(64 days)
The PCR 5.2 System is a digital film processing system for reading and then digitizing X-ray images from reusable imaging plates which have been exposed in conventional radiographic examination devices. The digitized X-ray images can then be viewed, stored, post-processed and printed. The Philips PCR system can be used in all conventional RAD/RF examination situations, except for mammography. PCR is suitable for routine RAD exams as well as specialist areas, like intensive care units, trauma departments and pediatric departments.
A PCR system consists of an image reader, one or more PCR User Terminals, and an Easy Vision PCR Printstation or optional EasyVision RAD workstation.
Imaging plates are exposed via conventional X-Ray devices. The imaging plates used in PCR systems are coated with a luminescent material which acts as an x-ray detector. It stores the x-ray image in the form of excited charge carriers. An exposed imaging plate is loaded into the image reader of the PCR system and the image stored on the imaging plate is scanned with a laser and converted to digital data. The digital X-ray image data is then routed to the EasyVision PCR Printstation or optional EasyVision RAD workstation for image processing, viewing, storing and/or printing to film if the workstations are connected to a compatible laser imager. The PCR User Terminal is used for the scheduling of patients and exams.
The PCR User Terminal consists of a Pentium-based PC, a keyboard, an operator terminal with function keys, and an optional bar-code reader. PCR User Terminals may be interconnected via standard ethernet.
Three image reader types, currently AC2, AC3 and 9000, can be connected to the system in order to meet different requirements based on image plate size and throughput.
The EasyVision PCR Printstation is a workstation that provides image storage, display, printing and processing functions using a SUN computer. The optional EasyVision RAD workstation is also a SUN computer that provides the same functions as the Printstation but it also provides more storage capability and additional post-processing functions. Both workstations are able to export digital images to the network via the DICOM protocol.
Digital image data from the image readers are processed based on selection of either an UnSharp Masking (UM) algorithm or a Dynamic Range Reconstruction (DRR) algorithm.
This 510(k) summary for the Philips Computed Radiography (PCR) 5.2 system describes a device that digitizes X-ray images. The primary focus of the document is on establishing substantial equivalence to a predicate device and outlining its functions. Consequently, the document does not contain details about specific acceptance criteria, a dedicated study proving device performance against those criteria, or many of the specific study design elements you requested.
Here's an attempt to answer your questions based only on the provided text:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly state quantitative acceptance criteria or report specific device performance metrics in comparison to such criteria. Instead, it focuses on demonstrating compliance with general electrical safety and communication standards, and substantial equivalence to a predicate device.
The "Performance Standards" section notes:
"This device complies with the relevant national and international standards for electrical safety (UL-1950. IEC-601-1, and IEC-950) as well as the international standard for electromagnetic compatibility (IEC-601-1-2) and the ACR/NEMA DICOM Version 3.0 digital imaging communication standard."
The "Substantial Equivalence Information" section implies performance is acceptable if it's "substantially equivalent" to previously cleared devices. Specifically, it notes that the new DRR algorithm is "substantially equivalent" to the Unsharp Mask (UM) algorithm and the Dynamic Range Control (DRC) algorithm. It states: "Processing with DRR improves low contrast resolution."
Therefore, we can infer the implied acceptance criteria are:
- Compliance with cited electrical safety and EMC standards.
- Compliance with DICOM 3.0 standards.
- Substantial equivalence in performance to the predicate device (Philips PCR ACe system) and its associated algorithms (UM and DRC for image processing), with an improvement in low contrast resolution with the new DRR algorithm.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document does not provide any information regarding a test set, its sample size, or data provenance. The assessment appears to be based on engineering comparisons and references to existing cleared devices rather than a new clinical performance study.
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. There is no mention of ground truth establishment by experts for a test set.
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
The document does not describe a multi-reader multi-case (MRMC) comparative effectiveness study. This device is an "Automatic Radiographic Film Processor" (Computed Radiography system), which digitizes X-ray images. While it performs "Image Processing" with algorithms like DRR, it is not described as an "AI" system in the contemporary sense, nor is there any mention of a study evaluating improvements in human reader performance with or without its assistance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document does not detail a standalone performance study. It describes the system's functions (image reading, processing, viewing, printing, storage, export) and emphasizes its equivalence to predicate devices. The claim "Processing with DRR improves low contrast resolution" is a statement about the algorithm's effect, but not presented as the result of a formal standalone performance study with metrics.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
The document does not describe the establishment or use of ground truth for evaluating the device's image processing capabilities. The primary evaluation method seems to be through comparison and demonstration of "substantial equivalence" of its technological characteristics (including algorithms) to previously cleared devices.
8. The sample size for the training set
The document does not mention any training set size. As the device involves image processing algorithms like UnSharp Masking and Dynamic Range Reconstruction, these algorithms would have been developed and tuned, but the text does not refer to a "training set" in a machine learning context.
9. How the ground truth for the training set was established
Not applicable, as no training set is mentioned in the context of device evaluation.
§ 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).