(52 days)
The product being submitted is going to be used as a PACS system and provide viewing tools for radiologists, technologists, other physicians, cardiologists, and patients. It will also provide archiving of images and data. The product will be sold to hospitals, imaging centers, and clinics. It is a software product sold with accompanying off-the-shelf hardware, It is substantially equivalent to other products now being sold as PACS. Further it is for using DICOM for presentation of Mammography studies, not for image processing. Will include the standard features for Mammo of window/level/zoom, as well as volumetric measurements and other Mammo tools. Mammo will only be interpreted on 510K approved 5 Mp LCD monitors. The Mammo images will be stored lossless (non-lossy compressed). Digitized conventional screen film mammograms will not be used in soft copy format for primary diagnosis.
The PACS product provides a system where images and accompanying data are sent from the modalities to the radiologists and technologists in digital format. The images are then viewed on a computer with such available tools a window, level, zoom, pan, roi, digital subtraction, ejection fraction, cross localize, and many other similar tools and with the ability to make notes and dictate a report. The images and report are then stored long term on a digital archive with multiple redundancy. All the information is also made available as a web based product where referring physicians or radiologists can access the information from anywhere using a secure system. The software is provided by NovaRad along with some 31d party software, principally from windows, and resides on off-the-shelf hardware hooked up to the radiology department local area network.
Here's an analysis of the provided text regarding the acceptance criteria and study for the NovaRad PACS (K063153):
This 510(k) summary explicitly states that no clinical tests were performed to compare the device to a predicate. The justification provided is that the device is "merely software products that send and store images and information. Since the images are not changed or analyzed by the product, there is no safety issue, except possible related to the safety of the archived images."
Therefore, the following table and subsequent sections will reflect this lack of clinical study data.
Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Specific Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Functional Equivalence | Provide the exact same ability to replace film with digital. | Meets criterion. Stated as "the exact same ability to replace film with digital." |
| Functional Equivalence | Perform the exact same functions as the predicate device. | Meets criterion. Stated as "perform the exact same functions." |
| Safety (Image Integrity) | Not change or analyze images. | Meets criterion. Stated as "images are not changed or analyzed by the product." |
| Safety (Archiving) | Ensure safety of archived images. | Meets criterion. NovaRad offers "more redundancy than the predicate device" with multiple RAID 5 archives on-site and a third redundant copy at corporate headquarters. |
| DICOM Compliance | Use DICOM for presentation of Mammography studies. | Meets criterion. Explicitly stated that it "is for using DICOM for presentation of Mammography studies." |
| Mammography Viewing | Include standard Mammography features (window/level/zoom, volumetric measurements, other Mammo tools). | Meets criterion. Explicitly stated that it "will include the standard features for Mammo of window/level/zoom, as well as volumetric measurements and other Mammo tools." |
| Mammography Display | Mammography only interpreted on 510(k) approved 5 Mp LCD monitors. | Meets criterion. Explicitly stated that "Mammo will only be interpreted on 510K approved 5 Mp LCD monitors." |
| Mammography Storage | Mammography images stored lossless (non-lossy compressed). | Meets criterion. Explicitly stated that "The Mammo images will be stored lossless (non-lossy compressed)." |
| Mammography Limitations | Digitized conventional screen film mammograms not used in soft copy format for primary diagnosis. | Meets criterion. Explicitly stated that "Digitized conventional screen film mammograms will not be used in soft copy format for primary diagnosis." |
Study Details (or lack thereof)
-
Sample size used for the test set and the data provenance:
- Not applicable. No clinical test set was used, as no clinical study comparing the devices was conducted. The equivalence was based on functional comparison and safety considerations regarding image storage.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not applicable. No clinical test set or ground truth establishment by experts was performed for comparison between the predicate and the NovaRad PACS. The submission primarily relies on the functional equivalency of a PACS system and its ability to store and display images without alteration.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not applicable. No clinical test set was used, therefore no adjudication method was employed.
-
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:
- No. An MRMC comparative effectiveness study was not performed. The device is a Picture Archiving and Communication System (PACS) and does not involve AI assistance for image interpretation.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- No. This device is a PACS for image management and viewing, not an AI algorithm. Therefore, a standalone performance study as understood for AI devices was not conducted.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not applicable. No clinical ground truth was established or used for the purpose of demonstrating substantial equivalence. The claim of substantial equivalence is based on the system's ability to perform the same functions as the predicate PACS without altering image data.
-
The sample size for the training set:
- Not applicable. As this is a PACS system designed for image storage and viewing, and not an AI or image analysis device, there is no "training set" in the context of machine learning.
-
How the ground truth for the training set was established:
- Not applicable. As there is no training set, there was no ground truth to establish for it.
§ 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).