Search Results

This computed tomography system is intended to generate and process cross-sectional images of patients by computer reconstruction of x-ray transmission data. The images delivered by the system can be used by a trained physician as an aid in diagnosis.

The images delivered by the system can be used by trained staff as an aid in diagnosis, treatment preparation and radiation therapy planning.

This CT system can be used for low dose lung cancer screening in high risk populations.*

*As defined by professional medical societies. 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 Siemens SOMATOM Confidence is a Computed Tomography X- ray System which features one continuously rotating tube-detector system and functions according to the fan beam principle. The SOMATOM Confidence produces CT images in DICOM format, which can be used by trained staff for post-processing applications commercially distributed by Siemens and other vendors as an aid in diagnosis, treatment preparation and therapy planning support (including, but not limited to, Brachytherapy, Particle including Proton Therapy, External Beam Radiation Therapy, Surgery). The computer system delivered with the CT scanner is able to run the post processing applications optionally.

The platform software for the SOMATOM Confidence, syngo CT VA62A (SOMARIS/7 VA62A), is a command-based program used for patient management, data management, X-ray scan control, image reconstruction, and image archive/evaluation. The SOMATOM Confidence will support the following modifications in comparison to the predicate devices:

• 1. New Marketing Name: SOMATOM Confidence (SOMATOM Confidence® RT Pro)
• 2. Modified Indication for Use Statement
• 3. New/Modified Hardware
  • Touch Panels ●
  • New Gantry and Patient Table Covers .
  • Stellar RT Detector .
• 4. Software version SOMARIS/7 VA62A
  • Data Exchange with external SW Client (Teamplay) ●
  • IT Hardening .
  • DirectDensity™ .
• 5. Update 510(k) Information

The SOMATOM Confidence will be offered in 20 and 64 slice configurations.

The provided text does not contain detailed acceptance criteria and the comprehensive study results to populate all the requested fields for a specific AI device. The document is a 510(k) summary for a CT scanner (SOMATOM Confidence® RT Pro), which is a general imaging device, not an AI-powered diagnostic tool with specific performance metrics like sensitivity, specificity, or AUC related to an AI algorithm.

However, I can extract the information related to the device itself and its general performance verification, as well as the reference to a clinical trial relevant to one of its indications for use (low-dose lung cancer screening).

Here's a breakdown of what can and cannot be answered from the provided text:

Information directly available or inferable about the SOMATOM Confidence® RT Pro (CT System):

• 1. A table of acceptance criteria and the reported device performance: The document states that "all of the software specifications have met the acceptance criteria" and that "the testing results support that the requirement specifications have met the acceptance criteria" for the DirectDensity™ feature. However, the specific acceptance criteria values (e.g., specific signal-to-noise ratios, spatial resolution, CT number accuracy) and their corresponding reported performance values for the device itself (the CT scanner) are not presented in a table format within this summary. It generally assures conformity to performance standards like ISO 14791, NEMA XR-29, IEC 61223-2-6, IEC 61223-3-5, IEC 62304, NEMA XR-25, and DICOM 3.1-3.20. For DirectDensity™, it mentions "image values proportional to relative electron density and perform as expected," but no quantitative criteria or performance figures are given.
• 6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The document describes the CT system's performance, including features like DirectDensity™. This is essentially a "standalone" evaluation of the imaging device's capabilities. There is no mention of an AI diagnostic algorithm being tested in a standalone capacity within this text.
• 7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): For the testing of the CT system and its features such as DirectDensity™, phantom tests (using a Gammex 467 Tissue Characterization Phantom) and simulations were used.
• 8. The sample size for the training set: Not applicable for the CT scanner hardware/software itself. If this were an AI algorithm submission, this would be crucial.
• 9. How the ground truth for the training set was established: Not applicable for the CT scanner hardware/software itself.

Information related to the referenced "National Lung Screening Trial (NLST)" for the low-dose lung cancer screening indication:

• 2. Sample size used for the test set and the data provenance:
  • Sample Size: The NLST was "a randomized trial of screening with the use of low-dose CT compared to chest radiography." While the exact number of participants is not given in this document, the referenced paper (N Engl J Med 2011; 365:395-409) is the primary source for this information. It is a prospective trial.
  • Data Provenance: The trial was sponsored by the National Cancer Institute, implying multi-center US-based data.
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not specified in this document, but would be detailed in the NLST publication. The interpretation task for CT in NLST was "to detect lung nodules of 4mm diameter or greater."
• 4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not specified in this document for the NLST.
• 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: The NLST was a comparative effectiveness study comparing low-dose CT to chest radiography for lung cancer screening outcomes (mortality reduction). It was not specifically an MRMC study with AI assistance. It evaluated human readers interpreting images from two different modalities. The effect size reported by NLST was that screening with low-dose CT reduced lung cancer mortality compared to chest radiography. This document does not quantify that effect size but refers to the publication.

