(263 days)
Veolity is intended to:
-
display a composite view of 2D cross-sections, and 3D volumes of chest CT images,
-
allow comparison between new and previous acquisitions as well as abnormal thoracic regions of interest, such as pulmonary nodules,
-
provide Computer-Aided Detection ("CAD") findings, which assist radiologists in the detection of solid pulmonary nodules between 4-30 mm in size in CT images with or without intravenous contrast. CAD is intended to be used as an adjunct, alerting the radiologist - after his or her initial reading of the scan - to regions of interest that may have been initially overlooked.
The system can be used with any combination of these features. Enabling is handled via licensing or configuration options.
Veolity is a medical imaging software platform that allows processing, review, and analysis of multi-dimensional digital images.
The system integrates within typical clinical workflow patterns through receiving and transferring medical images over a computer network. The software can be loaded on a standard off-theshelf personal computer (PC). It can operate as a stand-alone workstation or in a distributed server-client configuration across a computer network.
Veolity is intended to support the radiologist in the review and analysis of chest CT data. Automated image registration facilitates the synchronous display and navigation of current and previous CT images for follow-up comparison
The software enables the user to determine quantitative and characterizing information about nodules in the lung in a single study, or over the time course of several thoracic studies. Veolity automatically performs the measurements for segmented nodules, allowing lung nodules and measurements to be displayed. Afterwards nodule segmentation contour lines can be edited by the user manually with automatic recalculation of geometric measurements post-editing. Further, the application provides a range of interactive tools specifically designed for segmentation and volumetric analysis of findings in order to determine growth patterns and compose comparative reviews.
Veolity requires the user to identify a nodule and to determine the type of nodule in order to use the appropriate characterization tools. Additionally, the software provides an optional/licensable CAD package that analyzes the CT images to identify findings with features suggestive of solid pulmonary nodules between 4-30 mm in size. The CAD is not intended as a detection aid for either part-solid or non-solid lung nodules. The CAD is intended to be used as an adjunct, alerting the radiologist – after his or her initial reading of the scan – to regions of interest that may have been initially overlooked.
The provided text describes the MeVis Medical Solutions AG's Veolity device and its 510(k) submission (K201501). However, the document states: "N/A - No clinical testing has been conducted to demonstrate substantial equivalence." This means that detailed acceptance criteria tables, sample sizes for test sets, expert qualifications, etc., as requested in your prompt, are not explicitly provided in the document for a new clinical study.
The submission claims substantial equivalence based on the device being a combination of previously cleared predicate and reference devices. It asserts that the individual functionalities remain technically unchanged. The performance assessment for the CAD system relies on prior panel review results from the initial submission of the predicate device and a re-evaluation with a multi-center dataset designed to be comparable to the predicate device's clinical study.
Therefore, I cannot fully complete all sections of your request with specific details from this document regarding a new study demonstrating the device meets acceptance criteria. I will instead extract the information that is present and highlight the limitations.
Here's a breakdown of the requested information based on the provided text:
1. A table of acceptance criteria and the reported device performance
The document does not provide a specific table of quantitative acceptance criteria for the current submission's performance study. It states that the subject device's CAD system performance "provides equal results in terms of sensitivity and false positive rates compared to the primary predicate device."
It re-evaluated performance "in terms of sensitivity and false positive rate per case" and found it "equivalent to the primary predicate device."
- Acceptance Criteria (Implied): Equivalence in sensitivity and false positive rates per case compared to the primary predicate device (ImageChecker CT CAD Software System K043617).
- Reported Device Performance: Stated as "equivalent" to the primary predicate device's performance, which was based on its own initial submission. No specific numerical values for sensitivity or false positive rates are provided for Veolity.
2. Sample size used for the test set and the data provenance
- Test Set Sample Size: Not explicitly stated for the "re-evaluated" performance study. The text mentions it was conducted with "a multi-center dataset."
- Data Provenance: "modern and multivendor CT data." The document does not specify the country of origin or whether it was retrospective or prospective. Given it's a re-evaluation designed to be comparable to a predicate's clinical study, it's likely retrospective.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not explicitly stated for the "re-evaluated" performance study. The document refers to "panel review results" from the initial submission of the predicate device for its performance assessment. It does not provide details on the number or qualifications of experts for Veolity's re-evaluation.
4. Adjudication method for the test set
Not explicitly stated. Given the reliance on prior predicate studies, this information would likely be found in the predicate's 510(k) submission.
5. 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
- MRMC Study: The document does not describe an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated for this submission.
- Effect Size: Not applicable, as no such study is described. The CAD's indication for use states it is "intended to be used as an adjunct, alerting the radiologist - after his or her initial reading of the scan - to regions of interest that may have been initially overlooked." This implies an assistive role, but no data on human-AI collaboration improvement is presented here.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, a standalone performance evaluation of the CAD algorithm itself was done. The document states: "the subject device's CAD system performance provides equal results... in terms of sensitivity and false positive rates." This implies an algorithm-only evaluation against ground truth.
7. The type of ground truth used
The document does not explicitly state the method for establishing ground truth for the re-evaluated dataset. However, given that it's comparing against "sensitivity and false positive rates" for solid pulmonary nodules, the ground truth would typically be established by expert consensus (e.g., highly experienced radiologists, often with follow-up or pathology correlation if available within the original study design of the predicate).
For the predicate device, it mentions "panel review results," which strongly suggests expert consensus.
8. The sample size for the training set
The document does not provide any information about the training set used for the Veolity CAD algorithm. It only discusses performance evaluations.
9. How the ground truth for the training set was established
Not provided in the 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).