Search Results

The device is intended for radiation treatment planning for use in stereotactic, conformal, computer planned, Linac based radiation treatment and indicated for cranial, head and neck and extracranial lesions.

RT Elements are computed-based software applications for radiation therapy treatment planning and dose optimization for linac-based conformal radiation treatments, i.e. stereotactic radiosurgery (SRS), fractionated stereotactic radiotherapy (SRT) or stereotactic ablative radiotherapy (SABR), also known as stereotactic body radiation therapy (SBRT) for use in stereotactic, conformal, computer planned, Linac based radiation treatment of cranial, head and neck, and extracranial lesions.

The device consists of the following software modules: Multiple Brain Mets SRS 4.5, Cranial SRS 4.5, Spine SRS 4.5, Cranial SRS w/ Cones 4.5, RT Contouring 4.5, RT QA 4.5, Dose Review 4.5, Brain Mets Retreatment Review 4.5, and Physics Administration 7.5.

Here's the breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) clearance letter for RT Elements 4.5, specifically focusing on the AI Tumor Segmentation feature:

Acceptance Criteria and Reported Device Performance

Note: For "Gliomas and glio-/neuronal tumors," the reported lower bound 95% CI for Recall (0.74) is slightly below the stated acceptance criteria of 0.8. Additional clarification from the submission would be needed to understand how this was reconciled for clearance. However, for all other categories and overall, the reported performance meets or exceeds the acceptance criteria.

Study Details for AI Tumor Segmentation

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

• Sample Size: 412 patients (595 scans, 1878 annotations)
• Data Provenance: De-identified 3D CE-T1 MR images from multiple clinical sites in the US and Europe. Data was acquired from adult patients with one or multiple contrast-enhancing tumors. ¼ of the test pool corresponded to data from three independent sites in the USA.

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

• Number of Experts: Not explicitly stated as a number, but referred to as an "external/independent annotator team."
• Qualifications of Experts: US radiologists and non-US radiologists. No further details on years of experience or specialization are provided in this document.

4. Adjudication method for the test set:

• The document mentions "a well-defined data curation process" followed by the annotator team, but it does not explicitly describe a specific adjudication method (e.g., 2+1, 3+1) for resolving disagreements among annotators.

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, a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not reported for the AI tumor segmentation. The study focused on standalone algorithm performance against ground truth.

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

• Yes, a standalone performance study was done. The validation was conducted quantitatively by comparing the algorithm's automatically-created segmentations with the manual ground-truth segmentations.

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

• Expert Consensus Segmentations: The ground truth was established through "manual ground-truth segmentations, the so-called annotations," performed by the external/independent annotator team of radiologists.

8. The sample size for the training set:

• The sample size for the training set is not explicitly stated in this document. The document mentions that "The algorithm was trained on MRI image data with contrast-enhancing tumors from multiple clinical sites, including a wide variety of scanner models and patient characteristics."

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

• How the ground truth for the training set was established is not explicitly stated in this document. It can be inferred that it followed a similar process to the test set, involving expert annotations, but the details are not provided.

Ask a specific question about this device

Brainlab Elements Image Fusion is an application for the co-registration of image data within medical procedures by using rigid and deformable registration methods. It is intended to align anatomical structures between data sets. It is not intended for diagnostic purposes.

Brainlab Elements Image Fusion is indicated for planning of cranial and extracranial surgical treatments and preplanning of cranial and extracranial radiotherapy treatments.

Brainlab Elements Image Fusion Angio is a software application that is intended to be used for the co-registration of cerebrovascular image data. It is not intended for diagnostic purposes.

Brainlab Elements Image Fusion Angio is indicated for planning of cranial surgical treatments and preplanning of cranial radiotherapy treatments.

Brainlab Elements Fibertracking is an application for the processing and visualization of cranial white matter tracts based on Diffusion Weighted Imaging (DWI) data for use in treatment planning procedures. It is not intended for diagnostic purposes.

Brainlab Elements Fibertracking is indicated for planning of cranial surgical treatments and preplanning of cranial radiotherapy treatments.

Brainlab Elements Contouring provides an interface with tools and views to outline, refine, combine and manipulate structures in patient image data. It is not intended for diagnostic purposes.

Brainlab Elements Contouring is indicated for planning of cranial and extracranial surgical treatments and preplanning of cranial and extracranial radiotherapy treatments.

Brainlab Elements BOLD MRI Mapping provides tools to analyze blood oxygen level dependent data (BOLD MRI Data) to visualize the activation signal. It is not intended for diagnostic purposes.

Brainlab Elements BOLD MRI Mapping is indicated for planning of cranial surgical treatments.