Summary Table:

Additional Requested Information:

• 2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
  • For CT System Testing: Not explicitly specified (phantom tests, simulations).
  • For NLST: Not explicitly stated in this document, but implied to be a large, prospective, multi-center US trial (National Cancer Institute sponsorship).
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
  • For CT System Testing: Not applicable (phantom/simulations).
  • For NLST: Not specified in this document.
• 4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
  • For CT System Testing: Not applicable.
  • For NLST: Not specified in this document.
• 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
  • Not done with AI assistance. The NLST was a comparative effectiveness trial of two screening modalities (low-dose CT vs. chest radiography) interpreted by human readers. It did not involve AI assistance.
• 6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
  • Yes, for the CT system itself. The performance of the SOMATOM Confidence CT system and its features (like DirectDensity™) were evaluated. This is not an AI diagnostic algorithm, but the imaging device's performance.
• 7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
  • For CT System Testing: Phantom tests (Gammex 467 Tissue Characterization Phantom) and simulations.
  • For NLST: Lung cancer mortality (outcomes data) was the primary endpoint. The "interpretation task with CT for this study was to detect lung nodules of 4mm diameter or greater" which would have likely been verified by pathology/follow-up.
• 8. The sample size for the training set
  • Not applicable; this is for a CT system, not an AI algorithm requiring a training set in the typical sense.
• 9. How the ground truth for the training set was established
  • Not applicable.

Ask a specific question about this device

The SpotLight CT Computed Tomography X-ray is intended to produce cross-sectional images of the body by computer reconstruction of X-ray transmission data taken at different angles. The system has the capability to image whole organs, including the heart, in a single rotation. The system may acquire data using Axial, Cine and Cardiac CT scan techniques from patients of all ages. These images may be obtained either with or without contrast. This device may include signal analysis and display equipment, patient and equipment supports, components and accessories.

This device may include data and image processing to produce images in a variety of trans-axial and reformatted planes.

The system is indicated for X-ray Computed Tomography imaging of organs that fit in a 25cm field of view, including cardiac and vascular CT imaging. The device output is useful for diagnosis of disease or abnormality and for planning of therapy procedures.

The SpotLight CT is a third generation rotate-rotate CT scanner, designed and built based on technologies and principles of operation of the predicate device and other legally marketed CT scanners. The SpotLight CT is a multi-slice (192 detector rows), dual tube CT scanner consisting of a gantry, patient table, operator console, power distribution unit (PDU) and interconnecting cables. The system includes image acquisition hardware, image acquisition and reconstruction software for operator interface and image handling.

The provided document describes the Arineta Ltd. SpotLight CT device and its substantial equivalence to a predicate device. Here's a breakdown of the acceptance criteria and the study details:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in a tabular format with corresponding "reported device performance." Instead, it describes various performance specifications and how the device performed against them. I've re-framed the reported performance metrics as if they were acceptance criteria.

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

• Test Set (Clinical Testing): 38 subjects
• Data Provenance: Not explicitly stated, but the study was conducted at "one site," and the readers were "US certified." This suggests the data was collected in the US.
• Retrospective or Prospective: The clinical testing describes "data were collected," which could mean either. However, the phrase "The study protocol was designed to test the scanner across different patient populations, clinical scenarios and scan techniques" implies a prospective study design for collecting new data specifically for this evaluation.

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

• Number of Experts: Four (4)
• Qualifications: "US certified readers who are qualified radiologists or cardiologists." Specific years of experience are not mentioned.

4. Adjudication Method for the Test Set

The document states, "The images were evaluated and rated by four US certified readers." It does not specify an adjudication method like 2+1 or 3+1 for resolving discrepancies. It implies independent evaluation by each reader.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Was an MRMC study done? No, a multi-reader multi-case (MRMC) comparative effectiveness study (comparing human readers with and without AI assistance) was not done. The clinical testing focused on evaluating the device's diagnostic image quality for standalone performance.
• Effect size of human readers with AI vs without AI assistance: Not applicable, as no such study was conducted or reported.

6. Standalone (Algorithm Only) Performance

• Was a standalone study done? Yes, the described "Non-clinical Performance Testing" and "Clinical Testing" primarily focus on the standalone performance of the SpotLight CT system. The image quality, temporal resolution, dose performance, and diagnostic quality evaluations are all measures of the device's inherent capabilities without human intervention during the image generation or initial analysis phase. The "clinical diagnostic value and image quality" evaluated by the readers are also assessing the output of the device itself.

7. Type of Ground Truth Used

• Non-clinical/Phantom Testing: The ground truth for these tests would be objective physical measurements and known parameters of the phantoms used to evaluate image quality metrics (e.g., spatial resolution targets, known low contrast objects, CT number uniformity).
• Animal Testing: The "diagnostic quality" evaluation in animal models likely used established veterinary diagnostic criteria and potentially post-mortem examination or other correlative imaging as ground truth.
• Clinical Testing: The "clinical diagnostic value and image quality" in human subjects were evaluated by "qualified radiologists or cardiologists" against established clinical diagnostic criteria. While not explicitly stated as "expert consensus ground truth," the assessment by multiple, qualified experts serves as the de-facto ground truth for evaluating diagnostic utility. It does not mention pathology or long-term outcomes data for ground truth.

8. Sample Size for the Training Set

The document does not provide any information about a training set since this is a hardware device (CT scanner) with associated imaging software, not typically an AI/ML algorithm that requires a distinct "training set" in the common sense. The image reconstruction algorithm is described as "Stereo CT reconstruction algorithm based on common algorithms used in single source scanners that are modified to combine the data acquired from the two sources." This implies an engineered algorithm, not one trained on a dataset.

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

Not applicable, as there is no mention of an AI/ML algorithm requiring a training set in the document. The device uses an engineered image reconstruction algorithm.

Ask a specific question about this device