(89 days)
RadCalc Software is a program utilized in a radiation therapy department for the determination of monitor units and/or the dose to various points of interest for external beam radiation therapy and/or brachytherapy treatments. For external beam treatments, RadCalc's monitor unit calculation can be used to validate the monitor units or dose previously determined by hand or by the primary radiation therapy planning system. RadCalc's function is to support the primary radiation therapy planning computer by validating its calculation as a means of quality assurance. RadCalc Software not only performs this secondary function but can also be used as the primary means of calculating monitor units for external beam radiation treatments in situations where the physician does not order the use of a radiation therapy treatment plan.
RadCalc Software imports treatment planning parameters from the primary treatment planning system or a verify and record system; parameters can also be entered manually. The dosimetric calculations are then performed for photon or electron external beam radiation plans or LDR, HDR, and Permanent Implant brachytherapy treatment plans. The brachytherapy treatment module is only used to validate the dose to points of interest and not for brachytherapy treatment planning.
RadCalc Software allows for the transfer of the treatment planning data from the primary radiation therapy planning computer or the Verify and Record system (system actually controlling the radiation beam) to RadCalc and then to the facility's Verify and Record system or radiation therapy planning computer. This electronic transfer of treatment planning data reduces the number of errors that could occur as a result of manually inputting the data.
The RadCalc Software is a stand-alone program or operating from a server that provides determination of monitor units and/or the dose to various points of interest for external beam radiation therapy and/or brachytherapy treatments. RadCalc is designed to work on personal computers in a Windows operating system that is connected directly to the primary radiation therapy planning system. The program makes the task of performing independent Monitor Unit validations much faster, easier, and more accurate. RadCalc determines the monitor units or dose through the process of looking data up from previously input tables or data curves.
RadCalc's function is to support the primary radiation therapy planning computer by validating its calculation as a means of quality assurance. RadCalc can also be used as the primary means of calculating monitor units for external beam radiation treatments in situations where the physician does not order the use of a radiation therapy treatment plan.
RadCalc allows for the transfer of the treatment planning data from the primary radiation therapy planning computer or the Verify and Record system to RadCalc and then to the facility's Verify and Record system or radiation therapy planning computer. This electronic transfer of treatment planning data reduces the number of errors that could occur as a result of manually inputting the data. The software does not control any radiation hardware device, but does interface with the primary radiation therapy planning software and the Verify and Record software.
The provided 510(k) summary for RadCalc Software (K090531) indicates that no formal acceptance criteria or a traditional clinical study were conducted to prove the device meets specific performance criteria in the way a diagnostic or image analysis AI would.
Instead, the submission focuses on substantial equivalence to predicate devices and non-clinical software verification and validation. The device is a "Medical Charged Particle Radiation Therapy System - Accessory" and primarily functions as a quality assurance tool for validating Monitor Units (MUs) or radiation doses calculated by primary radiation therapy planning systems.
Here's a breakdown based on the provided text, addressing your points where possible:
1. Table of Acceptance Criteria and Reported Device Performance
No specific, quantified acceptance criteria (e.g., sensitivity, specificity, accuracy targets) are provided in the document for the RadCalc Software. The "performance" is implicitly tied to successfully passing software verification and validation tests as per FDA guidelines, demonstrating that it calculates MUs and doses in alignment with its design specifications and existing clinical practice.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Software development, verification, and validation per FDA guidelines. | Carried out in accordance with FDA guidelines. |
| Software met established Software Design Specifications. | Passed all testing against established Software Design Specifications for each test plan and module. |
| Risk control implemented to mitigate identified hazards. | Device Hazard analysis completed and risk control implemented. |
| Accurate calculation of monitor units/dose for external beam, LDR, HDR, and Permanent Implant brachytherapy. | Software passed all testing and supports claims of substantial equivalence. Used a brachytherapy treatment planning system for verification. |
| Smooth transfer of treatment planning data. | Verified to allow transfer of data and reduce errors, supporting claims of substantial equivalence. |
2. Sample Size Used for the Test Set and the Data Provenance
The document does not specify a "test set" in the context of clinical data or patient cases with ground truth labels. The testing appears to be software-centric functional testing rather than clinical performance evaluation.
- Sample Size: Not applicable in the traditional sense of patient data. The testing was against "established Software Design Specifications" and involved functional tests of the software's calculation capabilities and data transfer.
- Data Provenance: Not applicable. No patient data or clinical imagery was used for performance evaluation as described. The testing involved "a brachytherapy treatment planning system" for verification, implying simulated or synthetic data reflective of typical treatment planning scenarios.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
Not applicable. The "ground truth" for this software hinges on the correctness of its calculations against known physics principles and established radiation dosimetry standards, not expert interpretation of clinical data. The process involves comparing the software's calculated Monitor Units/doses against expected values derived from physics equations or existing, validated systems.
4. Adjudication Method for the Test Set
Not applicable. There was no clinical "test set" requiring expert adjudication.
5. If a Multi-Reader, Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance
No. This device is not an AI/CAD system designed to assist human readers in interpreting clinical data or images. It is a calculation validation tool. Therefore, an MRMC study comparing human performance with and without AI assistance is not applicable.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, in a way. The "testing" described is essentially the standalone performance of the software. The software's function is to perform calculations independently. Its "performance" is measured by its ability to accurately output these calculations according to its design specifications. This is inherent to the type of device (a calculation validation software), where the algorithm is the primary component being evaluated for correctness.
7. The Type of Ground Truth Used
The ground truth used for this software's validation would be:
- Physics-based calculations / Dosimetry principles: The expectation that the software correctly applies established radiation physics formulae to calculate monitor units and doses.
- Reference data/tables: The software relies on looking up data from "previously input tables or data curves," suggesting that these reference data themselves serve as part of the ground truth for its internal look-up functions.
- Comparison to existing, validated systems: The fact that it validates calculations from a "primary radiation therapy planning system" implies that the accuracy of those primary systems (or accepted gold standards in dosimetry) would form the basis for comparison.
- Software Design Specifications: The software being tested against its own design specifications implies these specifications serve as the "ground truth" for its intended functional behavior.
8. The Sample Size for the Training Set
Not applicable. This is not a machine learning or AI algorithm in the contemporary sense that requires a "training set" of data. It is a deterministic software program that performs calculations based on explicit rules and stored data (tables/curves), not by learning from examples.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as there is no training set.
§ 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.