(208 days)
The MAMMOMAT Inspiration PRIME system is intended for mammography exams, screening, diagnosis, and stereotactic biopsies under the supervision of medical professionals.
Mammographic images can be interpreted by either hard copy film or soft copy workstation.
Mammomat Inspiration PRIME is a floor-mounted mammography system for screening, diagnostic and biopsy procedures on standing, seated or recumbent patients.
The Mammomat Inspiration PRIME provides optional gridless acquisition and progressive reconstruction. During progressive reconstruction a unique algorithm replicates the function of the grid. The grid slides back and no longer absorbs primary radiation, therefore less radiation dose is needed. The Mammomat Inspiration PRIME in gridless acquisition mode reduces radiation dose up to 30 percent.
The system consists of an examination stand with integrated, microprocessorcontrolled, high-frequency generator as well as a radiation shield with an optional height-adjustable control desk in which the Acquisition Workstation (AWS) can be integrated. A swivel arm contains the X-ray tube on the top end and the object table with the detector on the bottom end.
The Siemens Mammomat Inspiration PRIME is a mammography system that introduces an optional gridless acquisition and progressive reconstruction algorithm designed to reduce radiation dose while maintaining image quality.
1. A table of acceptance criteria and the reported device performance
The provided text does not contain explicit acceptance criteria in a table format nor specific numerical performance metrics (e.g., sensitivity, specificity, AUC) for the device's diagnostic performance. Instead, it focuses on demonstrating that the new gridless acquisition mode with progressive reconstruction achieves dose reduction with equivalent image quality compared to the predicate device. The primary performance claim is dose reduction.
Key Claim: The modified Mammomat Inspiration Prime can lower dose up to 30 percent compared to the predicate (P030010/S006) with equivalent image quality.
Device Performance (as reported):
- Dose Reduction: Up to 30% reduction in radiation dose in gridless acquisition mode.
- Image Quality: Equivalent image quality to the predicate device, as evaluated with phantom testing and clinical image review.
2. Sample size used for the test set and the data provenance
The document explicitly mentions "clinical testing to quantify the potential of dose savings" (Section 10) and "clinical image review" (Section 8). However, it does not specify the sample size for the test set used in the clinical image review or the dose savings quantification. It also does not specify the data provenance (e.g., country of origin, retrospective or prospective nature).
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document states that "clinical image review" was conducted (Section 8), implying expert evaluation. However, it does not specify the number of experts involved or their qualifications (e.g., "radiologist with 10 years of experience").
4. Adjudication method for the test set
The document mentions "clinical image review" but does not describe any adjudication method (e.g., 2+1, 3+1, none) used for the test set results.
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
The submission describes a mammography system and its dose reduction technology, not an AI-based diagnostic tool intended to assist human readers. Therefore, an MRMC comparative effectiveness study involving AI assistance for human readers was not conducted or reported. The study focused on validating the image quality of the new gridless acquisition mode against a predicate device.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device in question, Mammomat Inspiration PRIME, is a mammography system that produces images. The "new algorithm for progressive image reconstruction" is an integral part of the image generation process, replacing the physical scatter radiation grid. Its performance in terms of image quality and dose reduction is inherently tied to the system itself.
While the algorithm functions independently in reconstructing the image, the evaluation of "equivalent image quality" (Section 8) implies human interpretation of those images. Therefore, a standalone algorithm-only diagnostic performance (without human in the loop for interpretation) was not the focus of this submission, as the device's output (images) is still intended for human review. The claim is about the quality of the image produced by the algorithm, not the algorithm's diagnostic capabilities.
7. The type of ground truth used
For the clinical image review, "equivalent image quality" was assessed. This likely implies a consensus-based expert review of the diagnostic quality and clarity of the images produced by the new system compared to those from the predicate device. The document also mentions "phantom testing" (Section 8), which uses objective, known ground truths provided by a phantom. However, for the clinical aspect, no specific external ground truth (like pathology or outcome data) is explicitly mentioned; rather, it appears to be a comparative assessment of image quality by experts.
8. The sample size for the training set
The document does not mention any "training set" in the context of an AI/machine learning algorithm for diagnostic purposes. The "progressive image reconstruction" is described as a "unique algorithm" (Section 5) that replicates the function of a grid. While such algorithms might involve some form of internal parameter optimization, the submission does not detail its development or refer to a distinct training set in the conventional sense of machine learning for diagnostic tasks.
9. How the ground truth for the training set was established
As no training set is discussed or implied for an AI diagnostic algorithm, the question of how its ground truth was established is not applicable based on the provided text. The algorithm's function is to reconstruct images by identifying and correcting for scatter, not to make a diagnosis.
§ 892.1715 Full-field digital mammography system.
(a)
Identification. A full-field digital mammography system is a device intended to produce planar digital x-ray images of the entire breast. This generic type of device may include digital mammography acquisition software, full-field digital image receptor, acquisition workstation, automatic exposure control, image processing and reconstruction programs, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). The special control for the device is FDA's guidance document entitled “Class II Special Controls Guidance Document: Full-Field Digital Mammography System.”See § 892.1(e) for the availability of this guidance document.