(289 days)
MUV 4.0 is a quality assurance (QA) tool intended for independent verification of the dose calculations performed during treatment planning for external beam therapy.
MUV 4.0 is a quality assurance (QA) tool intended for independent verification of the dose calculations performed during treatment planning for external beam therapy. The intended user is a medical physicist or someone well familiar with the dosimetric concepts that are of importance in external beam therapy.
The software requires beam data for individual treatment plans to be imported through the DICOM RT Plan format. The parameters associated with the treatment delivery on the accelerator can not be edited within the software, although parameters related to the calculation inside the patient/phantom, such as the coordinates and depths of the calculation points, are open for editing.
The software is validated for broad megavoltage photon beams in the range from 4 up to 30 MV and broad electron beams from 4 to 30 MeV, delivered by standard medical linear accelerators (linacs).
The software runs on a Windows XP, windows Vista and windows 7 systems (32 bit)
This document, K103515, describes the 510(k) premarket notification for the EQUAL Dose 4.0, a quality assurance (QA) tool for independent verification of dose calculations in external beam radiation therapy.
Here's an analysis of the provided information regarding acceptance criteria and the study:
1. Table of Acceptance Criteria and Reported Device Performance
The provided text does not explicitly state specific acceptance criteria in terms of numerical thresholds (e.g., accuracy percentages, deviation limits) for the EQUAL Dose 4.0 software.
However, the document describes the software's validation, which implies its performance meets certain expectations:
| Acceptance Criteria (Implied) | Reported Device Performance (Validation Context) |
|---|---|
| Independent verification of dose calculations for external beam therapy. | Validated for broad megavoltage photon beams (4-30 MV) and broad electron beams (4-30 MeV) delivered by standard medical linear accelerators (linacs). |
| Accuracy of dose calculation for photons using Pencil Beam algorithm. | Implied to be accurate for photon dose calculations, as it uses a Pencil Beam algorithm. |
| Accuracy of dose calculation for electrons using Gaussian Pencil Beam algorithm. | Implied to be accurate for electron dose calculations, as it uses a Gaussian Pencil Beam algorithm. |
| Functionality as a QA tool for treatment planning verification. | Described as a QA tool for "independent verification of the dose calculations performed during treatment planning for external beam therapy." |
2. Sample Sizes Used for the Test Set and Data Provenance
The document does not specify the sample size used for the test set or the data provenance (e.g., country of origin, retrospective or prospective). It mentions "beam data for individual treatment plans" can be imported but doesn't detail the origin or quantity of this data for validation.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
The document does not provide information on the number of experts used to establish ground truth or their qualifications. It states the intended user is a "medical physicist or someone well familiar with the dosimetric concepts that are of importance in external beam therapy," which suggests expert involvement might be assumed in practice, but no formal ground truth establishment process is detailed.
4. Adjudication Method for the Test Set
The document does not specify any adjudication method (e.g., 2+1, 3+1, none) for the test set.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
The document does not mention a Multi-Reader Multi-Case (MRMC) comparative effectiveness study. This is an independent verification tool for dose calculations, not a diagnostic imaging device typically evaluated with MRMC studies for human reader performance improvement.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
The provided information suggests that the validation described is for the standalone (algorithm only) performance of the EQUAL Dose 4.0. It's a "QA tool intended for independent verification of the dose calculations." The "intended user is a medical physicist," implying that the medical physicist uses the tool, but the validation described is of the software's calculation capabilities itself rather than human-AI combined performance. The validation addresses the accuracy of the software's internal calculations and algorithms (Pencil Beam, Gaussian Pencil Beam) against known physical principles and expected outcomes for radiation beams.
7. Type of Ground Truth Used
The document does not explicitly state the type of ground truth used. However, given it's a dose calculation verification tool, the ground truth would typically be established by:
- Established physics principles and analytical models: The algorithms (Pencil Beam, Gaussian Pencil Beam) are based on fundamental physics.
- Measurements from phantoms: Often, dose calculations are validated against actual dose measurements in phantoms using ionization chambers, films, or other dosimeters.
- Comparison to other validated treatment planning systems: Although this device is for verification, sometimes initial validation involves comparing its output to highly accurate reference systems.
The text's statement "The software is validated for broad megavoltage photon beams... and broad electron beams..." implies a comparison against established physical reality for these beam types.
8. Sample Size for the Training Set
The document does not specify a sample size for the training set. For a physics-based dose calculation software, a traditional "training set" as understood in machine learning might not be applicable in the same way. Instead, the "training" phase would involve the development and internal testing of the algorithms to ensure they correctly implement the physical models.
9. How the Ground Truth for the Training Set Was Established
Similar to point 8, the concept of a "training set" for ground truth establishment might not directly apply. If any "training" data were used during development (e.g., to fine-tune model parameters), the ground truth for that would likely be based on:
- Known physical properties of radiation beams and materials.
- Experimental data from linear accelerators and phantoms.
In summary, the provided submission focuses on the technical specifications and intended use of the EQUAL Dose 4.0 as a verification tool based on established physics algorithms, rather than detailing extensive clinical study results for acceptance criteria, sample sizes, or ground truth establishment in the way typically seen for diagnostic AI models. The validation mentioned is more akin to demonstrating the accurate implementation of known physical models within the software.
§ 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.