Search Results

SIMUPLAN Treatment Planning System is intended for use in preparing individual treatment plans for patients undergoing radiation therapy treatment with external beam or brachytherapy. The program output does not directly treat the patient; all information must be confirmed by the physician prior to treatment.

The SIMUPLAN Treatment Planning System is computer based software that runs on a Macintosh platform. The modified device, SIMUPLAN Treatment Planning System version 8.5, is a stereotatic radiosurgery module update only.

The planning process begins with the selection of the treatment machine (linear accelerator) and the image set that will be used for treatment planning. The patients' image sets (i.e. CT, MR, etc.) are imported into the system by standard methods: DICOM, disk, etc. From this data the stereotatic frame is localized and the patients' anatomical structures and tumor site are contoured. The treatment plan will be calculated from the target volume, isocenter, treatment machine and prescription dose and a dose distribution will be displayed. This treatment plan can be modified by the physician prior to final output and patient treatment. The physician approved treatment plan is then printed out and a hard copy of the isodose distribution is prepared for the patients' permanent record. The patient data is then saved under a unique file name in the patient database. The program output does not directly treat the patient; all information must be confirmed by the physician prior to treatment.

The provided text is a 510(k) summary for the SIMUPLAN Treatment Planning System. It describes the device, its intended use, and its substantial equivalence to predicate devices. However, the document does not include detailed information regarding acceptance criteria or a specific study proving the device meets acceptance criteria in the way typically found for AI/ML-based medical devices.

The SIMUPLAN Treatment Planning System is described as a "stereotatic radiosurgery module update only" for an existing device (version 8.5). This implies that the core functionality and validation may have been established in previous versions (K030821 and K093391). The focus of this 510(k) appears to be on demonstrating substantial equivalence of this update, rather than providing extensive de novo performance data.

Therefore, many of the requested categories cannot be filled from the provided text.

Here's a breakdown of what can be extracted and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample size used for the test set and the data provenance:

• Sample Size (Test Set): Not specified.
• Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). The document mentions "The patients' image sets (i.e. CT, MR, etc.) are imported into the system by standard methods: DICOM, disk, etc." but does not elaborate on the origin or nature of these image sets for testing purposes.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

• Not specified.

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 mention of an MRMC study. This device is a treatment planning system, not an AI-assisted diagnostic tool for human readers, so such a study would likely not be applicable in the same way. The document states: "The program output does not directly treat the patient; all information must be confirmed by the physician prior to treatment," implying human oversight is inherent.

6. If a standalone (i.e., algorithm-only without human-in-the-loop performance) was done:

• The document implies standalone calculation: "The treatment plan will be calculated from the target volume, isocenter, treatment machine and prescription dose and a dose distribution will be displayed." However, the performance metrics of this standalone calculation are not presented.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

• Not specified. Given it's a treatment planning system, ground truth would likely relate to the accuracy of dose calculations and geometric representations, which might be validated against physical phantoms or established calculation engines, but this is not detailed.

8. The sample size for the training set:

• Not specified. This document does not describe the development or training of an AI/ML model in the sense of a new algorithm, but rather an update to an existing software system.

9. How the ground truth for the training set was established:

• Not specified.

Summary of what is present in the document relevant to the request:

• Device Name: SIMUPLAN Treatment Planning System, version 8.5 (a stereotactic radiosurgery module update).
• Intended Use: "preparing individual treatment plans for patients undergoing radiation therapy treatment with external beam or brachytherapy."
• Predicate Devices: SIMUPLAN Treatment Planning System, v 7.5 (K030821) and v 8.4 (K093391). The 510(k) argues substantial equivalence to these devices.
• Technological Considerations: The software runs on a Macintosh platform and allows for image import (DICOM, disk), localization of the stereotactic frame, contouring of anatomical structures and tumor sites, calculation of treatment plans, display of dose distribution, and modification by the physician.
• Role of Physician: Explicitly states, "The program output does not directly treat the patient; all information must be confirmed by the physician prior to treatment."

Conclusion:

This 510(k) document (K120551) primarily focuses on demonstrating substantial equivalence of a software update for a radiation therapy planning system to its previously cleared versions. It does not provide the detailed performance study information with acceptance criteria, sample sizes, expert qualifications, or adjudication methods typically required for novel AI/ML devices or for a comprehensive de novo submission of a new device. The information requested regarding acceptance criteria and performance data is largely absent from this specific submission.

Ask a specific question about this device