Search Results

The RMF-2000 generates 2D digital mammography images. The RMF-2000 is intended to be used for screening and diagnosis of breast cancer. This unit is intended for use in the same clinical applications as traditional screen film mammography systems.

The system consists of a gantry with integrated high-voltage generator as well as an optional radiation shield with a height-adjustable control desk with an integrated Acquisition Workstation (AWS). The moveable swivel C-arm on the gantry contains the X-ray tube on the top end and the breast support with the X-ray detector on the bottom end. The detector is a full field digital mammography detector. RMF-2000 acquires digital mammographic images for diagnosis of the breast cancer. RMF-2000 is designed to be used in the same clinical application for 2D screening mammographic systems. The screening examination exposes X-rays to the left and the right breasts of the patient to acquire images. Also, the RMF-2000 can be used to additional precision diagnosis for breasts. The device's software provides an integrated solution for X-ray projection. It integrates with the X-ray generator and the digital detector and acquires and processes images. In addition, it complies with DICOM standards and is able to transmit and receive data with the PACS system, and print images through the DICOM printer.

The provided document is a 510(k) summary for the DRTECH Corporation's RMF-2000 Full-Field Digital Mammography system. The document focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed study proving the device meets specific performance acceptance criteria for an AI/software as a medical device (SaMD).

However, I can extract information related to the device's performance evaluation as presented in the document, framed within the context of substantial equivalence. The document describes a clinical image evaluation to demonstrate that the images produced by the RMF-2000 are of sufficient quality for mammographic use and substantially equivalent to those from the predicate device.

Here's an attempt to answer your questions based on the provided text, acknowledging that the depth of information about "acceptance criteria" and the "study" is limited to what's required for a 510(k) submission showing substantial equivalence of an imaging device, not necessarily an AI/SaMD.

Acceptance Criteria and Device Performance

The document doesn't explicitly list "acceptance criteria" in a quantitative table for device performance in the way one might expect for a robust AI/SaMD study (e.g., specific sensitivity, specificity, or AUC thresholds). Instead, the acceptance criterion for the clinical evaluation was implicitly the "sufficiently acceptable quality for mammographic usage" and "substantial equivalence to those from predicate device" concerning image quality, as determined by qualified physicians.

Table of Acceptance Criteria and Reported Device Performance (as inferred from the document):

Study Details:

1. Sample size used for the test set and the data provenance:

   • The document states "A clinical image evaluation... was conducted," but it does not specify the sample size (number of images or patients) used for this evaluation.
   • Data Provenance: Not explicitly stated (e.g., country of origin). The study is described as a "clinical image evaluation." It's retrospective as it involves evaluation of images.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • The document states "images, reviewed by MQSA qualified interpreting physicians."
   • Number of experts: Not specified (e.g., it doesn't say how many physicians reviewed the images).
   • Qualifications: "MQSA qualified interpreting physicians." MQSA (Mammography Quality Standards Act) qualification implies specific training and experience requirements for reading mammograms in the U.S.

3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

   • The document does not specify an adjudication method for the clinical image evaluation. It simply states "reviewed by MQSA qualified interpreting physicians."

4. 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 study comparing human readers with AI assistance versus without AI assistance was not done. The RMF-2000 is described as a digital mammography system (hardware + associated software for image acquisition and processing), not an AI algorithm for interpretation. The "clinical image evaluation" was to assess the image quality produced by the device, not to evaluate an AI's impact on human readers.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • Not applicable in the context of this document. This document describes a full-field digital mammography system, a medical device that produces images, not a standalone AI algorithm for image analysis. The evaluation was of the images produced by the device.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • The "ground truth" here is the expert assessment of image quality by MQSA qualified interpreting physicians and their determination of equivalence to images from a predicate device. There's no mention of pathology or outcomes data being used to establish a ground truth for disease presence, as the study's purpose was to evaluate device-produced image quality, not disease detection performance of an AI.

7. The sample size for the training set:

   • This question is not applicable to the information provided. The document describes a full-field digital mammography system, not an AI model that requires a training set. The "clinical image evaluation" is a validation of the device's image output, not a dataset for training.

8. How the ground truth for the training set was established:

   • This question is not applicable as there is no mention of a training set or AI model in the context of this 510(k) submission for the RMF-2000.

Ask a specific question about this device