(147 days)
The system is intended for use in radiation therapy clinics together with diagnostic or treatment equipment and provides:
- accurate and reproducible patient positioning. .
- patient motion supervision with an audible and/or visual alarm whenever . the patient motion during treatment is outside of the specified tolerance values, while still allowing for normal breathing motion without triggering the alarm.
- a respiratory signal to be supplied to diagnostic imaging equipment . (primarily CTs) for prospectively and retrospectively (aka 4DCT) gated imaging and reconstruction.
The system cannot directly determine the location of the intended treatment target, since only the patient external surface is detected. The actual target position must therefore, whenever deemed necessary by qualified personnel, be verified using other systems such as CBCT or EPID.
The Sentinel system is intended for use in radiation therapy clinics to accurately position patients in a reproducible way, prior to treatment and to monitor the patient continuously during treatment. The system provides information about a patient's position and the adjustments required in order to position the patient as close as possible to a reference setup. During monitoring, the system reports deviations in the patient's position during treatment.
The system shall only be used by hospital personnel, qualified to work in radiation therapy or diagnostics departments.
The Sentinel platform is based on advanced laser technology with multipurpose software modules covering different tasks in the treatment procedure. The c4D multi-application software supports all modes of operation in one integrated package. The software is user friendly and requires a minimum of user interaction in the daily clinical workflow, while providing the advanced user with sophisticated data management, analysis and reporting functionalities. The software is designed to integrate with existing systems at the clinic, such as CT, linacs and R&V systems, and with motorized couch tops.
The Sentinel system does not require any markers to be placed on the patient or the couch, and doesn't subject the patient to any additional radiation. This also means that the personnel can stay in the treatment room during the whole set up procedure.
Sentinel includes three application modules, cPosition for fast and accuracy patient positioning, cMotion for motion detection during the treatment delivery procedure and cRespiration for respiratory gating diagnostic CT imaging, so called 4D CT studies. Patient positioning before the actual treatment begins, together with subsequent motion detection, ensures that the patient's position is correct both before and during the whole treatment delivery.
The Sentinel hardware consists of a single scanner unit containing the laser and camera, mounted in the ceiling in front of the gantry. The scanner is connected to the PC running the c4D software.
During patient surface acquisition, a laser line is swept along the patient while the camera records a number of images. From the data acquired, a complete 3D surface of the patient can be reconstructed using laser line triangulation. For patient positioning, the acquired surface is captured in a few seconds and can contain several hundred contours. For motion detection the number of contours are typically lowered so that the desired frame rate is achieved. The system is capable of acquiring more than 50 contours per second.
The provided text does not contain detailed information about the acceptance criteria and a specific study that definitively proves the device meets those criteria in the format requested.
The document is a 510(k) Summary for the Sentinel device, primarily focused on demonstrating substantial equivalence to a predicate device. It briefly mentions "Verification and validation has been carried out according to the C-RAD quality management system" and refers to a "V&V report," but the details of this report, including specific acceptance criteria and study results, are not provided in this summary.
It does state: "For the functionality of sending data to the CT for gated imaging and/or reconstruction, non-clinical (phantom) tests have been performed in collaboration with three hospitals in Europe: Uppsala (Sweden), Malmö (Sweden), and Lisbon (Portugal)." However, the details of these phantom tests (e.g., specific metrics, acceptance thresholds, sample sizes, a table comparing expected vs. observed performance) are not included.
Therefore, I cannot directly extract the full requested information from the provided text.
Here's a breakdown of what can be inferred or what is missing based on the prompt's requirements:
1. A table of acceptance criteria and the reported device performance
- Acceptance Criteria: Not explicitly stated in a quantifiable, tabular format. The general intent is that the device provides "accurate and reproducible patient positioning" and "patient motion supervision with an audible and/or visual alarm whenever the patient motion during treatment is outside of the specified tolerance values, while still allowing for normal breathing motion without triggering the alarm" and provides "a respiratory signal to be supplied to diagnostic imaging equipment (primarily CTs) for prospectively and retrospectively (aka 4DCT) gated imaging and reconstruction." Specific numerical thresholds for accuracy, reproducibility, or alarm triggers are not provided.
- Reported Device Performance: Not presented in a quantifiable, tabular format. The document states that "non-clinical (phantom) tests have been performed" and concludes that "the non clinical tests demonstrates that the device is safe, as effective, and performs as well as the legally marketed device Sentinel (K082582)." No specific performance metrics or results from these tests are given.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Sample Size (Test Set): Not specified. The "non-clinical (phantom) tests" were performed, implying inanimate objects were used, not human patients. The number of phantom tests or data points is not mentioned.
- Data Provenance: "non-clinical (phantom) tests have been performed in collaboration with three hospitals in Europe: Uppsala (Sweden), Malmö (Sweden), and Lisbon (Portugal)." This indicates a prospective testing approach on phantoms.
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)
- Not applicable as the tests were "non-clinical (phantom) tests." Ground truth for phantom tests would typically involve precisely known physical properties or measurements rather than expert human interpretation of medical images.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not applicable/Not mentioned. Given it was non-clinical phantom testing, adjudication methods for human interpretation of medical data are not relevant.
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
- No MRMC comparative effectiveness study was done. This device is a positioning and monitoring system, not an AI-assisted diagnostic tool that requires human reader improvement studies. The document focuses on the device's ability to position and monitor, not interpret.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- The non-clinical phantom tests likely represent a standalone performance evaluation of the system's accuracy and functionality in controlling and monitoring without direct human intervention in the positioning process itself (though humans would set up the tests). The document doesn't explicitly describe these tests as "standalone" in the context of an AI-only performance evaluation, but rather as demonstrating the device's technical capabilities.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- For the non-clinical phantom tests, the ground truth would inherently be based on the known, precisely engineered properties of the phantoms and/or reference measurements established through highly accurate measurement tools. It's not expert consensus, pathology, or outcomes data.
8. The sample size for the training set
- Not applicable/Not mentioned. The document describes the system as "based on advanced laser technology with multipurpose software modules." It does not indicate the use of a machine learning model that would require a "training set" in the conventional sense. The software functions based on "advanced surface registration algorithms" and laser line triangulation.
9. How the ground truth for the training set was established
- Not applicable, as no training set for a machine learning model is indicated.
§ 892.5050 Medical charged-particle radiation therapy system.
(a)
Identification. A medical charged-particle radiation therapy system is a device that produces by acceleration high energy charged particles (e.g., electrons and protons) intended for use in radiation therapy. This generic type of device may include signal analysis and display equipment, patient and equipment supports, treatment planning computer programs, component parts, and accessories.(b)
Classification. Class II. When intended for use as a quality control system, the film dosimetry system (film scanning system) included as an accessory to the device described in paragraph (a) of this section, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.