(122 days)
MammoWorkstation is designed to assist radiologists in conducting primary diagnostic review for diagnostic and screening mammography through flexible and interactive manipulation of multi-modality softcopy images. It provides image review, manipulation, analysis, post-processing and printing capabilities that support image management display needs in the medical environment.
MammoWorkstation is designed to give easy and economic access to and display of multi-modality softcopy images, structured reports, and CAD results through interfaces to various image storage devices using DICOM or similar interface standards. It supports creation of structured reports according to the DICOM breast imaging report templates.
MammoWorkstation supports teleradiology and teleconferencing providing access to multi-modality softcopy images and structured reports in multiple locations within and outside the hospital.
Lossy compressed mammographic images must not be used for primary diagnostic interpretation unless approved for use in digital mammography.
Display monitors used for primary diagnostic interpretation of mammographic images must be approved for use in digital mammography.
All images sent to or imported in the Mammoworkstation must conform to regulatory requirements. Image quality must conform with applicable quality guidelines. All modalities must be certified for soft-copy reading.
The MammoWorkstation is a medical image review workstation software for diagnostic and screening mammography. MammoWorkstation has the capability to review Digital Breast Tomosynthesis (DBT) images that are compatible with DICOM Breast Tomosynthesis Image Storage. A synthetized 2D image, called V-Preview, is generated from the GE DBT set by MammoWorkstation and can be displayed before or during the diagnostic interpretation review of the DBT set. It can be used for the pre-review of the DBT set or as additional image but does not replace the FFDM image. It is a software product
The provided text describes a 510(k) premarket notification for the "MammoWorkstation" and includes a summary describing its functionality and comparison to a predicate device. However, it does not explicitly contain a study directly proving the device meets specific acceptance criteria with detailed performance metrics, sample sizes, expert qualifications, or adjudication methods.
The document states that the MammoWorkstation is considered "substantially equivalent to the predicate device" and that its "applications comply with voluntary standards as detailed in Section 9, 11 and 17 of this premarket submission." It also mentions "Performance testing (Verification)" and "Simulated use testing (Validation)" as part of the quality assurance measures.
Without those specific sections (9, 11, and 17) or further details within the provided text, it's impossible to extract the precise acceptance criteria and the comprehensive study data.
Therefore, I can only provide an answer based on the information available in the provided text.
Here's a breakdown of what can and cannot be answered based on the provided document:
Acceptance Criteria and Device Performance (Based on provided text, specific metrics are not available):
| Acceptance Criteria (Inferred from device description and comparison) | Reported Device Performance (Specificity is lacking in the provided text) |
|---|---|
| Functional Equivalence: | |
| - Ability to assist radiologists in primary diagnostic review for diagnostic and screening mammography. | "MammoWorkstation is designed to assist radiologists in conducting primary diagnostic review..." |
| - Flexible and interactive manipulation of multi-modality softcopy images. | "...through flexible and interactive manipulation of multi-modality softcopy images." |
| - Image review, manipulation, analysis, post-processing, and printing capabilities. | "It provides image review, manipulation, analysis, post-processing and printing capabilities..." |
| - Support for image management display needs. | "...that support image management display needs in the medical environment." |
| - Easy and economic access and display of multi-modality softcopy images, structured reports, and CAD results. | "MammoWorkstation is designed to give easy and economic access to and display of multi-modality softcopy images, structured reports, and CAD results..." |
| - Interface to various image storage devices using DICOM or similar standards. | "...through interfaces to various image storage devices using DICOM or similar interface standards." |
| - Support for creation of structured reports according to DICOM breast imaging report templates. | "It supports creation of structured reports according to the DICOM breast imaging report templates." |
| - Support for teleradiology and teleconferencing with access to images and reports in multiple locations. | "MammoWorkstation supports teleradiology and teleconferencing providing access to multi-modality softcopy images and structured reports in multiple locations..." |
| - Compatibility with DICOM Breast Tomosynthesis Image Storage. | "MammoWorkstation has the capability to review Digital Breast Tomosynthesis (DBT) images that are compatible with DICOM Breast Tomosynthesis Image Storage." |
| - Generation and display of V-Preview (synthesized 2D) images from GE DBT sets. | "A synthetized 2D image, called V-Preview, is generated from the GE DBT set by MammoWorkstation and can be displayed..." |
| Safety and Effectiveness: | |
| - Considered as safe and effective as the predicate device (K123575). | "GE Healthcare considers the MammoWorkstation to be as safe, as effective, and performance is substantially equivalent to the predicate device." |
| - Compliance with voluntary standards. | "The MammoWorkstation and its applications comply with voluntary standards as detailed in Section 9, 11 and 17 of this premarket submission." (Specific standards not detailed here) |
| Specific V-Preview functionality (difference from predicate): | |
| - V-Preview images labeled as "2D: Synthesized" and "V-Preview For navigation use only does not replace FFDM". | "The V-Preview images will be labeled as "2D: Synthesized" and "V-Preview For navigation use only does not replace FFDM" to distinguish them from non-synthesized images." |
| - V-Preview images can be annotated and printed or transferred to PACS. | "V-Preview images can be annotated and printed or transferred to a PACS for storage or viewing in alternate locations." |
| - V-Preview images can be generated by DicomShuttle configuration. | "In addition to the standard MammoWorkstation configuration, V-Preview images can be generated by the DicomShuttle configuration." |
1. Sample sized used for the test set and the data provenance:
- Sample Size: Not specified in the provided text. The document refers to "Performance testing (Verification)" and "Simulated use testing (Validation)" but does not provide details on the sample size of images/cases used in these tests.
- Data Provenance: Not specified in the provided text (e.g., country of origin, retrospective or prospective).
2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not specified in the provided text. The document refers to "Simulated use testing (Validation)" but does not mention the involvement or qualifications of experts for establishing ground truth. The device is designed to assist radiologists, implying radiologists are the end-users and implicitly the experts for interpretation, but their role in establishing ground truth for testing is not detailed here.
3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not specified in the provided text. There is no information regarding how discrepancies among experts (if any were used) were resolved.
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 MRMC study described: The document describes the device as a "medical image review workstation software" that "assists radiologists." While its function is in assisting radiologists, the provided text does not describe an MRMC comparative effectiveness study that quantitatively measures the improvement of human readers with AI assistance versus without. The focus is on substantial equivalence to a predicate device, not on demonstrating reader improvement.
- Effect Size: Not applicable, as no such study is described.
5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The MammoWorkstation is described as software that "assists radiologists" and is a "medical image review workstation software." It is not presented as a standalone AI algorithm that provides diagnostic interpretations without human intervention. Its stated purpose implies human-in-the-loop performance, but the document does not distinguish between standalone algorithm performance and human-in-the-loop performance studies. Given its classification as a picture archiving and communications system, it's primarily a viewing and manipulation tool rather than an autonomous diagnostic AI.
6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not specified in the provided text.
7. The sample size for the training set:
- Not specified in the provided text. The document refers to "Performance testing (Verification)" and "Simulated use testing (Validation)" but does not provide details of any training set, implying these tests are for verification/validation of existing software functionality rather than for a machine learning model that would require a distinct training set.
8. How the ground truth for the training set was established:
- Not applicable, as no training set (for an AI/ML model) is explicitly mentioned or detailed in the provided text. The device primarily functions as an image viewing and manipulation workstation.
§ 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).