(245 days)
syngo.CT Skull Unfolding provides curved MIP images of skull and brain surface for visual assessment by a radiologist.
syngo.CT Skull Unfolding is image analysis software for CT volume data sets which has been continuously acquired with computed tomography (CT) imaging systems. syngo.CT Skull Unfolding provides advanced visualization of the skull and brain surface for easy manual identification, marking and reporting of pathologies such as skull fractures and hematomas. It receives images from a hosting application and returns DICOM images to a hosting application, which can display the results within its user interface. The device does not mark, highlight, or direct users' attention to a specific location in the original image.
The provided text does NOT include acceptance criteria or a study that proves the device meets specific acceptance criteria in the manner typically found for a diagnostic algorithm. The document focuses on establishing substantial equivalence to a predicate device, which is a different regulatory pathway.
Here's a breakdown of why the requested information is largely absent and what details are available:
1. Table of Acceptance Criteria and Reported Device Performance:
- Acceptance Criteria: Not explicitly stated for performance metrics. The document instead focuses on "conformance with special controls for medical devices containing software" and that "all the software specifications have met the acceptance criteria." These are very high-level and refer to internal development and testing, not specific quantitative performance targets like sensitivity, specificity, or accuracy for a diagnostic task.
- Reported Device Performance: No specific quantitative performance metrics (e.g., accuracy, sensitivity, specificity, F1-score) are reported for the syngo.CT Skull Unfolding device. The document generally states that "The results of these tests demonstrate that the subject device performs as intended" and that "The result of all conducted testing was found acceptable to support the claim of substantial equivalence."
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size for Test Set: Not specified. The document mentions "non-clinical tests (integration and functional) were conducted," but does not provide details on the number of cases or images used for these tests.
- Data Provenance: Not specified. There is no information about the country of origin of the data or whether it was retrospective or prospective.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:
- Number of Experts: Not specified.
- Qualifications of Experts: Not specified.
- Ground Truth Establishment: Not specified. The device "provides curved MIP images of skull and brain surface for visual assessment by a radiologist" but does not perform an automated diagnostic task itself from which ground truth would typically be established.
4. Adjudication Method for the Test Set:
- Not applicable/Not specified. Since no independent expert review is mentioned for diagnostic performance, an adjudication method is not discussed.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done:
- No, an MRMC comparative effectiveness study was NOT done. The document describes the device as a "visualization method" and advanced visualization software, implying it's a tool to assist radiologists, not an AI intended to directly improve diagnostic accuracy that would typically be evaluated in an MRMC study. The comparison is mainly focused on technological characteristics with predicate and reference devices.
- Effect Size of Human Readers Improve with AI vs. Without AI Assistance: Not applicable, as no such study was conducted or reported.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done:
- No, a standalone performance study in a diagnostic sense was NOT done. The device's purpose is to "provide curved MIP images... for visual assessment by a radiologist." It is an assistive visualization tool, not an autonomous diagnostic algorithm.
7. The Type of Ground Truth Used:
- Not applicable/Not specified. The document focuses on the functionality of the software (e.g., "unfolded view of the skull," "curved maximum intensity projection (MIP)"). Ground truth, in the context of diagnostic accuracy, is not discussed because the device is a visualization tool rather than a diagnostic algorithm generating its own interpretations.
8. The Sample Size for the Training Set:
- Not specified. Given that the document emphasizes "same testing methods with same workflows as used to clear the predicate device" and that the device is primarily a visualization tool rather than a deep learning model for classification or detection, a "training set" in the common AI sense is not applicable or not explicitly mentioned. Bone segmentation uses "Thresholding based skull segmentation," which is a rule-based or traditional image processing technique, not typically requiring a large training dataset.
9. How the Ground Truth for the Training Set Was Established:
- Not applicable/Not specified, as no training set is mentioned in the context of complex AI models requiring established ground truth.
In summary, the provided FDA 510(k) clearance document for syngo.CT Skull Unfolding (K203411) focuses on establishing substantial equivalence based on technological characteristics and functional testing. It does not provide the kind of detailed performance metrics, acceptance criteria, or study design typically associated with the rigorous evaluation of diagnostic AI algorithms (e.g., sensitivity, specificity, reader studies, ground truth establishment). The device is described as an "image analysis software" that "provides advanced visualization of the skull and brain surface for easy manual identification, marking and reporting of pathologies," indicating it's a tool for radiologists, not a standalone diagnostic AI.
§ 892.1750 Computed tomography x-ray system.
(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.