(29 days)
ImageQube is intended for use by a physician or other medical professionals in the display and interpretation of medical images and demographic detail from all institutional imaging modalities, including, but not limited to, CT, MRI, NM, DR, US, PET Fusion, Angio and MG (including display of DICOM overlays and 3D Mammography images), along with secondary capture devices, such as film digitizers or other imaging sources. The ImageQube is designed for display, interpretation, storage and distribution of all modalities.
Only pre-processed DICOM For Presentation images can be interpreted for primary diagnosis in mammography. Lossy compressed mammographic images and digitized film screen images must not be viewed for primary image interpretations. Mammographic images may only be interpreted using an FDA approved monitor meeting all the technical specifications required by the FDA for the Performance of Screening and Diagnostic Mammography. Images that are printed to film must be done using an FDA-approved printer for the diagnosis of digital mammography images. Efficient mammography screening makes toolbars and thumbnails available on each monitor, while also handling DICOM overlay display.
Acquired medical images may be displayed and manipulated further utilizing Multi-Planar Reconstruction (MPR), Anatomic Triangulation (AT), Dynamic Cross-Referencing, Maximum Intensity Projection (MIP), Slab and 3-D display, sent to and retrieved by radiologists in-house at facilities or at remote sites, stored, archived or printed. The ImageQube can operate as an independent device, or can also be interfaced with Rational Imaging PACS systems. Annotated print pages, transcribed reports and Key Image Summaries can also be accessed.
ImageQube is designed for use by a physician or other medical professionals in the acquisition of medical images and demographic detail from all institutional imaging modalities, including, but not limited to CT, MRI, NM, DR, US, PET Fusion, Angio and MG (including display of DICOM overlay and 3D Mammography images), along with secondary capture devices, such as film digitizers or other imaging sources. The acquired medical images and demographic information may be displayed, processed, reviewed, sent to and retrieved by radiologists at remote sites, stored, archived or printed. Multiplanar Reconstruction (MPR), Anatomic Triangulation (AT), Dynamic Cross-Referencing, Maximum Intensity Projection (MIP), Slab and 3D display are also available for optional use.
The provided text describes a 510(k) summary for the ImageQube device, which is an imaging processing system. It focuses on establishing substantial equivalence to predicate devices rather than providing detailed acceptance criteria and a study proving the device meets those criteria.
Therefore, many of the requested details about acceptance criteria, specific performance metrics, study design, expert qualifications, ground truth, and sample sizes for effectiveness studies are not available in the provided text.
Based on the information provided, here's what can be extracted:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly present a table of acceptance criteria with corresponding performance results. Instead, it states:
"Support of the substantial equivalence of the ImageQube device was provided as a result of software validation, which confirms all features of the ImageQube device were compliant with the software requirements."
This suggests that the acceptance criteria were primarily related to software functionality and compliance with requirements, rather than clinical performance metrics like sensitivity or specificity.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
This information is not available in the provided text. The document refers to "software validation" but does not detail the test set size, its nature (e.g., medical images, synthetic data), or its provenance.
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)
This information is not available in the provided text. Since the validation mentioned is "software validation," it's unlikely that medical experts were involved in establishing ground truth in the traditional sense of clinical studies.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not available in the provided text.
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
A multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not done, or at least not described in this document. The focus is on the device's functionality as a standalone imaging processing system, not on its impact on human reader performance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
A standalone performance evaluation was implicitly done through "software validation," which "confirms all features of the ImageQube device were compliant with the software requirements." This suggests testing the algorithm/software functionality independently of human interaction. However, no specific performance metrics (e.g., accuracy, speed) are provided, only a statement of compliance.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)
The type of ground truth used is not explicitly stated. Given the focus on "software validation" and "compliance with software requirements," the ground truth likely involved predefined software specifications, expected output, or correct functionality, rather than clinical ground truth like pathology reports or expert consensus on medical findings.
8. The sample size for the training set
This information is not available in the provided text. The document describes a "software validation" which implies testing of developed software, but it doesn't mention a training set, which is typically associated with machine learning or AI models. Since the device is an "imaging processing system" and not specifically described as an AI/ML diagnostic tool, a training set as understood in AI development might not be applicable or simply not disclosed.
9. How the ground truth for the training set was established
This information is not available in the provided text, as a training set is not mentioned.
§ 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).