(188 days)
nordicDSC is a medical image post-processing software for the dynamic time course of the dynamic susceptibility contrast (DSC) enhanced MR data of the human brain to be used by trained professionals such as physicians, radiologists, and medical technicians to yield information useful in clinical applications.
The software is intended to be used off-line and in combination with a DICOM handling platform that can allow for user interactions, sending, receiving, and viewing of data, data quality control, and connection to network.
nordicDSC is an image analysis module that can be integrated into hospital infrastructure to analyze dynamic susceptibility contrast-enhanced (DSC) perfusion data obtained from Magnetic Resonance Imaging (MRI). The product can be deployed as a plugin to a DICOM handling platform.
The program functionality can be divided into three main categories:
- Accessing image data
- MR image processing and analysis
- Generating output, including information regarding blood flow, time to peak, and leakage.
The NordicNeuroLab AS nordicDSC Software underwent non-clinical performance testing to demonstrate its compliance with established standards and its suitability for its intended use. However, the provided document does not contain a detailed study proving the device meets specific acceptance criteria in terms of performance metrics. Instead, it primarily focuses on comparing the nordicDSC software with a predicate device (nordicICE Software, K090546) and verifying its compliance with general regulatory and software development standards.
Here's an analysis of the requested information based on the provided text:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly present a table of specific quantitative acceptance criteria alongside corresponding performance metrics for the nordicDSC device. It states, "The test results in this 510(k)premarket notification demonstrates that nordicDSC: ... Meets the acceptance criteria and is adequate for its intended use and specifications." This is a general statement of compliance, not a report of specific performance against defined criteria.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document provides no information regarding the sample size used for any test set or the provenance of the data (e.g., country of origin, retrospective or prospective).
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
The document does not mention the number of experts used to establish ground truth for any test set, nor does it specify their qualifications.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not describe any adjudication method used for a test set.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study or any assessment of human reader improvement with or without AI assistance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document does not explicitly state that a standalone performance study (algorithm only without human-in-the-loop) was conducted. While it refers to "non-clinical performance testing" and "verification and validation tests," these are primarily framed around compliance to standards and comparison to a predicate device's features rather than a direct, quantitative standalone performance evaluation against a gold standard.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)
The document does not specify the type of ground truth used for any testing.
8. The sample size for the training set
The document does not mention any training set or its sample size. The primary focus is on performance testing and comparison to a predicate, not on a machine learning model training process that would typically involve a "training set."
9. How the ground truth for the training set was established
Since no training set is mentioned, there is no information on how its ground truth was established.
Summary of what the document does provide regarding testing:
- Non-clinical performance testing: "Non-clinical performance testing has been performed on the nordicDSC Software and demonstrates compliance with the following International and FDA-recognized consensus standards and FDA guidance document: ISO 14971, IEC 62304, IEC 62366-1, IEC 82304-1 Edition 1.0 2016-10."
- Verification and Validation: "Verification and Validation tests have been performed to address intended use, the technological characteristics claims, requirement specifications and the risk management results."
- Nondeterministic algorithm variation: "The algorithm is inherently nondeterministic, so head-to-head comparisons have to consider the internal variation, which has been found to be within +/- 10%." This provides a very general statement about the algorithm's consistency but not its accuracy or specific performance against a clinical gold standard.
- Substantial Equivalence: The primary method of demonstrating safety and effectiveness appears to be through showing substantial equivalence to a predicate device (nordicICE Software, K090546) based on intended use, indications for use, and technical/operational characteristics.
Conclusion:
The provided 510(k) summary focuses on demonstrating substantial equivalence to a predicate device and compliance with general software and risk management standards. It explicitly states that "The test results in this 510(k)premarket notification demonstrates that nordicDSC: ... Meets the acceptance criteria and is adequate for its intended use and specifications." This implies that acceptance criteria were defined and met. However, the document does not disclose the specific quantitative acceptance criteria, the detailed study design (including sample sizes, data provenance, ground truth establishment, or expert involvement), or the specific performance results that would allow for a complete answer to your request. The "Brief discussion of the nonclinical tests" refers to general compliance rather than specific clinical performance metrics.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).