(98 days)
McKesson Radiology Mammography Plus™ ("Mammography Plus"), is an accessory to McKesson Radiology Station™, a component of McKesson Radiology™. McKesson Radiology is medical image and information management software that is intended to receive, transmit, store, archive, manage, display, print and process digital medical images, digital medical video and associated patient and medical information. McKesson Radiology™ includes a suite of standalone, web-enabled software components, and is intended for installation and use with off-the-shelf hardware that meets or exceeds minimum specifications.
McKesson Radiology Station™ is the primary software component used for processing and presentation of medical images on display devices with network access to McKesson Radiology. McKesson Radiology Station is intended to process and display lossless and non-lossed medical images provided from DICOM conformant modalities such as X-Ray Radiography (including digital mammography), X-Ray Computed Tomography, Magnetic Resonance Imaging. Ultrasound, and Nuclear Medical images obtained from other DICOM-compliant modalities.
Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretations.
Mammographic images may only be interpreted using cleared monitors intended for mammography display.
McKesson Radiology is indicated for use by qualified healthcare professionals including, but not restricted to, radiologists. non-radiology specialists, physicians and technologists.
Mammography Plus, an accessory to the McKesson Radiology Station, the radiology viewing component of McKesson Radiology, consists of image display and manipulation tools that help radiologists zoom in onto an image, interpret Computer Aided Detection (CAD) findings, navigate through and visualize digital mammography and Digital Breast Tomosynthesis (DBT) images, compare historically similar images, and configure their reading environment.
Mammography Plus uses the underlying capabilities of McKesson Radiology's diagnostic viewer, McKesson Radiology Station, to integrate specialized functionality into the diagnostic reading workflows. The McKesson Radiology Station viewer interfaces with the McKesson Radiology Platform to access patient and study information.
Here's an analysis of the provided text regarding the acceptance criteria and study for the McKesson Radiology Mammography Plus device:
The provided documents (K142850) do not contain typical acceptance criteria for specific performance metrics (e.g., sensitivity, specificity, AUC) or a dedicated clinical study demonstrating these metrics against ground truth. Instead, the submission focuses on verifying the device's functionality and image quality against established standards and its substantial equivalence to a predicate device for its intended use as a PACS accessory with mammography viewing and manipulation tools.
The "Performance Data" section describes verification and validation testing, which are typically aimed at ensuring the device meets its design specifications and complies with relevant regulatory and consensus standards.
Here's a breakdown of the requested information based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
Note: The document does not provide specific quantitative "acceptance criteria" related to diagnostic performance (e.g., sensitivity, specificity) for the device itself. The acceptance is based on functional verification, compliance with standards, and demonstration of substantial equivalence.
| Acceptance Criterion (Implicit/Standard-based) | Reported Device Performance |
|---|---|
| Functional Verification: | Functioned as intended. |
| ISO 13485:2003 Compliance | Verification and validation testing performed. |
| IEC 62304:2006 Compliance | Verification and validation testing performed. |
| ISO 14971:2007/ EN 14971:2012 Compliance | Verification and validation testing performed. |
| NEMA XR 22-2006 (Image Quality) | Bench testing included testing to conform to this standard. |
| NEMA XR 23-2006 (Image Quality) | Bench testing included testing to conform to this standard. |
| IEC/ ISO 10918-1:1994 (Image Quality) | Bench testing included testing to conform to this standard. |
| NEMA PS 3.1 - 3.20 (2014) DICOM Compliance | Bench testing included testing to conform to this standard. |
| AAPM TG18 Test Patterns (Display Performance) | Bench testing performed using these patterns in conjunction with AAPM On-line Report No. 03. |
| SMPTE Test Pattern (Display Performance) | Bench testing performed using this pattern (RP 133-1991). |
| MQSA Compliance | Bench testing included testing to conform to this act. |
| Usability Assessments | Performed (compared to predicate). |
| Image Quality Assessments | Performed (compared to predicate). |
| Substantial Equivalence to Predicate | Observed results demonstrated substantial equivalence with predicate devices. |
2. Sample Size Used for the Test Set and Data Provenance
The document does not describe a "test set" in the context of a diagnostic performance study with patient data. The testing described is primarily focused on functional verification, image quality assessment, and usability. Therefore, there is no information provided on the sample size or data provenance (country, retrospective/prospective) for a clinical test set as one would typically find for a diagnostic AI algorithm.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
As there is no mention of a diagnostic performance study with a clinical test set, there is no information provided on the number of experts or their qualifications for establishing ground truth for such a test set.
4. Adjudication Method for the Test Set
Since a diagnostic performance study with a clinical test set is not described, there is no information on adjudication methods.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
The document does not describe a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance. The device is characterized as an accessory for image display and manipulation, not as a diagnostic AI tool that directly provides CAD findings (though it supports interpretation of CAD findings from other systems).
6. Standalone Performance Study
A standalone performance study (i.e., algorithm only without human-in-the-loop performance evaluation) for diagnostic accuracy is not described in the provided text. The device's performance is gauged by its ability to meet design specifications, adhere to industry standards for image quality and display, and its usability as an accessory.
7. Type of Ground Truth Used
For the described verification and validation, the "ground truth" is implicitly related to:
- Design Specifications: The device's intended functionality.
- Consensus Standards: (e.g., NEMA, AAPM, DICOM) which define expected behavior for image display and processing.
- Predicate Device Performance: Used for comparison in usability and image quality assessments.
There is no mention of pathology, outcomes data, or expert consensus on patient cases being used as ground truth for diagnostic accuracy in a clinical study.
8. Sample Size for the Training Set
The document does not describe a machine learning algorithm or AI model requiring a "training set." McKesson Radiology Mammography Plus is presented as software for image display, manipulation, and workflow integration for mammography images, including support for CAD findings (presumably from other CAD systems). Therefore, no information on a training set size is provided.
9. How the Ground Truth for the Training Set Was Established
Since no training set is mentioned as part of the device's development, this information is not applicable and not provided.
§ 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).