(54 days)
Nordic Image Control and Evaluation (nICE) Software is an image management system intended to be used by trained professionals, including but not limited to physicians, nurses and medical technicians. The system is used with general purpose computing hardware to acquire, transmit, process and store images and data throughout a clinical environment. Data and images are acquired through DICOM compliant imaging devices and modalities.
Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretations.
Nordic Image Control and Evaluation (nICE) Software is a medical imaging manipulation tool, designed to provide a way to optimize the clinician's workflow. It targets activities fundamental to their work: reading, defining, sharing and reporting medical radiographic images. It is designed to work within a Windows™ operating system, and provides the user with the ability to view a wide range of image types.
The provided 510(k) summary for the Nordic Image Control and Evaluation (nICE) Software version 2.1 does not contain specific acceptance criteria or an explicit study proving device performance against such criteria.
Instead, the submission states:
1. Acceptance Criteria and Reported Device Performance:
The document broadly states: "Prospectively defined verification and validation activities for the nICE Software assure that the nICE Software is substantially equivalent to the cleared eFILM Workstation with Modules and meets design and performance specifications as well as user needs when operated according to the operating instructions."
- Acceptance Criteria: Not explicitly stated as quantifiable metrics. The acceptance is based on demonstrating "substantial equivalence" to the predicate device (eFILM Workstation with Modules, K020995) in terms of intended use, indications for use, technological characteristics, and operational characteristics, as well as meeting general "design and performance specifications" and "user needs."
- Reported Device Performance: No specific numerical performance metrics (e.g., sensitivity, specificity, accuracy, processing times, image quality scores) are reported in this summary. The performance is implied to be functionally equivalent to the predicate device.
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size: Not mentioned.
- Data Provenance: Not mentioned.
3. Number of Experts Used to Establish Ground Truth and Their Qualifications:
- Number of Experts: Not mentioned.
- Qualifications of Experts: Not mentioned.
4. Adjudication Method:
- Adjudication Method: Not mentioned.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No MRMC comparative effectiveness study is mentioned
- Effect Size: Not applicable as no such study is described.
6. Standalone Performance Study:
- No standalone performance study with specific metrics (e.g., sensitivity, specificity) for the algorithm without human interaction is provided. The substance of the submission focuses on verifying and validating the software's functionality and equivalence to existing PACS systems, rather than its performance as a diagnostic AI tool.
7. Type of Ground Truth Used:
- Type of Ground Truth: Not mentioned. Given the nature of the device as an image management and manipulation tool (PACS), the "ground truth" for its verification and validation would more likely relate to proper image display, manipulation functions, data integrity, and adherence to DICOM standards, rather than diagnostic accuracy against a clinical ground truth like pathology or outcomes data.
8. Sample Size for the Training Set:
- Sample Size: Not mentioned. The nICE Software is described as an "image management and manipulation tool," implying it is not an AI/ML diagnostic algorithm that would typically require a training set in the conventional sense. Its development would involve software engineering and testing against functional requirements.
9. How the Ground Truth for the Training Set Was Established:
- How Ground Truth Was Established: Not applicable, as there is no mention of a training set for an AI/ML algorithm.
Summary of Findings:
The 510(k) summary for the nICE Software focuses on demonstrating substantial equivalence to a predicate PACS workstation (eFILM Workstation with Modules). It describes the software's intended use as an image management system for acquiring, transmitting, processing, and storing images and data. The "performance testing" section refers to "prospectively defined verification and validation activities" to assure substantial equivalence and meeting design/performance specifications and user needs.
Crucially, this submission does not describe the kind of performance study typically seen for AI-enabled diagnostic imaging devices that would include specific acceptance criteria, test sets, ground truth establishment, and reported sensitivity/specificity/accuracy metrics. This is because the nICE Software, as described, is a Picture Archiving and Communication System (PACS), which is a foundational image management infrastructure, not a diagnostic AI algorithm that independently interprets medical images. The acceptance criteria here would therefore be related to software functionality, reliability, security, interoperability (e.g., DICOM compliance), and proper image display, rather than diagnostic performance.
§ 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).