(15 days)
The Modified M-IV Mammography System is intended to produce radiographic images of the breast. It is suitable for reasons of images for initial examination for screening and diagnostic mammography. Screening mammography involves the production of images for initial examination for reasons of images for initial examination for Screening mainmography inverves the production of magnified images for more thorough examination of areas of the breast determined suspicious mages for more morough oxamilasses in the sampression views, and the unrough sereening manilies are . . . . . . . production of images used by a physician in preparation for biopsy.
Modified M-IV Mammography System
This document (K011987) is a 510(k) summary for a Modified M-IV Mammography System. It primarily focuses on regulatory compliance and the intended use of the device, rather than detailed performance studies and acceptance criteria typically associated with algorithm-driven devices.
Based on the provided text, the device is a mammography system, which is a hardware device for producing radiographic images, not an AI-enabled diagnostic algorithm. Therefore, many of the requested categories for AI device studies (like sample size for test/training sets, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, etc.) are not applicable to this submission.
The "acceptance criteria" discussed are primarily regulatory and operational standards for the mammography system itself, not performance metrics of an AI algorithm.
Here's a breakdown of the available information:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance (Compliance/Design) |
|---|---|
| Classification to UL Standard 187 | Designed for classification to UL Standard 187 |
| Classification to Canadian Standards Association, CSA Standard C22.2 No. 114 | Designed for classification by Underwriters Laboratories, Inc. to Canadian Standards Association, CSA Standard C22.2 No. 114 |
| Certification to International Electrotechnical Commission Standard IEC-601-1 | Designed for certification to International Electrotechnical Commission Standard IEC-601-1 |
| Conformity to Federal Performance Standards for Ionizing Radiation Emitting Products (21CFR 1000) | Tested and conforms to 21CFR 1000 |
| Meet requirements for American College of Radiology (ACR) accreditation (for image quality and radiation dose limits) | Designed to meet the requirements for ACR accreditation |
| User-friendly and comprehensive Operator's Manual (for safe and effective operation) | Comprehensive Operator's Manual provided, ensuring safe and effective operation |
Regarding the other requested information (which are largely not applicable to this type of device submission):
2. Sample sized used for the test set and the data provenance:
- Not Applicable. This submission is for a physical mammography system, not an AI algorithm. There is no "test set" of images or patient data in the context of an algorithm's performance.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not Applicable. Ground truth, in the context of AI, refers to expert consensus on disease presence/absence. This is not relevant for a hardware device submission.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not Applicable. No adjudication method for a test set is discussed as this is not an AI algorithm submission.
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:
- Not Applicable. This is a hardware device. No AI component is mentioned, and therefore, no MRMC study or assessment of human reader improvement with AI assistance would be performed or reported in this type of 510(k).
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not Applicable. This is a hardware device. "Standalone performance" in the context of an algorithm is not relevant here.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not Applicable. Ground truth in the context of disease diagnosis is not relevant for the regulatory acceptance of a mammography image acquisition system. The "ground truth" for this device is its adherence to technical standards and its ability to produce images, not the diagnostic accuracy of those images themselves.
8. The sample size for the training set:
- Not Applicable. This submission is for a physical mammography system. There is no AI training set involved.
9. How the ground truth for the training set was established:
- Not Applicable. As there is no AI training set, there's no ground truth establishment for it.
Summary Explanation:
This 510(k) submission (K011987) for the "Modified M-IV Mammography System" focuses on demonstrating the safety and effectiveness of the physical device itself, not on the performance of a diagnostic algorithm or AI. The "acceptance criteria" are therefore centered on compliance with established engineering, electrical safety, radiation emission, and imaging quality standards for mammography equipment (e.g., UL, CSA, IEC, 21CFR 1000, ACR guidelines). The document indicates that the device has been "designed for" these classifications/certifications and "tested and conforms" to the federal standards, suggesting internal testing and design verification were performed to meet these criteria.
The absence of information regarding test sets, training sets, expert review, or AI performance studies is entirely consistent with a 510(k) submission for a non-AI-enabled hardware device like a mammography machine.
§ 892.1710 Mammographic x-ray system.
(a)
Identification. A mammographic x-ray system is a device intended to be used to produce radiographs of the breast. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.