs.
EndoNaut is a stand-alone software medical device that runs on a Windows based computer that meets the minimum requirements.
EndoNaut software provides navigation tools for image-guided endovascular surgery. The device enables to register the X-ray intra-operative images and the pre-operative data.
The device is operated by the physician or a trained operator. The client machine captures a live fluoroscopy video feed from the X-ray's machine external video port, either in digital or in analog format. Any machine that meets the hardware and software requirements can be supported.
The EndoNaut will be marketed as a software only solution.
Below is a summary of the acceptance criteria and study information for the EndoNaut device, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Performance Metric | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Registration Accuracy | Registration error less than 3mm | Results meet the acceptance criteria |
| Panorama Creation Error | Maximum acceptable error of 10mm for peripheral artery surgery | Mean errors below the acceptance criteria |
| Measuring Functions (Distance) | No error for distance measurement along centerline (compared to planning tool) | Results meet the acceptance criteria |
| Measuring Functions (Length on Image) | Max error 1mm for length measurements on images (compared to visible rule) | Results meet the acceptance criteria |
| Software Compliance | Compliance with ISO 14971, IEC 62304, IEC 62366, and FDA Guidance for Software Contained in Medical Devices | Software verification and validation testing performed, demonstrating compliance with these standards and usability testing with clinical users. |
| Clinical Feasibility | Feasibility of fusion imaging during aortic endovascular procedures (Primary Endpoint) | Clinical study conclusion confirms the device is safe and effective and supports the indications for use, implying feasibility was achieved. (Specific percentage not provided) |
| Clinical Efficiency | Evaluation of efficiency in deploying infrarenal aortic stent grafts to treat unruptured atheromatous aneurysms (Secondary Endpoint: radiation dose) | Clinical study conclusion confirms the device is safe and effective and supports the indications for use. (Specific improvement in radiation dose not provided, but implies efficiency was found acceptable) |
2. Sample Sizes and Data Provenance
-
Test Set (for Technical Performance - Registration Accuracy):
- Sample Size: 5000 different registrations on 100 pre-operative CT-scan images from 50 patients.
- Data Provenance: Not explicitly stated (e.g., country of origin). Appears to be retrospective, using existing CT-scan images.
-
Test Set (for Technical Performance - Panorama Creation):
- Sample Size: 7 cases (6 patients and 1 phantom).
- Data Provenance: Not explicitly stated. The use of "in-vivo data" suggests patient data, likely retrospective or collected specifically for this purpose.
-
Test Set (for Clinical Study):
- Sample Size: Not explicitly stated, though it is described as a "single-centre, prospective feasibility pilot study."
- Data Provenance: Prospective, single-center study. Location not specified.
3. Number of Experts and Qualifications for Ground Truth (Test Set)
- Technical Performance (Registration Accuracy): Not applicable. The ground truth was a "gold standard transformation matrix," which suggests a numerically derived or calculated reference, not directly established by human experts in this context.
- Technical Performance (Panorama Creation): One "perfect panorama (manually corrected)" was used as ground truth. No specific number or qualifications of the individual who manually corrected it are provided.
- Clinical Study: Not applicable for establishing ground truth of the device's performance. The clinical endpoints (feasibility, radiation dose) are objective measures.
4. Adjudication Method for the Test Set
- Technical Performance: Not applicable as the ground truth was either a numerical matrix or a manually corrected panorama, without a listed multi-reader adjudication process.
- Clinical Study: No explicit adjudication method for clinical endpoints (e.g., disagreement resolution for radiation dose measurements) is described.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No MRMC comparative effectiveness study is mentioned, nor is there any information about the effect size of human readers improving with AI vs. without AI assistance. The clinical study focused on feasibility and efficiency of the device itself.
6. Standalone Performance
- Yes, performance evaluations were conducted for the algorithm in a standalone manner. The technical performance tests (registration accuracy, panorama creation, measuring functions) demonstrate the algorithm's capabilities without direct human interaction beyond setting up the test scenarios. The device itself is described as a "stand-alone software medical device."
7. Type of Ground Truth Used
- Technical Performance (Registration Accuracy): "Gold standard transformation matrix."
- Technical Performance (Panorama Creation): "Perfect panorama (manually corrected)."
- Technical Performance (Measuring Functions): Comparison with measurements from "EndoSize (planning tool)" and "a visible rule on the fluoroscopic image."
- Clinical Study: Clinical endpoints such as "feasibility rate of fusion" and "radiation dose as measured by fluoroscopy time, dose-area product and air kerma" were used as measures of outcome.
8. Sample Size for the Training Set
- The document does not explicitly state the sample size for any training set. The performance data section describes testing on CT-scan images and patient cases but does not distinguish between training and test data or provide details on the training methodology.
9. How the Ground Truth for the Training Set Was Established
- Since no information about a distinctive training set or its sample size is provided, there is no description of how ground truth for a training set was established.
§ 892.1650 Image-intensified fluoroscopic x-ray system.
(a)
Identification. An image-intensified fluoroscopic x-ray system is a device intended to visualize anatomical structures by converting a pattern of x-radiation into a visible image through electronic amplification. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). An anthrogram tray or radiology dental tray intended for use with an image-intensified fluoroscopic x-ray system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9. In addition, when intended as an accessory to the device described in paragraph (a) of this section, the fluoroscopic compression device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.