(365 days)
DM-Density is a software application intended for use with compatible full field digital mammography systems. DM-Density calculates percent breast density defined as the ratio of fibroglandular tissue to total breast area estimates. DM-Density provides these numerical values for each breast as well as a density category to aid interpreting physicians in the assessment of breast tissue composition. DM-Density produces adjunctive information. It is not a diagnostic aid.
DM-Density is a standalone software application that automatically analyzes "for presentation" full field digital mammograms to calculate breast tissue composition. The software processes full field digital mammograms according to proprietary algorithms and generates a Breast Density Grade in accordance with the American College of Radiology's Breast Imaging Reporting and Data System (BI-RADS) density classification scales. DM-Density has been validated on Hologic's Selenia Dimensions and Lorad Selenia systems. DM-Density data output is packaged for viewing on a mammography workstation or PACS as a DICOM mammography Structured Report or Secondary Capture. Output may also be transmitted to a RIS.
Here's a breakdown of the acceptance criteria and study information for DM-Density, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Metric) | Reported Device Performance |
|---|---|
| Reliability | Assessed using Pearson's Correlation Coefficient for DM-Density percent density, dense breast area, and total area measurements (Left/Right breasts, CC/MLO views). |
| Accuracy (Percent Density) | Validated DM-Density percent density and total area measurements. The accuracy of dense breast area measurements follows by implication. |
| Accuracy (Breast Density Grade) | Validated using the Kappa statistic against known Breast Density Grade assessments. |
| Reproducibility | Assessed with Pearson Correlation Coefficient using a dataset of subjects with two mammograms within a two-year period. |
| Inverse Relationship to Age | Assessed by calculating Pearson's Correlation Coefficient between DM-Density percent density measures and age at time of screening. |
Note: The document does not provide specific numerical thresholds for "acceptance" (e.g., Pearson's correlation coefficient > 0.9, Kappa > 0.8). It only states that testing was performed "in accordance with Densitas' design control processes" and that "DM-Density product specifications have been met."
2. Sample Size Used for the Test Set and Data Provenance
The exact sample size for each specific test (Reliability, Accuracy, Reproducibility, Inverse relationship to age) is not explicitly stated in the provided document.
- Data Provenance: The data used for reproducibility testing was from "subjects who had two mammograms acquired on compatible mammography acquisition systems within a two year time period." The document doesn't specify the country of origin, but it does mention that DM-Density has been validated on Hologic's Selenia Dimensions and Lorad Selenia systems.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: "Expert radiologist visual assessments" were used for validation, but the exact number of experts is not specified.
- Qualifications of Experts: They are referred to generally as "expert radiologists." No further details on their specific experience (e.g., years of experience, subspecialty) are provided.
4. Adjudication Method for the Test Set
The adjudication method for establishing ground truth from the expert radiologists is not explicitly stated. It mentions "expert radiologist visual assessments," but doesn't specify if it was a consensus, majority vote, or other method.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was an MRMC study done? No, the document states, "There was no human clinical testing required to support the medical device." This indicates that no MRMC study involving human readers and AI assistance was conducted or reported.
6. Standalone (Algorithm Only) Performance Study
- Was a standalone study done? Yes, the described performance testing (Reliability, Accuracy, Reproducibility, Inverse Relationship to Age) assesses the DM-Density software's performance as a standalone algorithm without human intervention.
- The "Accuracy" assessment specifically states "validating DM-Density percent density and total area measurements" and "validating the Breast Density Grade assessments to known Breast Density Grade assessments using the Kappa statistic," which are direct measures of the algorithm's performance against derived ground truth.
7. Type of Ground Truth Used
- For Accuracy (Breast Density Grade): "expert radiologist visual assessments of mammography density" were used to establish "known Breast Density Grade assessments." This indicates expert consensus or individual expert assessment as ground truth for density categories.
- For Accuracy (Percent Density) and Reliability: The ground truth for percent density, dense breast area, and total area measurements is implied to be a carefully measured value derived from the same images, likely through a reference method or manual segmentation, which the algorithm is then compared against. The document doesn't explicitly state the method for this specific ground truth, but it's not pathology or outcomes data.
8. Sample Size for the Training Set
The sample size for the training set is not provided in the document. The document refers to "proprietary algorithms" but does not detail their development or the data used for training.
9. How the Ground Truth for the Training Set Was Established
The document does not provide information on how the ground truth for the training set was established. It only discusses "proprietary algorithms" and validation testing.
§ 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).