Search Results

The Spectral CT Verida Family is a Computed Tomography X-Ray System intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data taken at different angles and planes. This device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.

The Spectral CT Verida Family system acquires one CT dataset – composed of data from a higher-energy detected x-ray spectrum and a lower- energy detected x-ray spectrum. The two spectra may be used to analyze the differences in the energy dependence of the attenuation coefficient of different materials. This allows for the generation of images at energies selected from the available spectrum and to provide information about the chemical composition of the body materials and/or contrast agents. Additionally, materials analysis provides for the quantification and graphical display of attenuation, material density, and effective atomic number.

This information may be used by a trained healthcare professional as a diagnostic tool for the visualization and analysis of anatomical and pathological structures in patients of all ages, and to be used for diagnostic imaging in radiology, interventional radiology, and cardiology and in oncology as part of treatment preparation and radiation therapy planning. The Extended field of view images and respiratory correlated scanning (4DCT) are for treatment preparation and radiation therapy planning/simulation usage only. This device is indicated for head, whole body, cardiac and vascular X-ray Computed Tomography applications in patients of all ages.

The system is also intended to be used for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer*. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by either a governmental body or professional medical society.

The system incorporates both conventional iterative reconstruction (IR) and artificial intelligence (AI)-based reconstruction functionality. Spectral Precise Image (SPI) is an AI-based deep learning reconstruction feature intended to optimize image quality by reducing noise and enhancing image appearance in Head, Whole Body, Cardiac, and Vascular X-ray Computed Tomography applications. Clinical performance evaluation of the SPI feature was conducted in adult patients (≥22 years of age). The use of SPI in pediatric populations has not been clinically validated.

AI-based reconstruction outputs are intended to provide supplemental data for clinical interpretation and do not replace professional clinical judgment. Image quality and reconstruction performance may be subject to variability based on patient anatomy, body habitus, physiological motion, and technical acquisition conditions. It is the responsibility of the clinician to select the reconstruction method appropriate for the specific clinical task and patient population.

*Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl. J Med 2011; 365:395-409) and subsequent literature, for further information.

The Spectral CT Verida Family is a Computed Tomography X-Ray System intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data taken at different angles and planes. This device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.

The Spectral CT Verida Family system acquires one CT dataset – composed of data from a higher energy detected X-ray spectrum and a lower- energy detected X-ray spectrum. The two spectra may be used to analyze the differences in the energy dependence of the attenuation coefficient of different materials. This allows for the generation of images at energies selected from the available spectrum and provides information about the chemical composition of the body materials and/or contrast agents. Additionally, materials analysis provides for the quantification and graphical display of attenuation, material density, and effective atomic number.

The Spectral CT Verida Family system consists of three main components – a scanner system that includes a rotating gantry, a movable patient couch, and an operator console for control and image reconstruction; a Spectral Reconstruction System; and a Spectral CT Viewer. On the gantry, the main active components are the X-ray high voltage (HV) power supply, the X-ray tube, and the detection system.

The fundamental design and characteristics of the main components used in the proposed Spectral CT Verida Family system are identical to the cleared to market primary predicate device, Spectral CT 7500 RT system (K240844).

Acceptance Criteria and Study for Spectral CT Verida Family (K253649)

1. Acceptance Criteria and Reported Device Performance

The core of the clinical performance evaluation focused on the Spectral Precise Image (SPI) feature, an AI-based deep learning reconstruction algorithm. The primary performance criteria revolved around demonstrating non-inferiority of SPI compared to the iDose⁴ reconstruction method in terms of image quality and diagnostic confidence.

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

• Sample Size: 147 scans, distributed as follows:
  • Head: 42 scans
  • Body: 42 scans
  • Cardiac: 42 scans
  • Chest: 21 scans
• Data Provenance: Retrospective, multi-site. The data was "previously acquired, anonymized clinical CT data" from adult patients (>22 years of age).
• Country of Origin: Not explicitly stated, but the study sites, Hospital of the University of Pennsylvania (UPenn) and Albert Einstein College of Medicine/Montefiore Medical Center, are located in the United States.

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

The document states that "U.S. board-certified radiologists/cardiologists, blinded to reconstruction method" were used as readers. The specific number of experts used and their detailed experience (e.g., "10 years of experience") are not explicitly mentioned in the provided text.

4. Adjudication Method for the Test Set

The adjudication method is not explicitly mentioned in the provided text. The document states that images were "presented side-by-side, randomized order," and readers assessed with a "5-point Likert scale for image quality and diagnostic confidence," but it does not describe how discrepancies or consensus among multiple readers were handled if multiple readers were used per case. Given that it mentions "readers," it implies more than one.

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: Yes, an MRMC comparative effectiveness study was conducted. It was a "multi-site, controlled, blinded, non-inferiority clinical investigation." Readers were "blinded to reconstruction method" and assessed images using a 5-point Likert scale.
• Effect Size of Human Reader Improvement with AI: The study demonstrated that SPI (AI-based reconstruction) was non-inferior to iDose⁴ (standard-of-care reference) for image quality and diagnostic confidence. Furthermore, "SPI offers improved image texture, and higher reader agreement, in clinical image reconstruction." While these findings suggest benefits from SPI, the document does not quantify an "effect size" as a specific improvement metric (e.g., mean difference in diagnostic accuracy scores or specific percentages of improvement) of human readers with AI assistance versus without AI assistance. The focus was on non-inferiority and qualitative improvements in image texture and agreement.

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

Yes, a standalone (algorithm only) performance evaluation was done as part of the Summary of Non-Clinical Performance Testing. This involved "bench performance testing" to evaluate image quality and spectral accuracy using phantoms.

• Image Quality Metrics Testing: Evaluated CT number linearity, image noise, uniformity, CNR, spatial resolution (MTF and SSP), low contrast resolution (visual), and image artifacts using Verida system, Gammex ACR, and Catphan phantoms.
• Spectral Accuracy Testing: Evaluated MonoE, VNC, iodine density, Z effective, electron density, uric acid using Gammex 472, Gammex 467, Gammex ACR, and 20cm MECT phantoms.

7. The Type of Ground Truth Used

• For the clinical study (human-in-the-loop): The ground truth was based on expert consensus/reader judgment using a 5-point Likert scale for image quality and diagnostic confidence. The iDose⁴ images served as the "standard-of-care reference" for comparison.
• For the non-clinical standalone study: The ground truth was based on known phantom properties and physical measurements (e.g., expected CT numbers, noise levels, spatial resolution targets, known material compositions for spectral accuracy).

8. The Sample Size for the Training Set

The document does not specify the sample size for the training set used for the Spectral Precise Image (SPI) AI-based deep learning reconstruction. It only describes the test set used for the clinical validation.

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

The document does not describe how the ground truth for the training set was established. It mentions that SPI is an "AI-based deep learning reconstruction feature" and is "derived from the previously cleared Precise Image framework," but it does not provide details about the training data or its annotation process.

Ask a specific question about this device