(27 days)
R2 DigitalNow HD is a software application intended to process digitized screen-film mammograms for comparison purposes only. The software processes digitized prior film images to produce lossy-compressed DICOM images that more closely resemble digital mammography images. R2 DigitalNow HD images are intended for comparison purposes only and cannot be used for primary diagnosis.
DigitalNow HD is a software application which runs on the Hologic Cenova server (Class I exempt per 21 CFR § 892.2010 and 21 CFR § 892.2020).
R2 DigitalNow HD is a software application intended to process digitized screen-film mammograms.
The provided text does not contain detailed information about specific acceptance criteria or the study that rigorously proves the device meets those criteria. The submission is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device rather than comprehensive performance validation against defined acceptance criteria.
However, based on the implied acceptance criteria for a 510(k) submission and the information provided, we can infer some aspects:
The primary "acceptance criterion" for this 510(k) submission appears to be demonstrating substantial equivalence to the predicate device (DexTop Mammography Workstation K080351 for certain software functions) in terms of intended use, technological characteristics, and safety and effectiveness.
Here's an attempt to structure an answer based on the given information, highlighting what is present and what is absent:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criterion (Inferred from 510(k) Goal) | Reported Device Performance (Summary from Document) |
|---|---|
| Substantial Equivalence to Predicate Device | The FDA reviewed the 510(k) and determined the device is substantially equivalent to legally marketed predicate devices for the stated indications for use. |
| Intended Use Equivalence | "R2 DigitalNow HD is a software application intended to process digitized screen-film mammograms for comparison purposes only." This matches the general scope of such software. |
| Technological Characteristics Equivalence | DigitalNow HD is described as "a software application intended to process digitized screen-film mammograms." The submission would have detailed its algorithms and processing. |
| Safety and Effectiveness | "The 510(k) Pre-Market Notification for DigitalNow HD contains adequate information and data to enable FDA - CDRH to determine substantial equivalence..." |
| "General Safety and Effectiveness Concerns: The device labeling contains instructions for use and any necessary cautions and warnings to provide for safe and effective use of this device. Risk management is ensured via a risk analysis, which is used to identify potential hazards." | |
| Compliance with Standards | Designed and manufactured in accordance with ISO 13485, ISO 14971, ANSI/AAMI SW68:2001, 21 CFR § 820. |
Note: The document explicitly states, "The submission contains the results of a hazard analysis and the 'Level of Concern' for potential hazards has been classified as 'Moderate'." This indicates risk management was performed and reviewed as part of establishing safety.
2. Sample Size Used for the Test Set and Data Provenance
The provided text does not specify a sample size for a test set (e.g., number of images, number of patients). It also does not mention the data provenance (e.g., country of origin, retrospective or prospective).
For a 510(k) submission, particularly one involving image processing for comparison only and not primary diagnosis, the "test set" might not be a clinical image dataset for performance metrics like sensitivity/specificity. Instead, testing might focus on technical validation, such as image quality assessment (e.g., preservation of detail, compression artifacts, adherence to DICOM standards) and functional testing against specified requirements. The document mentions "The performance of the software is also tested in accordance with Hologic's SOPs and testing procedures to demonstrate adequate performance," which implies internal validation.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
This information is not provided in the given text. Since the device is for "comparison purposes only" and "cannot be used for primary diagnosis," a ground truth established by experts for diagnostic performance (e.g., disease presence/absence) would likely not be the primary focus of the performance testing presented in this summary. If image quality was assessed by experts, their qualifications are not mentioned.
4. Adjudication Method for the Test Set
This information is not provided in the given text.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
An MRMC study is not mentioned in the provided text. Given the device's intended use ("for comparison purposes only" and "cannot be used for primary diagnosis"), a comparative effectiveness study showing human readers' improvement with AI assistance would not be required or relevant for this specific 510(k) pathway.
6. Standalone (Algorithm Only) Performance Study
The text does not explicitly describe a standalone performance study in terms of specific clinical metrics like sensitivity or specificity. The "performance" mentioned likely refers to technical performance, such as:
- Ability to process digitized screen-film mammograms.
- Production of lossy-compressed DICOM images.
- Resemblance to digital mammography images (qualitative assessment).
The submission implies internal testing ("The performance of the software is also tested in accordance with Hologic's SOPs and testing procedures to demonstrate adequate performance"), which would include standalone functional and technical validation.
7. Type of Ground Truth Used
The text does not specify the type of ground truth used. For this type of device, ground truth would likely relate to objective measurements of image fidelity to the original film, proper DICOM formatting, and the visual similarity ("more closely resemble digital mammography images") which could be a qualitative assessment by an internal team rather than a clinical ground truth like pathology or outcomes data.
8. Sample Size for the Training Set
The text does not provide any information regarding a training set sample size. Given the stated function ("process digitized screen-film mammograms to produce lossy-compressed DICOM images that more closely resemble digital mammography images"), it's possible the algorithms are based on image processing techniques that don't rely on a "training set" in the machine learning sense (i.e., for classification or detection). Instead, they might use fixed, rule-based, or adaptive algorithms for image manipulation. If machine learning was involved for the "resemblance" aspect, the training data is not discussed.
9. How the Ground Truth for the Training Set Was Established
This information is not provided in the given text, as no training set or its ground truth is mentioned.
§ 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).