Search Results

The Hologic SecurView DX is intended for selection, display, manipulation, filming and media interchange of multi-modality images from a variety of different modality systems. It also interfaces to various image storage and printing devices using DICOM or similar interface standards.

The device used with FDA cleared monitors may be used by a trained physician for display, manipulation and interpretation of lossless compressed or non-compressed mammographic images for screening and diagnostic mammography, as well as any other DICOM multi-modality image.

The SecurView DX is typically used by trained professionals, including, but not limited to physicians, radiologists, nurses, medical technicians and assistants.

The Hologic SecurView DX is mainly a software product. It is used for visualization and manipulation of digital radiology images. The SecurView DX is a multi-modality review workstation software focused on mammographic applications. The software can drive high-resolution displays (FDA cleared for Mammography), a PC mouse, a keyboard, optional lower resolution monitors and dedicated workflow keypad.

The software accepts standard or multi-frame mammography images that have been created according to the "FOR PRESENTATION" specification of the DICOM Standard with no compression or using lossless compression. Image processing is external to the SecurView DX software.

The software accepts standard or multi-frame multimodality images of US, MR, DR, CR, SC, CT, PET, and other DICOM formats for display and manipulation on high resolution displays (FDA cleared for mammography) or on other lower resolution color displays in 2-D or 3-D view.

The SecurView DX software can be used in a single or in a multi-workstation configuration.

The provided 510(k) summary for SecurView DX (K103385) describes a software product that is substantially equivalent to its predicate device (K062107). This means the primary "study" proving its acceptance involves demonstrating that the modified device behaves essentially the same as the previously cleared device, with minor changes that do not raise new questions of safety or effectiveness.

Therefore, the documentation does not contain information about a traditional clinical study with acceptance criteria and reported device performance metrics in the way one might expect for a novel device or AI algorithm with specific performance claims. Instead, the acceptance is based on demonstrating substantial equivalence through a comparison of features and by verifying that the modified software continues to function as intended.

Below is an attempt to structure the requested information based on the provided document, highlighting what is present and what is absent due to the nature of a substantial equivalence submission for a software update.

Acceptance Criteria and Device Performance for SecurView DX (K103385)

Given that this is a 510(k) submission for substantial equivalence of a software update (SecurView DX, K103385) to a predicate device (SecurView DX, K062107), the "acceptance criteria" and "device performance" are primarily demonstrated through comparison to the predicate device and verification that the modified software performs its intended functions without introducing new safety or effectiveness concerns. There isn't a separate, quantifiable performance outcome defined with specific thresholds for sensitivity, specificity, etc., as would be the case for a device with a quantifiable diagnostic claim.

The primary acceptance criteria for this submission are that the modified device is substantially equivalent to the predicate device in terms of intended use, indications for use, and conformance to relevant standards, and that the modifications do not introduce new safety or effectiveness issues.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size for Test Set: Not applicable or not specified in the document. This submission relies on demonstrating substantial equivalence through comparison to the predicate and internal verification/validation activities of the software changes. There is no mention of a "test set" in the context of clinical images or patient data for performance evaluation. The "bench testing designed to simulate clinical factors" implies internal testing, not a formal clinical trial with a defined patient sample size.
• Data Provenance: Not applicable or not specified.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

• Not applicable. This type of information is not typically part of a substantial equivalence submission for a software update of this nature, as there isn't a "ground truth" establishment in the context of a diagnostic performance study.

4. Adjudication Method for the Test Set

• Not applicable. There is no mention of a formal test set requiring adjudication in the context of a clinical performance study.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and 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 SecurView DX is a viewing workstation and does not incorporate AI in the sense of a diagnostic algorithm to which human readers would be compared or assisted by for specific diagnostic tasks with an effect size measurement. The mention of "AIE Region of Interest Image Enhancement for Digital Mammography software, cleared as K062059" refers to an external, separate medical device whose output SecurView DX can display, not an AI component integrated into SecurView DX itself for diagnostic assistance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

• Not applicable. The SecurView DX is a display and manipulation software, not a standalone diagnostic algorithm.

7. The Type of Ground Truth Used

• Not applicable. Ground truth, in the context of diagnostic performance, is not discussed as there is no diagnostic performance study described for this submission. The "ground truth" for the software's functionality is its adherence to specifications and its ability to correctly display and manipulate medical images, similar to the predicate device.

8. The Sample Size for the Training Set

• Not applicable. This device is not an AI algorithm that requires a training set of images.

9. How the Ground Truth for the Training Set Was Established

• Not applicable, as there is no training set for an AI algorithm.

Ask a specific question about this device