(178 days)
The Aspire CR for Mammography (CRm) System is indicated for generating mammographic images that can be used for screening and diagnosis of breast cancer. The Fuji Aspire CRm System is intended to be used in the same clinical applications as traditional film/screen systems.
The FCR Aspire CRm is Fuji's newest reader to join our CR for mammography (FCRm) line of mammography readers (ClearView CSm and ClearView 1-m). The Aspire CRm system is composed of an Aspire CRm image reader, a new 50 micron HR VI single sided image plate (IP), and the same Fuji Flash Plus IIPm acquisition workstation as our approved FCRMS. In addition, any cleared dedicated mammographic x-ray machine may be used with the Aspire CRm system to generate digital mammographic images for screening and diagnosis of breast cancer. The mammographic images can be interpreted by a qualified physician using either hardcopy film or softcopy display at a 5 megapixel 510(k) cleared for mammography soft copy review station, and optionally printed on a 510(k) cleared for mammography printer.
Here's an analysis of the provided text regarding the Aspire CR for Mammography (CRm) FFDM System, focusing on acceptance criteria and supporting studies:
It's important to note that this 510(k) summary is for a substantial equivalence determination, not an approval based on specific performance criteria demonstrated against a disease state. The primary goal is to show that the new device performs "as well as" or "similarly to" legally marketed predicate devices, especially regarding physical image quality parameters. Therefore, the "acceptance criteria" here are more about demonstrating comparable technical performance than clinical outcome thresholds.
Acceptance Criteria and Reported Device Performance
The document doesn't explicitly state quantitative clinical acceptance criteria a typical medical device would have (e.g., AUC > X, Sensitivity > Y at Specificity Z). Instead, it focuses on demonstrating substantial equivalence to predicate devices through technical performance studies and an image attribute evaluation. The implied "acceptance criteria" for the preclinical studies are that the Aspire CRm's performance should be comparable or equivalent to the predicate devices in the listed parameters.
| Acceptance Criteria (Implied: Comparable to predicate devices) | Reported Device Performance (Summary) |
|---|---|
| Preclinical Studies | The results demonstrate that our proposed device is substantially equivalent to our cleared predicate devices. |
| Sensitometric Response | Aspire CRm performed as well as the predicate devices. |
| Spatial Resolution | Aspire CRm performed as well as the predicate devices. |
| Noise Analysis | Aspire CRm performed as well as the predicate devices. |
| Detective Quantum Efficiency (DQE) | Aspire CRm performed as well as the predicate devices. |
| Dynamic Range-NEQ | Aspire CRm performed as well as the predicate devices. |
| Dynamic Range-DQE | Aspire CRm performed as well as the predicate devices. |
| Image Erasure and Fading Test | Aspire CRm performed as well as the predicate devices. |
| Image Fogging Test | Aspire CRm performed as well as the predicate devices. |
| ACR Phantom Scoring (2cm, 4.2cm, 6cm) | Aspire CRm performed as well as the predicate devices. |
| CD MAM Scoring | Aspire CRm performed as well as the predicate devices. |
| MTF Comparison (Aspire CRm vs. Kodak DirectView CR) | Performance is comparable (explicitly stated "Aspire CRm (HR-VI) / Kodak DirectViewCR (EHR-M2) MTF Comparison"). |
| DQE Comparison (Aspire CRm vs. Kodak DirectView CR) | Performance is comparable (explicitly stated "Aspire CRm (HR-VI) / Kodak DirectViewCR (EHR-M2) DQE Comparison"). |
| Clinical Image Studies | Images were of sufficiently acceptable quality for clinical mammographic usage. |
Study Details
-
Sample sizes used for the test set and the data provenance:
- Preclinical Studies: The document does not specify the exact sample size for each individual preclinical test (e.g., number of measurements, number of phantoms used). It states these tests were performed in accordance with Section 8 of the Class II Special Controls Guidance Document: Full-Field Digital Mammography System.
- Clinical Image Studies: The document mentions "An image attribute evaluation was conducted." It does not specify the number of images or cases included in this evaluation.
- Data Provenance: Not explicitly stated for either preclinical or clinical image studies (e.g., country of origin). The studies appear to be prospective or experimental studies conducted by the manufacturer, rather than retrospective analysis of existing clinical data.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- For the "Image attribute evaluation," the document does not specify the number of experts or their qualifications. However, for mammography, these would typically be board-certified radiologists experienced in mammography interpretation.
- For preclinical phantom studies, "ground truth" is established by the known physical properties of the phantoms and the objective measurements of the device's performance.
-
Adjudication method for the test set:
- The document does not specify an adjudication method for the image attribute evaluation. If multiple experts were involved, a consensus or majority read often serves as adjudication, but this is not detailed here. For preclinical objective measurements, adjudication is not typically relevant as the results are quantitative.
-
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, an MRMC comparative effectiveness study was not done.
- The document describes an "image attribute evaluation," which assesses image quality for clinical usage, but not a study comparing human reader performance with and without AI assistance. The device in question is a Full-Field Digital Mammography (FFDM) System (hardware and associated processing), not an AI-assisted interpretation product. Therefore, the concept of "human readers improve with AI vs without AI assistance" is not applicable to this submission.
-
If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
- Yes, in essence, standalone performance was evaluated for the physical image acquisition and processing system. The preclinical studies (e.g., DQE, MTF, noise, sensitometric response, phantom scoring) are evaluations of the system's inherent image quality performance, which is a form of standalone testing for the image generation algorithm and hardware. The "image attribute evaluation" also assesses the quality of images produced solely by the system before human interpretation.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Preclinical Studies: The ground truth for these studies is based on controlled phantom measurements and objective physical parameters (e.g., known object sizes in phantoms, defined input X-ray dosages, standard test patterns).
- Clinical Image Studies: For the "image attribute evaluation," the ground truth for "sufficiently acceptable quality for clinical mammographic usage" would implicitly come from expert readers' subjective assessment of image quality (e.g., clarity of structures, presence of artifacts, visibility of clinical features). It does not reference pathology or outcomes data to establish ground truth for individual cases.
-
The sample size for the training set:
- The document does not provide information on a training set sample size. This device is an image acquisition and processing system, not typically an AI/machine learning algorithm that requires a distinct "training set" in the context of diagnostic decision-making. The system's processing parameters are likely tuned and optimized during development, but this is not described as a "training set" in the common AI sense.
-
How the ground truth for the training set was established:
- As no "training set" is described for an AI/ML algorithm, this question is not applicable in the context of this 510(k) submission. Parameters of the image processing pipeline would be tuned based on engineering principles and optimization for image quality metrics, often against known physical phantom data or expert assessment of image appearance, rather than a labeled clinical training set for disease detection.
§ 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.