(49 days)
The SharpView Image Enhancement System is intended for use by a qualified/trained technologist for transfer, storage, enhancement, and viewing of multi-modality images from a variety of diagnosis imaging systems.
The product is a software or a kit containing software and hardware (Image processing board), which is intended to be installed on a personal computer. Typically the personal computer receives digital medical images in DICOM 3 format over a network connection. The enhanced and original image can be sent in DICOM 3 format over the network connection. The original file and the enhanced file can be kept locally if selected.
The provided documentation does not contain detailed acceptance criteria for device performance or a study proving that the device meets such criteria. Instead, it focuses on demonstrating substantial equivalence to a predicate device for regulatory purposes.
Here's an analysis of the available information in relation to your request:
1. A table of acceptance criteria and the reported device performance:
This information is not available in the provided text. The document states that "The result of bench and user testing indicates that the modified device is as safe and effective as the predicate device" (Section 5) and "After analysing both bench and user testing data, it is the conclusion of ContextVision AB that the multi-modality SharpView Image Enhancement System is as safe and effective as the predicate device..." (Section 7). However, it does not provide specific acceptance criteria (e.g., quantitative metrics for image quality, enhancement effectiveness, processing speed, or diagnostic accuracy) or the reported performance data against those criteria.
2. Sample size 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. The document mentions "bench and user testing data" but does not specify the sample size used, the nature of the data (e.g., number of images, modalities, or clinical cases), or the provenance of the data.
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. The document does not describe how ground truth was established for any testing, or if experts were involved in a formal capacity to define a ground truth.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
This information is not available. The document does not describe any adjudication methods used for the 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:
This information is not available. The document describes the device as an "Image Enhancement System" intended to assist a "qualified/trained technologist" for transfer, storage, enhancement, and viewing of images. While it's an image processing tool, the document does not mention a clinical performance study using human readers, let alone an MRMC study or any effect size related to 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 implies "bench and user testing," which would likely include standalone algorithm performance (e.g., image processing speed, image quality metrics). However, specific details about standalone performance tests and their results are not provided. The core function of the device is image enhancement, which is inherently an "algorithm only" function in terms of its direct output on an image. The "user testing" would then evaluate the impact of this enhanced image on the user.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
This information is not available. Given the nature of an "Image Enhancement System," the "ground truth" for evaluating its performance would likely involve subjective image quality assessments, objective image metric improvements (e.g., signal-to-noise ratio, contrast-to-noise ratio), or a direct comparison to the predicate device's enhanced images. However, the document does not specify how this was established.
8. The sample size for the training set:
This information is not available. The document does not explicitly state that the device uses machine learning or AI that would require a dedicated "training set." It mentions "GOP® Enhancement software" which is a proprietary image processing method, but whether this involves a training phase akin to machine learning is not detailed.
9. How the ground truth for the training set was established:
This information is not available for the same reasons as point 8.
§ 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).