(413 days)
NovaPACS is intended for the viewing, archiving, analysis, annotation, distribution, editing, fusion, and processing of digital medical images and data acquired from diagnostic imaging devices and all DICOM devices, etc.
NovaPACS is intended for use by trained healthcare professionals, including radiologists, physicians, technologists, clinicians, and nurses. NovaPACS allows the end user to display, manipulate, archive, and evaluate images.
NovaPACS is not intended for diagnostic image review on a mobile platform.
While NovaPACS provides tools to assist the healthcare professional determine diagnostic viability, it is the user's responsibility to ensure quality, display contrast, ambient light confirm image compression ratios are consistent with the generally accepted standards of the clinical application.
NovaPACS is a picture archiving and communication system software that retrieves, archives, and displays images and data from all common modalities. NovaPACS uses a variety of workstations, including a Technologist Workstation, Enterprise Radiologist Workstation, Cardio Viewer and Workstation, NovaMG Workstation, and NovaWeb Web Viewer.
The NovaPACS software makes images and data available in digital format from all common modalities. The images are viewed on a computer monitor or portable device. NovaPACS tools/features include the following: window, level, zoom, pan, digital subtraction, ejection, cross localization, note-taking ability, voice dictation, and other similar tools. It includes the capability to measure distance and image intensity values, such as standardized uptake value. NovaPACS displays measurement lines, annotations, regions of interest, and fusion blending control functionality. Advanced features include 3D image rendering, virtual colonoscopy, and vessel analysis.
Images and data are stored on a digital archive with multiple redundancies; images and data are site and off-site. Novarad provides all software, including third party software (i.e. Windows® OS). NovaPACS software resides on third party hardware, which may vary depending on the client's PACS needs. All hardware is connected to the radiology department local area network.
NovaPACS integrates with NovaRIS and may integrate with any other third party RIS software that has HL7 interface capabilities.
NovaPACS integrates with Novarad Mobile Rad application to display data on 3rd party mobile platforms. Mobile Rad is not intended to replace a full diagnostic workstation.
This K132853 510(k) summary for NovaPACS does not contain the specific information required to complete the request thoroughly. The document describes the device, its intended use, and substantial equivalence to predicate devices, but lacks detailed performance data and study specifics.
Here's a breakdown of what can and cannot be extracted from the provided text regarding acceptance criteria and a study proving fulfillment:
1. A table of acceptance criteria and the reported device performance:
The document mentions "performance requirements" and "specifications" but does not provide a specific table of acceptance criteria with corresponding device performance values. It states:
- "NovaPACS software passes all performance requirements and meets all specifications prior to release, including:"
- "All requirements in the iteration have a test case and the test case has run and passed a."
- "All Acceptance tests have passed b."
- "All Current tests have passed C."
- "d. All high-impact bugs have been corrected and verified by Quality Assurance"
- "e. Any unresolved anomalies have been assessed in a risk meeting, and it has been found that they do not pose a safety risk to the end user (or their patients) and do not substantially affect the performance of NovaPACS software."
It also states: "Performance testing results show that the software features of NovaPACS operate correctly and safely and meet equivalent objectives and perform equivalent functions as those represented in the predicate devices."
And more broadly: "Thorough software testing has been performed for NovaPACS to safety and efficacy of the device. Of over 1200 test cases run on the NovaPACS Software, 99% passed, 1% failed, and 0% were blocked on their latest run. Of the failed tests, the majority represent minor user interface errors."
Lacking Information: Specific quantitative acceptance criteria (e.g., minimum accuracy, sensitivity, specificity, processing speed, image quality metrics) are not provided. The phrase "All Acceptance tests have passed" confirms the existence of such tests and their successful completion, but not the content of those tests or their specific targets.
2. Sample size used for the test set and the data provenance:
- Test set sample size: The document mentions "over 1200 test cases run on the NovaPACS Software." It does not specify if these test cases correspond to a specific number of patient cases or images, nor does it detail the nature of the data used in these tests. It seems to refer more to functional and system-level tests rather than a clinical dataset.
- Data provenance: Not specified. It's likely internal testing data related to software function.
- Retrospective or prospective: Not specified, but given the nature of the "test cases," it's likely part of a software development and validation process rather than a traditional clinical study with patient data collected retrospectively or prospectively.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of experts: Not specified.
- Qualifications of experts: Not specified.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not specified. The document primarily discusses software testing for functionality and bug resolution, not expert review of medical images.
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:
- Not performed. The document explicitly states: "There are no clinical tests to compare NovaPACS and predicate devices, as they are software products that send and store images and information." This implies no MRMC study or study comparing human performance with or without AI assistance was conducted or deemed necessary for this type of PACS device. NovaPACS is described as a system for viewing, archiving, and processing, not as an AI diagnostic aid.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not applicable in the typical AI sense. While the software has "features" like 3D rendering and vessel analysis, it's presented as a tool for "trained healthcare professionals" to "display, manipulate, archive, and evaluate images." It's not an autonomous diagnostic algorithm. The performance described ("99% passed" of 1200 test cases) relates to the correct functioning of the software itself, not its diagnostic accuracy in a standalone mode.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
- Not explicitly stated in terms of diagnostic ground truth. For the stated "test cases," the ground truth would be the expected functional behavior of the software feature (e.g., whether an image loads correctly, a measurement tool accurately calculates distance, or a 3D rendering displays as designed). It's not referring to ground truth for clinical diagnoses on patient images.
8. The sample size for the training set:
- Not applicable/Not provided. This document describes a PACS software system, which typically does not involve a "training set" in the machine learning sense for pattern recognition or diagnostic AI. The software's capabilities are based on coded algorithms and functionalities, not on learning from a dataset.
9. How the ground truth for the training set was established:
- Not applicable/Not provided. (See point 8).
In summary, the provided K132853 document focuses on demonstrating the functional equivalence and safety of the NovaPACS software as a Picture Archiving and Communication System (PACS) through software testing, rather than reporting on a clinical study of diagnostic performance using AI, which would typically involve detailed acceptance criteria, ground truth, and reader studies.
§ 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).