(106 days)
TiGRT TPS is a Radiation Therapy Treatment Planning System for radiation dose planning of patients undergoing external beam treatment in the oncology clinic. TiGRT TPS is used to plan radiation treatments with linear accelerators and other similar teletherapy devices with x-ray and/or electron energies from 1 to 25MV, as well as Cobalt-60.
TiGRT TPS is a Radiation Therapy Treatment Planning System for radiation dose planning of patients undergoing external beam treatment in the oncology clinic. TiGRT TPS is used to plan radiation treatments with linear accelerators and other similar teletherapy devices with x-ray and/or electron energies from 1 to 25MV, as well as Cobalt-60.
The provided text describes a 510(k) submission for a Radiation Treatment Planning System called TiGRT TPS. This submission focuses on demonstrating substantial equivalence to a predicate device (WiMRT, K041971) rather than presenting a detailed performance study with specific acceptance criteria and outcome metrics for standalone or human-in-the-loop performance.
Here's an analysis of the requested information based on the provided document:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly state quantitative acceptance criteria for device performance (e.g., accuracy of dose calculation, speed of optimization) or present specific reported device performance metrics against such criteria. Instead, the acceptance is based on demonstrating substantial equivalence to a predicate device. The "performance documentation" listed is about the process of development and risk management, not a direct measurement of the device's functional output against numerical benchmarks.
| Acceptance Criteria (Implied by Substantial Equivalence) | Reported Device Performance |
|---|---|
| Intended Use is the same as the predicate. | TiGRT TPS has the same intended use as WiMRT. |
| Technological Characteristics are similar to the predicate. | TiGRT TPS has similar design, function, application, operating system, networking, application use (Conformal, IMRT, SRS/SRT), dose calculation algorithm (Super-position Convolution), and IMRT optimization algorithm (Genetic Algorithm) as WiMRT. It uses DICOM 3/RT. |
| No new issues of safety or effectiveness are introduced. | "No new issues of safety or effectiveness are introduced by using this device." Also, "No new issues of biocompatibility are raised." |
| Compliance with design and development controls. | Provided documentation including: Level of Concern of TPS (Major), TiGRT TPS Description, Risk Management, Hazard Analysis Report, Product Requirement Specification, Architecture Design Chart, Software Design Description, PRS/SDD Traceability Matrix, PRS/STT Traceability Matrix, Development Environment Description, Verification and Validation Documents, Revision Level History, and Unresolved Anomalies. |
2. Sample size used for the test set and the data provenance
The document does not describe a traditional "test set" in the context of clinical or performance validation data (e.g., patient cases, imaging data) for evaluating the device's diagnostic or treatment accuracy. The submission focuses on comparing the new device's specifications and design to a predicate, and the provided "Performance Documentation" relates to software development and risk management. Therefore, no specific sample size or data provenance for a performance test set is mentioned.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Since no specific test set involving medical data (e.g., images for diagnosis, treatment plans for review) is described, this information is not applicable and not provided in the document. The "ground truth" for this submission revolves around the technical specifications and safety profile being equivalent to an already approved device.
4. Adjudication method for the test set
As there is no described test set requiring expert review or ground truth establishment, no adjudication method is mentioned.
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 TiGRT TPS is a Radiation Treatment Planning System, not a diagnostic AI tool that assists human readers. Therefore, an MRMC comparative effectiveness study involving human readers and AI assistance is not described and not relevant to this type of device. The document does not mention any AI capabilities that would directly assist human interpretation in a diagnostic sense.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document does not provide details of a standalone performance study in terms of metrics like dose calculation accuracy against physical measurements or clinical outcomes for a specific patient cohort. The "performance documentation" relates to the software development process and risk analysis rather than direct performance measurement of the algorithm itself against ground truth. The acceptance is based on design and functional similarity to the predicate, implying that if the design is substantially equivalent, the performance is also considered equivalent.
7. The type of ground truth used
The concept of "ground truth" in this 510(k) submission is primarily established by:
- Predicate Device Specifications: The technical characteristics and intended use of the legally marketed predicate device (WiMRT) serve as the "ground truth" or benchmark against which TiGRT TPS is compared for substantial equivalence.
- Industry Standards and Best Practices: Implied "ground truth" for software development and risk management practices (e.g., "Hazard Analysis Report," "Verification and Validation Documents," "Software Design Description") ensure the device is developed safely and effectively, analogous to how the predicate was developed.
8. The sample size for the training set
The document does not describe any machine learning or AI components that would require a "training set" of data. The device relies on established dose calculation algorithms (Super-position Convolution) and optimization algorithms (Genetic Algorithm) which typically do not involve statistical machine learning training on a large dataset in the same way modern AI systems do. Therefore, this information is not applicable and not provided.
9. How the ground truth for the training set was established
As there is no described training set for a machine learning model, this information is not applicable and not provided.
§ 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.