(48 days)
The Advance Image Enhancement, Inc.'s Region of Interest Image Enhancement software is intended to improve the sharpness and clarity of subtle image features. The device used with FDA cleared monitors may be used by a trained physician or healthcare professional for display. manipulation and interpretation of lossless compressed mammographic images for screening and diagnostic mammography, as well as any other DICOM multi-modality image.
The AIE software is intended as an added tool residing on any DICOM image workstation for improving the radiologist's perception of image features on any lossless compressed or noncompressed multi-modality DICOM "for-presentation" image. This software would be used while the radiologist is reviewing magnification window image segments on FDA cleared monitors and is intended to complement existing DICOM image workstation functionality.
Warning: Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretations. Mammographic images may only be interpreted using an FDA approved monitor that offers at least 5 Mpixel resolution and meets other technical specifications reviewed and accepted by FDA.
The Region of Interest Image Enhancement for Digital Mammography (ROILE-DM) software created by Advanced Image Enhancement, Inc. is intended to improve the overall ability of an image reader to resolve abnormalities with greater confidence in their findings. The AIE software is intended to improve the sharpness and clarity of subtle image features. The device used with FDA cleared monitors may be used by a trained physician for display, manipulation and interpretation of lossless compressed or noncompressed mammographic images for screening and diagnostic mammography, as well as any other DICOM multi-modality image. The intended operational environment is the radiology reading room or any other FDA approved environment.
Here's an analysis of the acceptance criteria and study details based on the provided text for device K062059:
The provided submission does not explicitly state acceptance criteria in a quantitative or pass/fail format. Instead, it describes a comparative study against a predicate device to demonstrate substantial equivalence and establish that the device is safe and effective for its intended use. The "acceptance criteria" are implicitly met if the study demonstrates substantial equivalence to the predicate device.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|
| Substantial equivalence to predicate device (Hologic, Inc.'s SecureView DX Softcopy Workstation) for intended use. | The study showed that the AIE Region of Interest Enhancement Software is substantially equivalent to the predicate device. |
| Safe and effective for its intended use (improving sharpness and clarity of subtle image features in mammography for trained physicians). | The information provided in the premarket notification submission demonstrated that the device is safe and effective for its intended use. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: 50 mammography cases.
- Data Provenance: Not explicitly stated (e.g., country of origin, retrospective or prospective).
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The text describes a "reader study," but it does not specify how ground truth was established for the 50 mammography cases. The 6 radiologists performed a "features analysis comparing" the devices, implying they were evaluating the images themselves rather than establishing a separate ground truth.
- Number of Experts for Ground Truth: Not explicitly stated, as the study description focuses on reader comparison rather than ground truth establishment by these readers.
- Qualifications of Experts: 6 MQSA certified Radiologists.
4. Adjudication Method for the Test Set
Not specified. The study description states they "performed a features analysis comparing" the devices, but it doesn't detail any adjudication method for reaching a consensus or ground truth among the readers.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs Without AI Assistance
- MRMC Comparative Effectiveness Study: Yes, a reader study was conducted where "6 MQSA certified Radiologists... performed a features analysis comparing the AIE Region of Interest Enhancement Software to the predicate device on 50 mammography cases." This implies a comparative study between the two software tools.
- Effect Size of Human Readers Improvement with AI vs. Without AI Assistance: The document does not provide a quantitative "effect size" or a direct comparison of readers with and without AI assistance. The comparison was between the AIE software and a predicate device (Hologic SecureView DX Softcopy Workstation). The study concluded substantial equivalence, suggesting comparable performance, but no metrics on specific improvement are given.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done
No, the device is described as an "added tool residing on any DICOM image workstation for improving the radiologist's perception" and is "used by a trained physician" for display, manipulation, and interpretation. The clinical testing performed was a reader study. There is no indication of a standalone algorithm performance evaluation.
7. The Type of Ground Truth Used
The document does not explicitly state the type of ground truth used for the 50 mammography cases in the reader study. Since the study involved radiologists comparing features, it's possible that the "ground truth" was based on established clinical findings or a reference standard that was not explicitly detailed in this summary. However, it is not stated as pathology, outcome data, or expert consensus specifically.
8. The Sample Size for the Training Set
Not applicable. The description is of a 510(k) submission, which focuses on demonstrating device safety and effectiveness, often through comparison to a predicate. It does not provide details about the development or training of the AIE software.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as no information regarding a training set or its ground truth establishment is provided in the document.
§ 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).