(43 days)
Volpara is a software application intended for use with the raw data from digital breast x-ray systems, including tomosynthesis. Volpara calculates and quantifies a density map and from that determines volumetric breast density as a ratio of fibroglandular tissue and total breast volume estimates. Volpara provides these numerical values along with a BI-RADS breast density 4th or 5th Edition category to aid health care professionals in the assessment of breast tissue composition. Volpara is not an interpretive or diagnostic aid and should be used only as adjunctive information when the final assessment of breast density category is made by an MQSA qualified interpreting physician.
The Volpara 1.5.2 software provides volumetric assessment of digital x-ray images of the breast, including in that definition both digital mammograms and raw tomosynthesis projections. The assessment takes the form of generating and validating density maps where the value at each pixel represents the thickness of fibroglandular tissue between that pixel and the x-ray source. From those density maps various quantitative densitymap based statistics are computed, namely:
- volume of fibroglandular tissue in cm3, ●
- volume of breast in cm3 ●
- the volumetric breast density in %,
- a BI-RADS 4th Edition or 5th Edition breast density category ●
- average thickness of dense tissue
- maximum thickness of dense tissue
- maximum volume of dense tissue above any 1cm² square region ●
The device outputs those numbers along with the density maps themselves marked with the location of the various maxima.
Volpara operates on a Windows server that meets Volpara data input and output requirements and generally is located outside the patient environment. The device does not contact the patient, nor does it control any life-sustaining devices.
Here's a breakdown of the acceptance criteria and the study information based on the provided text for the Volpara Imaging Software:
Note: The provided document is a 510(k) summary for a modification to an existing device (Volpara Imaging Software 1.5.2 building on 1.5.1). Therefore, much of the comprehensive study data might be referenced from the predicate device's clearance (K152028). The current document focuses on verification and validation for the specific modifications.
Acceptance Criteria and Reported Device Performance
The document does not explicitly list a table of quantified acceptance criteria with corresponding device performance metrics in the format requested. Instead, it describes various "Performance Data" and states that "established acceptance criteria was met for all of the tests conducted."
However, we can infer the types of performance criteria based on the verification bench testing:
| Acceptance Criteria (Inferred from Test Objective) | Reported Device Performance (Summary from text) |
|---|---|
| Measurement accuracy (Volpara estimates vs. known values from phantoms) | "Measurement accuracy was assessed by comparing Volpara estimates with known values from breast phantoms." - "All verification and validation testing was successful in that established acceptance criteria was met." |
| Relationship to ground truth (Volpara estimates vs. 3D breast MRI data for fibroglandular tissue) | "Relationship to ground truth was assessed by running Volpara over x-ray images of breasts for which there was 3D breast MRI data available with a comparison of estimates of fibroglandular tissue." - "All verification and validation testing was successful in that established acceptance criteria was met." |
| Reproducibility (Volpara results for breast density compared with expected decrease with age) | "Reproducibility was assessed by running Volpara over substantial datasets where we have the women's age and results compared with the expected and known decrease in breast density with age." - "All verification and validation testing was successful in that established acceptance criteria was met." |
| Reproducibility (Volpara results for left/right breasts and CC/MLO views) | "Reproducibility was assessed by running Volpara over substantial data sets and the results for left and right breasts and CC and MLO views were compared to confirm that the results were similar for each view and each breast." - "All verification and validation testing was successful in that established acceptance criteria was met." |
| Reproducibility (Volpara results for same woman imaged on GE and Hologic systems one year apart) | "Reproducibility was assessed by running Volpara over substantial data sets where the same woman had been imaged on GE and Hologic systems one year apart and the results were compared to confirm they were similar." - "All verification and validation testing was successful in that established acceptance criteria was met." |
| Reproducibility (Volpara results for same woman imaged on GE, Hologic, Siemens tomosynthesis-compatible units in both tomosynthesis and mammography modes) | "Reproducibility was assessed by running over substantial data sets where the same woman had been imaged on one of GE, Hologic and Siemens tomosynthesis-compatible units running in both tomosynthesis and mammography modes, and the results were compared to confirm they were similar." - "All verification and validation testing was successful in that established acceptance criteria was met." |
| Relationship to visual assessment (Volpara BI-RADS category vs. MQSA qualified radiologist assessment) | "Relationship to visual assessment was assessed by running Volpara over x-ray images for which a BI-RADS 4th and 5th Edition density category was available from MQSA qualified radiologists followed by a comparison of the two sets of data." - "All verification and validation testing was successful in that established acceptance criteria was met." |
| Physician ability to integrate software and assess usability (Beta site testing) | "Beta site testing to assess the ability of physicians to successfully integrate the software into their existing systems as well as assess usability for target users." - "All verification and validation testing was successful in that established acceptance criteria was met." |
| Comparison of Volpara breast densities to existing databases (Beta site testing) | "Beta site testing to collect minimum, average and maximum Volpara breast densities and compare these to other existing databases." - "All verification and validation testing was successful in that established acceptance criteria was met." |
Study Information
-
Sample size used for the test set and the data provenance:
- Sample Size: Not explicitly stated with a specific number for each test. The text frequently uses the phrase "substantial datasets," indicating a significant but unspecified quantity of images/patients.
- Data Provenance: Not explicitly stated (e.g., country of origin). Some tests involve "x-ray images of breasts" and "existing databases." For the reproducibility tests involving different imaging systems (GE, Hologic, Siemens), it implies multi-vendor data. The "expected and known decrease in breast density with age" suggests real-world patient data.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not explicitly stated how many specifically, but for the "Relationship to visual assessment" ground truth, it states, "BI-RADS 4th and 5th Edition density category was available from MQSA qualified radiologists."
- Qualifications: "MQSA qualified radiologists." (MQSA refers to the Mammography Quality Standards Act, implying specialized training and certification in mammography interpretation).
-
Adjudication method for the test set:
- Not explicitly stated. For the visual assessment comparison, it mentions a "comparison of the two sets of data" (Volpara vs. radiologists), but details on how discrepancies were resolved or if consensus reading was performed are not provided.
-
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 comparative effectiveness study is described in this document. The device is explicitly stated as "not an interpretive or diagnostic aid and should be used only as adjunctive information." Therefore, the study focuses on the device's accuracy and reproducibility in providing density measurements, not on improving human reader performance.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, the verification and validation tests described are primarily standalone performance assessments of the Volpara algorithm in calculating density, reproducibility, and correlation with other measurements (MRI, radiologist BI-RADS assessment). The beta site testing involves physicians but to assess usability and integration, not to measure human-in-the-loop diagnostic performance.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc):
- Known values from breast phantoms: For measurement accuracy.
- 3D breast MRI data: For fibroglandular tissue volume comparison (considered a more objective measure than visual assessment).
- Expected and known decrease in breast density with age: For reproducibility validation.
- MQSA qualified radiologists' BI-RADS 4th and 5th Edition density categories: For comparison to visual assessment.
- Existing databases: For comparison of Volpara breast densities during beta site testing.
-
The sample size for the training set:
- The document does not provide information about the training set size or methodology. This is a 510(k) summary for a device modification, and often details about initial model training are not reiterated if they were part of the predicate device's submission.
-
How the ground truth for the training set was established:
- Not specified in this 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).