Search Results

nordicICE is an image processing software package to be used by trained professionals including but not limited to physicians and medical technicians. The software runs on a standard "off-the-shelf" PC workstation and can be used to perform image viewing, processing and analysis of medical images. Data and images are acquired through DICOM compliant imaging devices and modalities.

nordicICE provides both viewing and analysis capabilities of functional and dynamic imaging datasets acquired with MRI or other relevant modalities, including blood oxygen level dependent (BOLD) fMRI, diffusion weighted MRI (DWI) / fiber tracking and dynamic analysis.

BOLD fMRI: BOLD analysis is used to highlight small magnetic susceptibility changes in the human brain in areas with altered blood-flow resulting from neuronal activity.

DWI/Fiber Tracking: Diffusion analysis is used to visualize local water diffusion properties from the analysis of diffusion-weighted MRI data. Fiber tracking utilize the directional dependency of the diffusion to display the white matter structure in the brain.

Dynamic Analysis: Dynamic analysis is used for visualization and analysis of dynamic imaging data, showing properties of changes in contrast over time where such techniques are useful or necessary.

nordicICE (nlCE) - Nordic Image Control and Evaluation software - is a medical viewing, analysis, and processing package developed with a view to ease of use and high performance on a standard Windows platform. The software provides a wide range of basic image processing and manipulation functions, in addition to comprehensive functionality for dynamic image analysis and processing/display of functional MRI (fMRI) data. The main user of the program will be imaging professionals who need to visualize and analyze images taken primarily from a MRI system.

This 510(k) summary for the Nordic Image Control and Evaluation (nordicICE) Software primarily focuses on demonstrating substantial equivalence to a predicate device (Nordic Image Control and Evaluation (nordicICE) Software, K063539) and detailing its intended use and features rather than providing extensive details about specific acceptance criteria and a structured study to prove those criteria.

Based on the provided text, a comprehensive table of acceptance criteria and reported device performance, as well as many of the requested study details, cannot be fully extracted because the document does not contain this specific information in the format requested for a detailed AI/CAD device study. This document is a regulatory submission for a PACS-like software, which historically did not require the same rigorous, quantitative performance studies as modern AI/CAD algorithms. Instead, the focus is on verification and validation (V&V) of software functionality and substantial equivalence.

However, I can extract what is implied and stated regarding validation and equivalence:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

• Not specified. The document mentions "verification and validation" but does not detail a specific "test set" in terms of patient cases or images, sample size, or data provenance (e.g., country of origin, retrospective/prospective). This is typical for software validation focused on functional correctness rather than diagnostic performance against ground truth.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

• Not applicable/Not specified. The document does not describe a study involving human experts establishing ground truth for a test set to measure diagnostic performance. The validation appears to be against internal specifications and comparison to a predicate device's functionality.

4. Adjudication Method for the Test Set

• Not applicable/Not specified. No mention of adjudication, as there is no described study comparing the software's output against an expert-adjudicated ground truth.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and the effect size of how much human readers improve with AI vs without AI assistance

• No. An MRMC study was not done. This device is a general image viewing, processing, and analysis software, not an AI/CAD diagnostic aid for which MRMC studies are typically performed. The document focuses on the software's functionality and its equivalence to a predicate, not its impact on human reader performance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done

• Not applicable in the typical sense of AI algorithms. While the software itself performs analysis (e.g., BOLD fMRI analysis, DWI processing), the validation described is for the software's computational correctness and functional equivalence to a predicate, not for its standalone diagnostic performance. There is no "algorithm only" performance reported against a clinical outcome or expert ground truth in the document.

7. The Type of Ground Truth Used

• Internal specifications and predicate device functionality. The "ground truth" for the validation appears to be the expected behavior as defined in the product design and development procedures, and the established functionality of the predicate device. It is not clinical ground truth like pathology, expert consensus, or outcomes data, which would be expected for a diagnostic AI device.

8. The Sample Size for the Training Set

• Not applicable/Not specified. This software is described as an image processing, viewing, and analysis package. It is not an AI/Machine Learning algorithm that typically requires a large 'training set' for model development.

9. How the Ground Truth for the Training Set Was Established

• Not applicable/Not specified. As there is no mention of a training set for an AI/ML algorithm, the method for establishing ground truth for such a set is not discussed.

Summary of the Study (Implied):

The "study" described is a verification and validation (V&V) process and a substantial equivalence comparison to a predicate device. This type of submission, especially from 2008 for a PACS-like viewing/processing software, focuses on:

• Confirming the software meets its design specifications (internal V&V).
• Demonstrating that the new device has the same intended use and technological characteristics as a previously cleared device (the predicate K063539), and any differences do not raise new questions of safety or effectiveness.

The document explicitly states: "nordicICE has been verified and validated according to NIL's procedures for product design and development. The validation proves the safety and effectiveness of the system. The information provided by nordicICE was found to be substantially equivalent with the predicate device Nordic Image Control and Evaluation (nordicICE) Software (K063539)." This is the core "study" proving the device met its implied acceptance criteria (functional correctness, safety, effectiveness, and substantial equivalence).

Ask a specific question about this device