The Brainlab Elements are applications and background services for processing of medical images including functionalities such as data transfer, image co-registration, image segmentation, contouring and other image processing.

They consist of the following software applications:

1. Image Fusion 5.0
2. Image Fusion Angio 1.0
3. Contouring 5.0
4. BOLD MRI Mapping 1.0
5. Fibertracking 3.0

This device is a successor of the Predicate Device Brainlab Elements 6.0 (K223106).

Brainlab Elements Image Fusion is an application for the co-registration of image data within medical procedures by using rigid and deformable registration methods.

Brainlab Elements Image Fusion Angio is a software application that is intended to be used for the co-registration of cerebrovascular image data. It allows co-registration of 2D digital subtraction angiography images to 3D vascular images in order to combine flow and location information. In particular, 2D DSA (digital subtraction angiography) sequences can be fused to MRA, CTA and 3D DSA sequences.

Brainlab Elements Contouring provides an interface with tools and views to outline, refine, combine and manipulate structures in patient image data. The output is saved as 3D DICOM segmentation object and can be used for further processing and treatment planning.

BOLD MRI Mapping provides methods to analyze task-based (block-design) functional magnet resonance images (fMRI). It provides a user interface with tools and views in order to visualize activation maps and generate 3D objects that can be used for further treatment planning.

Brainlab Elements Fibertracking is an application for the processing and visualization of information based upon Diffusion Weighted Imaging (DWI) data, i.e. to calculate and visualize cranial white matter tracts in selected regions of interest, which can be used for treatment planning procedures.

The provided text is a 510(k) clearance letter and its summary for Brainlab Elements 7.0. It details various components of the software, their indications for use, device descriptions, and comparisons to predicate devices. Crucially, it includes a "Performance Data" section with information on AI/ML performance tests for the Contouring 5.0 module, specifically for "Elements AI Tumor Segmentation."

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, focusing on the AI/ML component discussed:

Acceptance Criteria and Device Performance (Elements AI Tumor Segmentation, Contouring 5.0)

1. Table of Acceptance Criteria and Reported Device Performance

Sub-stratified Performance:

It's important to note that the acceptance criteria are stated for the lower bound of the 95% confidence intervals, while the reported device performance is presented as the mean values. The text explicitly states, "Successful validation has been completed based on images containing up to 30 cranial metastases, each showing a diameter of at least 3 mm, and images with primary cranial tumors that are at least 10 mm in diameter (for meningioma, cranial/paraspinal nerve tumors, gliomas, glioneuronal and neuronal tumors)." This implies that the lower bounds of the 95% confidence intervals for the reported mean values also met or exceeded the criteria.

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

• Test Set Sample Size: 412 patients (595 scans, 1878 annotations).
• Data Provenance: Retrospective image data sets from multiple clinical sites in the US and Europe. The data contained a homogenous distribution by gender and a diversity of ethnicity groups (White/Black/Latino/Asian). Most data were from patients who underwent stereotactic radiosurgery with diverse MR protocols (mainly 1.5T/3T MRI scans acquired in axial scan orientation). One-quarter (1/4) of the test pool corresponded to data from three independent sites in the USA.

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

• Number of Experts: Not explicitly stated as a specific number. The text refers to an "external/independent annotator team."
• Qualifications of Experts: The annotator team included US radiologists and non US radiologists. No further details on their experience (e.g., years of experience) are provided.

4. Adjudication Method for the Test Set

• The text states that the ground truth segmentations, "the so-called annotations," were established by an external/independent annotator team following a "well-defined data curation process." However, the specific adjudication method (e.g., 2+1, 3+1 consensus, or independent review) among these annotators is not detailed in the provided text.

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, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study evaluating human readers' improvement with AI assistance vs. without AI assistance was not discussed or presented in the provided text. The performance data is for the AI algorithm in a standalone manner.

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

• Yes, a standalone performance evaluation of the "Elements AI Tumor Segmentation" algorithm was performed. The study describes the algorithm's quantitative validation by comparing its automatically-created segmentations directly to "ground-truth annotations." This indicates an algorithm-only performance assessment.

7. The Type of Ground Truth Used

• The ground truth used was expert consensus (or at least expert-generated) segmentations/annotations. The text explicitly states, "The validation was conducted quantitatively by comparing the (manual) ground-truth segmentations, the so-called annotations with the respective automatically-created segmentations. The annotations involved external/independent annotator team including US radiologists and non US radiologists."

8. The Sample Size for the Training Set

• The sample size for the training set is not specified in the provided text. The numbers given (412 patients, 595 scans, 1878 annotations) pertain to the test set used for validation.

