FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

The various materials of an anatomical region of interest have different attenuation coefficients, which depend on the used energy. These differences provide information on the chemical composition of the scanned body materials. syngo.CT Dual Energy combines images acquired with low and high energy spectra to visualize this information. Depending on the region of interest, contrast agents may be used.

The general functionality of the syngo.CT Dual Energy application is as follows:

Monoenergetic
Brain Hemorrhage
Gout Evaluation
Lung Vessels
Heart PBV
Bone Removal
Lung Perfusion
Liver VNC
Monoenergetic Plus
Virtual Unenhanced
Bone Marrow
Hard Plaques
Rho/Z
Kidney Stones*
SPR (Stopping Power Ratio)
SPP (Spectral Post-Processing Format)

The availability of each feature is depending on the Dual Energy scan mode.

*) Kidney Stones is designed to support the visualization of the chemical composition of kidney stones and especially the differentiation between uric acid and non-uric acid stones. For full identification of the kidney stone additional clinical information should be considered such as patient history and urine testing. Only a well-trained radiologist can make the final diagnosis under consideration of all available information. The accuracy of identification is decreased in obese patients.

Device Description

syngo.CT Dual Energy is a post-processing application consisting of several postprocessing application classes that can be used to improve visualization of various energy dependent materials in the human body. This software application is designed to operate on the most recent version syngo.via client/server platform, which supports preprocessing and loading of datasets by syngo.via depending on configurable rules.

These application classes are designed for specific clinical tasks, so that algorithms, additional tool buttons, the use of colored overlay images and image representation (for example MPR or maximum intensity projection) is optimized correspondingly.

AI/ML Overview

The provided text describes the syngo.CT Dual Energy device and its substantial equivalence to predicate devices, but it does not contain a specific table of acceptance criteria with reported device performance for a multi-reader multi-case (MRMC) study or standalone AI performance.

The document primarily focuses on establishing substantial equivalence based on the device's technological characteristics, adherence to standards, and functionality being similar to existing cleared devices. It states that "the post-processing software functionality remains unchanged from the subject device and the predicate devices."

However, based on the information provided, I can infer some aspects and highlight what is missing.

Here's an analysis of the acceptance criteria and study information, addressing each of your points based only on the provided text:

Acceptance Criteria and Device Performance (Inferred/Missing)

The document does not explicitly present a table of quantitative acceptance criteria for clinical performance (e.g., sensitivity, specificity, accuracy for a specific disease detection task) or corresponding reported device performance values. The clearance is based on the device having "the same intended use and similar indication for use" and "technological characteristics such as image visualization, operating platform, and image manipulation are the same as the predicate devices."

The closest the document comes to performance assessment is for the new features (SPR and SPP) and the revalidation of existing features for the combined application:

For SPR (Stopping Power Ratio): "the report shows that the SPR feature can reproduce the theoretical SPR values of the phantom inserts used from Dual Energy CT scans."
For SPP (Spectral Post-Processing Format): "the combination of the SPP-generation process produces equivalent results to the reference method based on functionality available in the predicate device(s). This means also that the information in the SPP-format (including all hidden data) was correctly calculated."
For other application classes (Rho/Z, Kidney Stones, Monoenergetic Plus, Bone Removal, Liver VNC, Hard Plaques): "These studies demonstrate that the subject device performs as well as the predicate device applications that were tested using the same methods."

Since no specific quantitative metrics or a defined Acceptance Criteria table with Reported Performance are present in the provided text, that section cannot be filled out as requested. The basis for acceptance is stated as "The result of all conducted testing was found acceptable to support the claim of substantial equivalence," implying that the performance matched the predicate devices or theoretical expectations for new features.

Detailed Study Information from the Text:

A table of acceptance criteria and the reported device performance:
- Not provided in the document. The document describes functional equivalence and performance "as well as" predicate devices or theoretical values for new features, but no specific quantitative acceptance criteria or reported values are presented in a table.
Sample sizes used for the test set and the data provenance:
- Test Set Sample Size: The document mentions "phantom-based validation" for SPR and SPP, and "phantom bench testing and clinical validation in a retrospective study" for Rho/Z and Kidney Stones. "Retrospective clinically validated studies" were also conducted for Monoenergetic Plus, Bone Removal, Liver VNC, and Hard Plaques.
  - Specific numbers for phantom or clinical cases are NOT provided.
- Data Provenance: "clinical validation in a retrospective study was conducted." The geographic origin of the data (country of origin) is NOT specified. The studies are explicitly stated as retrospective.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: The document states for Kidney Stones: "Only a well-trained radiologist can make the final diagnosis under consideration of all available information." This implies expert involvement for ground truth, but the specific number of experts used for ground truth establishment for any of the test sets is NOT provided.
- Qualifications of Experts: For Kidney Stones, "a well-trained radiologist" is mentioned. Specific experience (e.g., 10 years) is NOT provided.
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- NOT specified.
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:
- No MRMC comparative effectiveness study is explicitly mentioned or described. The device is a "post-processing application" that "improves visualization" and helps in "differentiation." The focus is on the device's performance per se and its equivalence to predicate devices, not on human reader improvement with or without AI assistance. The term "AI" is not used; it's described as software providing "visualization" and "evaluation tools."
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The evaluations for SPR and SPP ("reproduce the theoretical SPR values," "produces equivalent results to the reference method") appear to be standalone algorithm performance tests using phantoms.
- For the other clinical application classes, the description "demonstrate that the subject device performs as well as the predicate device applications" suggests an assessment of the algorithm's output, which would be standalone, but this is not explicitly delineated from a human-in-the-loop study. Given it's a post-processing application, the algorithm's output is what's being evaluated.
The type of ground truth used (expert consensus, pathology, outcomes data, etc):
- Theoretical values/Reference methods: For SPR (theoretical values) and SPP (reference method based on predicate device functionality).
- Clinical validation: For Rho/Z, Kidney Stones, Monoenergetic Plus, Bone Removal, Liver VNC, and Hard Plaques, it states "clinical validation" and "clinically validated studies." For Kidney Stones, "Only a well-trained radiologist can make the final diagnosis," suggesting the ground truth is expert diagnosis/interpretation, potentially combined with "patient history and urine testing." It does not explicitly mention pathology or long-term outcomes data.
The sample size for the training set:
- NOT provided. The document describes testing and validation (test set), but there is no information about a dedicated training set or its size, consistent with this being a 510(k) submission for a post-processing software update/combination, rather than a novel AI/machine learning device. The existing functionalities are described as unchanged.
How the ground truth for the training set was established:
- NOT applicable/provided. As no training set information is present, the method for establishing its ground truth is also not mentioned.

Summary

Regulation Number and Section

§ 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.