(100 days)
The AlignRT system is used to position patients at the isocentre of the linear accelerator for radiation therapy procedures. Patient contour data can be extracted and exported from the acquired data for the purpose of treatment planning. AlignRT is used by radiotherapy professionals in appropriate hospital environments. It can be used with all types of radiotherapy patients and can image any visible anatomical region. The system is completely non-invasive and does not require the application of any external markers to the patient.
AlignRT is a video-based three-dimensional (3D) surface imaging system, which is used to image the skin surface of a patient in 3D before and during radiotherapy treatment. The system consists of advanced software, a computer workstation, two 3D camera units, cables, and templates that are used for camera calibration. The system is non-invasive, does not require the use of body markers and produces no irradiation during the imaging process. AlignRT first generates a reference surface of the optimum treatment position determined during treatment simulation. This reference image is generated by either recording the surface of a patient placed in a conventional radiotherapy simulator in which the system is installed or by importing skin contours from CT (X-Ray Computer Tomography) volumetric data generated via third party treatment planning software. Prior to each treatment session the patient's position is imaged and compared to the reference image by the system's surface matching software. Where movement from the reference position is detected the software calculates new co-ordinates to adjust the treatment couch for optimal positioning of the patient. The system is designed to interface directly with certain third party couch control systems. In order to minimise the setup errors that can result from respiratory motion, an option is available to gate the image capture of the system so that all data is acquired at a repeatable point within the breathing cycle such as the end of exhalation. Real-time imaging (1 frame/sec) of the patient is possible during the actual treatment and software verification tools are provided in order to determine any patient movement. Patient contour data may be extracted from surface data acquired by the system. In addition, lung contour data may be estimated by utilising AlignRT 3D surface data and 2D X-ray data acquired from either a conventional simulator or portal imager. These data may be exported for the purpose of treatment planning by radiotherapy professionals.
Based on the provided 510(k) summary (K052682) for the AlignRT system, the following information regarding acceptance criteria and study details can be extracted:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document (K052682) is a 510(k) summary, which focuses on demonstrating substantial equivalence to predicate devices rather than providing a detailed performance study with explicit acceptance criteria and corresponding performance metrics for a novel technology. Therefore, the "acceptance criteria" listed below are inferred from the device's stated purpose and comparison to predicates, and the "reported device performance" is a general statement from the summary. Specific quantitative metrics are not detailed in this document.
| Acceptance Criteria (Inferred from Device Purpose and Comparison) | Reported Device Performance (General Statement in Summary) |
|---|---|
| Ability to image the skin surface of a patient in 3D before and during radiotherapy treatment. | "AlignRT is a video-based three-dimensional (3D) surface imaging system, which is used to image the skin surface of a patient in 3D before and during radiotherapy treatment." |
| Capability to generate a reference surface of the optimum treatment position. | "AlignRT first generates a reference surface of the optimum treatment position determined during treatment simulation." |
| Comparison of patient's current position to the reference image. | "Prior to each treatment session the patient's position is imaged and compared to the reference image by the system's surface matching software." |
| Calculation of new co-ordinates to adjust the treatment couch for optimal patient positioning where movement is detected. | "Where movement from the reference position is detected the software calculates new co-ordinates to adjust the treatment couch for optimal positioning of the patient." |
| Real-time imaging capability during treatment to detect patient movement. | "Real-time imaging (1 frame/sec) of the patient is possible during the actual treatment and software verification tools are provided in order to determine any patient movement." |
| Ability to extract patient contour data. | "Patient contour data may be extracted from surface data acquired by the system." |
| Ability to estimate lung contour data by utilizing 3D surface data and 2D X-ray data. | "In addition, lung contour data may be estimated by utilising AlignRT 3D surface data and 2D X-ray data acquired from either a conventional simulator or portal imager." |
| No new efficacy or safety concerns compared to predicate devices despite technological differences. | "performance data has been submitted to show that AlignRT achieves its intended use and that these technological differences raise no new efficacy or safety concerns." |
2. Sample Size Used for the Test Set and Data Provenance
The 510(k) summary does not explicitly state a sample size for a test set or any details about data provenance (e.g., country of origin, retrospective or prospective data) for a specific clinical study. General "performance data" is mentioned as being submitted, but the specifics are not included in this publicly available summary.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
The 510(k) summary does not provide information regarding the number of experts, their qualifications, or how ground truth was established for any specific test set. The device's function involves comparing to a "reference surface" determined during "treatment simulation" or from "CT volumetric data," which implies clinical input from radiotherapy professionals, but specific details about establishing ground truth for validation are absent.
4. Adjudication Method for the Test Set
The 510(k) summary does not describe any adjudication method used for a test set.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
The 510(k) summary makes no mention of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study, nor does it quantify any effect size of human readers improving with or without AI assistance. The AlignRT system is presented as a positioning and monitoring tool for radiotherapy, not an AI-assisted diagnostic or interpretive tool for human readers in the traditional MRMC sense.
6. Standalone (Algorithm Only) Performance Study
The document states that "performance data has been submitted to show that AlignRT achieves its intended use." This implies that a standalone performance evaluation of the system's capabilities (e.g., accuracy of 3D surface imaging, precision of position detection, correlation with actual patient movement) was likely performed and submitted to the FDA. However, the details of such a standalone study, including specific metrics and methodologies, are not present in this summary. The core of the device is its algorithm for surface matching and coordinate calculation.
7. Type of Ground Truth Used
The ground truth for the core function of the AlignRT system is implicitly related to:
- The "optimum treatment position determined during treatment simulation." This would be established by radiotherapy professionals.
- "Skin contours from CT (X-Ray Computer Tomography) volumetric data" which are considered a gold standard for anatomical representation in radiotherapy planning.
- "2D X-ray data acquired from either a conventional simulator or portal imager" when estimating lung contour data.
Therefore, the ground truth leans towards expert consensus (for optimal treatment position) and imaging modalities considered high-fidelity anatomical references (CT, X-ray). Pathology or outcomes data are not mentioned as direct ground truth for this positioning device.
8. Sample Size for the Training Set
The 510(k) summary does not provide any information regarding the sample size of a training set. Given the described functionality (3D surface imaging, matching, coordinate calculation), the system likely relies on image processing algorithms that might be trained or calibrated, but details are not disclosed.
9. How the Ground Truth for the Training Set Was Established
Since no information on a training set is provided, there is correspondingly no information on how its ground truth was established.
§ 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.