9. How the Ground Truth for the Training Set was Established

• The method for establishing ground truth for the training set is not detailed in the provided text. The description of ground truth establishment (expert annotations) is specifically mentioned for the test set used for validation. However, it's highly probable that a similar expert annotation process was used for the training data given the nature of the validation.

Ask a specific question about this device

The software displays medical images and data. It also includes functions for image review, image manipulation, basic measurements and 3D visualization.

Viewer is a software for viewing DICOM data, such as native slices generated with medical imaging devices, axial, coronal and sagittal reconstructions, and data specific volume rendered views (e.g., skin, vessels, bone). Viewer supports basic manipulation such as windowing, reconstructions or alignment and it provides basic measurement functionality for distances and angles. Viewer is not intended for diagnosis nor for treatment planning. The Subject Device (Viewer) for which we are seeking clearance consists of the following software modules.

• · Viewer 5.4 (General Viewing)
• · Universal Atlas Performer 6.0
• Universal Atlas Transfer Performer 6.0
  Universal Atlas Performer: Software for analyzing and processing medical image data with Universal Atlas to create different output results for further use by Brainlab applications
  Universal Atlas Transfer Performer: Software that provides medical image data autoseqmentation information to Brainlab applications
  When installed on a server, Viewer can be used on mobile devices like tablets. No specific application or user interface is provided for mobile devices. In mixed reality, the data and the views are selected and opened via desktop PC. The views are then rendered on the connected stereoscopic head-mounted display. Multiple users in the same room can connect to the Viewer session and view/review the data (such as already saved surgical plans) on their mixed reality glasses.

The Brainlab AG Viewer (5.4) and associated products (Elements Viewer, Mixed Reality Viewer, Smart Layout, Elements Viewer Smart Layout) are a medical image management and processing system. The device displays medical images and data, and includes functions for image review, manipulation, basic measurements, and 3D visualization.

Here's an analysis of the acceptance criteria and supporting studies based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text details various tests performed to ensure the device's performance, particularly focusing on the mixed reality aspects and measurement accuracy. However, specific numerical "acceptance criteria" (e.g., "accuracy must be >95%") and corresponding reported performance values are not explicitly stated in a detailed quantitative manner in the summary. Instead, the document describes the types of tests conducted and generally states that they were successful or ensured certain qualities.

2. Sample Size for the Test Set and Data Provenance

The document does not explicitly state the sample sizes used for any of the described tests (Ambient Light, Hospital Environment, Display Quality, Measurement Accuracy).

Regarding data provenance, the document does not specify the country of origin for any data, nor whether the data used in testing was retrospective or prospective.

3. Number of Experts and Qualifications for Ground Truth

The document does not provide information on the number of experts used to establish ground truth for any of the described tests, nor their qualifications.

4. Adjudication Method for the Test Set

The document does not describe any adjudication method (e.g., 2+1, 3+1, none) used 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. The study is focused on the device's technical performance and accuracy, not on human reader improvement with or without AI assistance.

6. Standalone (Algorithm Only) Performance Study

The document describes the "Viewer" as software for displaying and manipulating medical images. While it's a software-only device, the tests described (e.g., display quality, measurement accuracy) inherently assess the algorithm's performance in its intended functions without direct human-in-the-loop impact on the results being measured during those specific tests. However, it's not explicitly framed as an "algorithm-only" performance study in contrast to human performance, but rather as instrumental performance validation. The Mixed Reality functionality, while requiring a human operator, still has its underlying software/hardware performance (e.g., accuracy of 3D measurement placement) evaluated.

7. Type of Ground Truth Used

The document does not explicitly state the type of ground truth used for any of the tests. For "Measurement accuracy test," it can be inferred that a known, precisely measured physical or digital standard would have been used as ground truth for comparison. For other tests like display quality or compatibility, the ground truth would be conformance to established technical specifications or standards for optical properties and functional compatibility, respectively.

8. Sample Size for the Training Set

The document does not provide any information regarding a training set sample size. This is consistent with the device being primarily a viewing, manipulation, and measurement tool rather than an AI/ML diagnostic algorithm that requires a "training set" in the conventional sense. The "Universal Atlas Performer" and "Universal Atlas Transfer Performer" modules do involve "analyzing and processing medical image data with Universal Atlas to create different output results" and "provides medical image data autosegmentation information," which might imply some form of algorithmic learning or rule-based processing. However, no details on training sets for these specific components are included.

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

As no training set is mentioned or detailed, there is no information on how its ground truth might have been established.

Ask a specific question about this device

Spine Planning is intended for pre- and intraoperative planning of open and minimally invasive spinal procedures. It displays digital patient images (CT, Cone Beam CT, MR, X-ray) and allows measurement and planning of spinal implants like screws and rods.

