Search Results

VeriSuite is an image processing software for verification of the patient position of a correction vector for the treatment of tumors during a radiation therapy with photons, electrons (from a linear accelerator) or particles (protons).

An authorized person must evaluate the correctness of the calculation and approve the result for further usage. The system shall only be used after correct installation in appropriate treatment rooms by trained personnel. Legal regulations especially regulation for the operation of X-ray devices must be regarded.

VeriSuite must not be used for diagnostic purposes.

VeriSuite® is an image processing system for verification and correction of the patient position during a radiation therapy treatment. The verification or correction is performed by a comparison of the current patient treatment position with a CT series of the patient and information from the radiation therapy planning. The correction can also be based on fiducial, radio-opaque markers that are implanted in the patient.

With the fluoroscopy extension it is possible to observe the position of the patient and the treatment area during the treatment. Mainly the movements of the patient caused by breathing are in the focus. This information can be used to interrupt the treatment by the user.

With the 3D3D extension it is possible to compare two CT volumes with each other. The positioning volume is received from the TRCS (i.e. from a second CT device located in the treatment room.)

VeriSuite® is a system of devices consisting of the VeriSuite® software and a number of hardware devices.

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not explicitly state a specific numerical sample size for the test set used in the non-clinical performance data section. It mentions:

• "Test have been performed with medical phantoms."
• "Simulated patient data was used to perform the workflow and verify precision and robustness of the algorithm."

Data Provenance:

• Medical Phantoms: These are physical models designed to mimic human anatomy for testing purposes. Their provenance is typically laboratory-based.
• Simulated Patient Data: The source of this simulated data is not specified (e.g., whether it's derived from previous real patient scans, purely synthetic, etc.).
• "Feedback from VeriSuite® users in the EU (CE marked)" indicates some real-world input, but this feedback is used to improve the algorithm and obtain the reported improved robustness and precision, rather than being part of a formal, quantifiable test set for acceptance criteria.

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

The document does not specify the number of experts used or their qualifications for establishing ground truth during the non-clinical testing. The "ground truth" seems to be established by the "expected parameters" for precision and robustness, which would typically be defined by engineering specifications and potentially clinical guidance from experts, but this is not detailed.

4. Adjudication Method for the Test Set

The document does not describe an adjudication method for the test set. The validation appears to be based on the algorithm's performance against predefined "expected parameters" and by expert assessment in the form of "feedback from VeriSuite® users in the EU."

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size

No multi-reader multi-case (MRMC) comparative effectiveness study is mentioned for evaluating human reader improvement with or without AI assistance. The study focuses on the standalone performance of the 3D3D extension.

6. If a Standalone (i.e., Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, a standalone performance evaluation was done. The "Non-clinical Performance Data" section describes tests performed with "medical phantoms" and "simulated patient data" to verify the precision and robustness of the algorithm, and the "calculation of a correction vector." This focuses on the algorithm's capabilities without detailing human interaction beyond the assessment of usability.

7. The Type of Ground Truth Used

The ground truth for the non-clinical tests appears to be:

• Phantom-based measurements: For precision and robustness, the known characteristics of the medical phantoms would serve as ground truth.
• Simulated patient data with known outcomes: For simulated data, the ground truth would be the pre-defined correct patient positions and correction vectors.
• "Expected parameters": This implies a pre-defined set of correctness values or ranges for the algorithm's output.

8. The Sample Size for the Training Set

The document does not provide information on the sample size used for the training set of the VeriSuite 3D3D matching module.

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

The document does not explicitly describe how the ground truth for any potential training set was established. The focus of the provided text is on verification and validation of the device's performance after its development, rather than the details of its developmental training.

Ask a specific question about this device