Search Results

BrainSCAN is a stereotactic radiation treatment planning system with the same intended use as the commercially available BrainSCAN Radiosurgery and BrainSCAN Conformal RT modules. It is intended for use in stereotactic, conformal, computer planned, LINAC based radiation treatment of cranial, head and neck, and extracranial lesions. It is intended to be experienced and trained health professionals.

BrainSCAN is a software program to generate treatment plans and to simulate the dose delivery for external beam radiotherapy. BrainSCAN is the evolutionary successor of the predicate devices and is a treatment planning software specialized for stereotactic procedures for cranial as well as extracranial lesions. It includes functions for all relevant steps from image viewing to quality assurance. BrainSCAN is developed for the Windows NT operating systems and is tested and released for Alpha and Intel processor platforms.

BrainSCAN incorporates all capabilities of the predicate devices and extends some of them. BrainSCAN allows aligning of two image sets of different imaging modalities automatically to obtain a common coordinate system for both. It allows defining a stereotactic coordinate system for treatment of extracranial lesions using the patient positioning system ExacTrac. To account for tissue inhomogeneities the possibility to calculate dose with a pencil beam algorithm is added. If the pencil beam algorithm is used it is possible to calculate the dose distribution of intensity modulated beams. BrainSCAN further extends the capabilities of the predicate devices to export treatment plans with the possibilities to export plans to the archive and verification system of Varian (VARiS) and to generate ASCII-files for the import into the archive and verification system of Impac (Lantis/Impac).

The provided 510(k) summary for BrainSCAN does not contain explicit acceptance criteria or a dedicated study demonstrating the device meets such criteria in terms of specific performance metrics.

This 510(k) submission focuses on demonstrating substantial equivalence to predicate devices (BrainSCAN Radiosurgery Module K920879 and BrainSCAN Conformal RT Module K971367), rather than proving quantitative performance against new acceptance criteria. The approval is based on the new version of BrainSCAN being as safe and effective as the previously cleared devices.

However, we can infer some aspects related to testing and validation from the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

As noted, explicit, quantifiable acceptance criteria with corresponding reported performance metrics are not present in the provided document. The submission instead asserts the device's performance through:

2. Sample Size Used for the Test Set and Data Provenance:

The document does not specify a sample size for a "test set" in the context of a performance study to establish new acceptance criteria. The testing mentioned appears to be internal validation (subsystem, integration, risk-based tests) rather than a formal clinical performance study with a distinct test set.

Data provenance (e.g., country of origin, retrospective/prospective) is not mentioned for any specific performance testing. The only mention of prior use is about the predicate devices being used "in over a hundred installations worldwide" and "thousands of patients have safely been treated using the predicate devices... in clinics like the University of California, Los Angeles." This refers to experience with the predicate devices, not new data from the BrainSCAN 5.0.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:

This information is not provided as there is no description of a formal "test set" with ground truth established by experts. The statement, "All treatment plans generated with BrainSCAN have to be approved by signature of a radiation physicist and a physician, normally a radiation oncologist, prior to treatment," describes a clinical workflow for patient treatment approval, not a method for establishing ground truth in a performance study.

4. Adjudication Method for the Test Set:

This information is not provided as there is no mention of a formal "test set" or an adjudication process for such a set.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

No MRMC comparative effectiveness study is mentioned. The submission does not describe any study comparing human readers with AI assistance versus human readers without AI assistance, nor does it provide an effect size. The BrainSCAN system is described as a "treatment planning software" used by professionals, implying a tool rather than an AI assistant that directly guides human interpretation in a diagnostic sense.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:

The document describes internal testing of the software's components ("subsystem level," "integration test") and "dosimetric as well as cross checks with other treatment planning systems." While this implies evaluation of the algorithm's output in isolation (e.g., accuracy of dose calculations), it's not presented as a formal standalone performance study with defined metrics like sensitivity, specificity, etc., typically seen for diagnostic AI. The ultimate use case clearly involves significant human oversight ("approved by signature of a radiation physicist and a physician").

7. Type of Ground Truth Used:

For the "dosimetric cross checks," the implied ground truth would be the results from other, established treatment planning systems (acting as a reference standard) and possibly physical dosimetric measurements (though not explicitly stated, "dosimetric... checks" often imply this).

For other internal testing (subsystem, integration, risk analysis), the "ground truth" would likely be expected software behavior, specifications, and risk mitigation requirements.

There is no mention of pathology or outcomes data being used as ground truth for evaluating the BrainSCAN 5.0 software in this submission.

8. Sample Size for the Training Set:

No information is provided about a "training set." The BrainSCAN 5.0, as described, is a physics-based radiation treatment planning system, not a machine learning or AI system that requires a distinct "training set" in the modern sense. Its algorithms (e.g., pencil beam dose calculation) are based on established physics principles and programmed, rather than being "trained" on a dataset.

9. How Ground Truth for the Training Set Was Established:

This question is not applicable as there is no mention of a "training set" for the BrainSCAN 5.0 system as described in this 510(k) summary.

Ask a specific question about this device

Computer aided planning of static and dynamic conformal radiation therapy treatments. The BrainSCAN Conformal RT Module is intended to plan radiation therapy treatments of lesions using conformal block collimators that are shaped (i.e. contour molded) to the outline of the lesion in beam's eye view or using a multileaf collimator. Using shaped collimators helps to deliver radiation exactly to the target volume while sparing surrounding healthy tissue and critical structures from accessing radiation.

Not Found

I am sorry, but the provided text does not contain information about the acceptance criteria, study details, or performance of the BrainLab BrainScan Conformal RT Module. The document is an FDA 510(k) clearance letter from 1997, which confirms that the device is substantially equivalent to previously marketed devices for specific indications for use.

Therefore, I cannot provide the requested table and study details based on the given input.

Ask a specific question about this device