(349 days)
ProFuse CAD is a post-processing software tool intended for viewing, reviewing and reporting imaging files such as Magnetic Resonance Imaging (MR), Computed Tomography (CT) and Positron Emission Tomography (PET) studies.
The software is able to process time series modality data acquired before, during, and after a contrast agent has been administered to the patient. The software allows a physician to evaluate tissue characteristics based on contrast enhancement visible on the time series data can also be processed to get subtraction image time -series with any reference time point.
ProFuse CAD also provides capability to process a specialized MRI series called diffusion weighted imaging to evaluate tissue characteristics based on water diffusion. Some of the other posts -processing features include multi-planar reformats and registration between images.
ProFuse CAD has a marking feature that allows the user to outline organs with minimal input and also annotate regions in the image in 3D. The software also allows for grading the annotated regions as defined by the user. After review, the software automatically generates a patient report that provides information like; organ volume, annotations; and grading along with automatically generated screenshots of the annotations in different images.
Planned data from ProFuse CAD can be used for interventional procedures like MR - TRUS fusion biopsies. The data can be displayed on medical device data systems.
ProFuse CAD is used as a tool to review and add to the results of interventional procedures like; adding pathology information when reviewing MR-TRUS fusion biopsy.
When interpreted by a skilled physician, this device provides information that is intended to be used for screening, analysis, and interventional planning. Patient management decisions should not be made based solely on the results of ProFuse CAD.
ProFuse CAD is intended to be used as an image viewer of multi-modality, digital images, including Ultrasound, CT, PET.
ProFuse CAD is intended to be used in a variety of setting such as; medical offices, clinics, hospital, and home office.
ProFuse CAD is standalone Computer Aided Detection (CAD) software that is used by radiologists to visualize, analyze, plan and interpret medical images using tools available in the software. Some of the tools in the software are
- Visualization: The software allows simultaneous visualization of different images with the ability to view them in different orientations e.g. transverse, sagittal, coronal and 3D.
- Organ segmentation: The software allows user to outline the organ of interest (e.g. prostate)
- Image annotation: The software allows user to mark regions of interest (ROI) on images
- Time-series analysis: The software allows user to view the time-curve plots for a single location or average over a region (ROI). The user could also calculate different parametric maps based on pharmacokinetic modeling. The parametric maps could be viewed as a separate series or be overlaid as color on another series. The software also allows users to calculate subtracting images from a customizable user defined time point.
- Diffusion series analysis: Diffusion weighted series is a special type of magnetic resonance imaging (MRI) sequence that measures diffusion of water molecules in the body. A set of different diffusion weighted images are obtained and from the set of images the software allows the user to fit different mathematical models to extract different parametric maps. The parametric maps could be viewed as a separate series or be overlaid as color on another series.
- Report: The software allows the user to create reports following either the PIRADS (see definition) standard or a customizable standard.
- Export: The software allows the planned images to be exported for different procedures e.g. biopsy, therapy, etc. Information exported by ProFuse CAD could then be used in other software solutions like ProFuse Bx, ProFuse FP.
- Review: Review, add and modify data from the 3D visualization software (Artemis). The data includes acquired volume, organ segmentation, planned and recorded biopsy location and pathology information.
The provided text describes the ProFuse CAD device and its regulatory submission (K173744) but does NOT contain specific, detailed information about acceptance criteria for particular performance metrics or the quantitative results of a study designed to prove the device meets those criteria.
The document discusses "Testing and Performance Data" and "Nonclinical Testing and Performance Information," stating that "all product and engineering specifications were verified and validated" and that "nonclinical and performance testing results are provided in the 510(k) and demonstrate that the predetermined acceptance criteria are met." However, it fails to specify what those acceptance criteria were or what the quantitative performance results were. It also mentions the use of "simulated and retrospective clinical data" for verification of diffusion and perfusion analysis tools but does not give the sample sizes or other study details requested.
Therefore, I cannot fully complete the requested table and information based on the provided text.
Here's what can be extracted and what is missing:
1. Table of Acceptance Criteria and Reported Device Performance
- Cannot create. The document states that predetermined acceptance criteria were met, but it does not specify what those criteria are (e.g., minimum accuracy, sensitivity, specificity, or volume estimation error) nor does it provide precise numerical results for the device's performance against any specific metric. It only vaguely mentions "measurement validation using phantoms, clinical images were used to show that ProFuse CAD performs as well as or better than the other primary and referenced predicate devices."
2. Sample size used for the test set and the data provenance
- Partial information: "Simulated and retrospective clinical data were used for verification of the diffusion and perfusion analysis tools."
- Missing: Specific sample sizes (number of cases/studies) for the test set. Country of origin for the retrospective clinical data is not mentioned.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Missing. The document does not specify how ground truth was established, nor does it mention the number or qualifications of experts involved in the test set evaluation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Missing. No information on adjudication methods for establishing ground truth or evaluating device performance.
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
- Missing. The document describes ProFuse CAD as a "post-processing software tool" and "standalone Computer Aided Detection (CAD) software." It states it's intended to be "interpreted by a skilled physician" and that "Patient management decisions should not be made based solely on the results of ProFuse CAD." This implies human-in-the-loop usage. However, it does not describe an MRMC study comparing human performance with and without AI assistance, nor does it provide any effect size.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
- Implied but not detailed: The document states that "nonclinical and performance testing results are provided in the 510(k) and demonstrate that the predetermined acceptance criteria are met." It also mentions "measurement validation using phantoms, clinical images were used to show that ProFuse CAD performs as well as or better than the other primary and referenced predicate devices." This implies standalone performance was evaluated, especially for features like volume estimation accuracy with phantoms and diffusion/perfusion analysis. However, no specific standalone performance metrics or results are given.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Partial/Vague:
- For "volume estimation accuracy studies," "test phantoms incorporating simulated prostates" were used. For these, the ground truth would likely be the known volumes of the phantoms.
- For "diffusion and perfusion analysis tools," "simulated and retrospective clinical data" were used. The document does not specify how ground truth was established for these clinical cases (e.g., expert reads, pathology, follow-up).
- The "Intended Use" section mentions "adding lab pathology information when reviewing MR-TRUS fusion biopsy," which hints at pathology being a relevant ground truth for certain clinical applications, but it's not explicitly stated as the ground truth for the verification studies.
8. The sample size for the training set
- Missing. The document does not provide any information about the training set, indicating it was either not applicable (e.g., if it's a rule-based system or not a machine learning model where a distinct "training set" and "test set" are used in the typical ML sense, although "simulated and retrospective clinical data" were used for verification) or that this information was not deemed necessary for the 510(k) summary provided.
9. How the ground truth for the training set was established
- Missing. As the training set size is missing, so is this information.
In summary, the provided document is a high-level 510(k) clearance letter and a summary of the device's features and intended use. It asserts that performance testing was conducted and acceptance criteria were met but does not provide the detailed quantitative results or the comprehensive study design information that would be necessary to fill out the requested table and answer many of the questions.
§ 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).