The Spine Planning software allows the user to plan spinal surgery pre-operatively or intra-operatively. The software is able to display 2D X-Ray images and 3D datasets (e.g. CT or MR scans). The software consists of features for automated labelling of vertebrae and proposals for screw and rod implants, proposals for measurement of spinal parameters.

The device can be used in combination with spinal navigation software during surgery, where preplanned or intra-operatively created information can be displayed, or solely as a pre-operative tool to prepare the surgery.

AI/ML algorithms are used in Spine Planning for

• . Detection of landmarks on 2D images for vertebrae labeling and measurement and
• . Vertebra detection on Digitally Reconstructed Radiograph (DRR) images of 3D datasets for atlas reqistration (labeling of the vertebra).

The AI/ML algorithm is a Convolutional Network (CNN) developed using a Supervised Learning approach. The algorithm was developed using a controlled internal process that defines from the inspection of input data to the training and verification of the algorithm.

Here's a breakdown of the acceptance criteria and the study details for the Spine Planning 2.0 device, based on the provided document:

Acceptance Criteria and Device Performance

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics in a pass/fail format. However, based on the Performance Data section, we can infer the areas of assessment and general performance claims. The "Reported Device Performance" column will reflect the general findings described in the text.

• Quantified quality of vertebra level assignment.
• Quantified quality of landmark predictions.
• Quantified performance of observer view direction for 2D X-rays. |
  | Screw Proposal Algorithm Evaluation (Comparison to Predicate): | Thoracic and lumbar pedicle screw proposals generated by the new algorithm were found to be similar to those generated by the predicate algorithm. |
  | Usability Evaluation: | No critical use-related problems identified. |

Study Details

The provided text describes several evaluations rather than a single, unified study with a comprehensive design. Information for some of the requested points is not explicitly stated in the document.

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

• AI/ML Detected X-Ray Landmarks Assessment:
  • Sample Size: Not explicitly stated.
  • Data Provenance: "2D X-rays from the Universal Atlas Transfer Performer 6.0." This suggests either a curated dataset or potentially synthetic data within a software environment, but specific origin (e.g., country, hospital) or whether it was retrospective/prospective is not provided.
• Screw Proposal Algorithm Evaluation:
  • Sample Size: Not explicitly stated.
  • Data Provenance: Not explicitly stated, but implies the use of test cases to generate screw proposals for comparison.
• Usability Evaluation:
  • Sample Size: Not explicitly stated.
  • Data Provenance: Not explicitly stated.

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

• AI/ML Detected X-Ray Landmarks Assessment: Not explicitly stated in the provided text. The document mentions "quantifying" various quality aspects, which implies a comparison to a known standard or expert annotation, but details are missing.
• Screw Proposal Algorithm Evaluation: Not explicitly stated. The comparison is "to the predicate and back-up algorithms," suggesting an algorithmic ground truth or comparison standard rather than human expert ground truth for individual screw proposals.
• Usability Evaluation: Not applicable, as usability testing focuses on user interaction rather than ground truth for clinical accuracy.

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

• Not explicitly stated for any of the described evaluations.

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 MRMC comparative effectiveness study involving human readers with and without AI assistance is described in the provided text. The evaluations focus on the algorithm's performance or similarity to a predicate, and usability for the intended user group.

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

• Yes, the AI/ML Detected X-Ray Landmarks Assessment and the Screw Proposal Algorithm Evaluation appear to be standalone algorithm performance assessments.
  • The "AI/ML Detected X-Ray Landmarks Assessment" explicitly evaluates the AI/ML detected landmarks.
  • The "Screw Proposal Algorithm Evaluation" compares the new algorithm's proposals to existing algorithms, indicating a standalone algorithmic assessment.

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

• AI/ML Detected X-Ray Landmarks Assessment: Inferred to be a form of expert-defined or algorithm-defined gold standard given the quantification of object detection, quality of labeling, and landmark predictions. The source "Universal Atlas Transfer Performer 6.0" might imply a reference standard built within that system.
• Screw Proposal Algorithm Evaluation: The ground truth used for comparison was the output of the "predicate and back-up algorithms," implying an algorithmic gold standard.
• Usability Evaluation: Ground truth is not applicable in the sense of clinical accuracy; rather, the measure is the identification of "critical use-related problems" by users during testing.

8. The sample size for the training set:

• Not explicitly stated for the AI/ML algorithms mentioned. The document only mentions that the "AI/ML algorithm is a Convolutional Network (CNN) developed using a Supervised Learning approach" and "developed using a controlled internal process that defines from the inspection of input data to the training and verification of the algorithm."

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

• Not explicitly stated. Given it's a "Supervised Learning approach," it would imply that the training data was meticulously labeled, likely by experts (e.g., radiologists, orthopedic surgeons) or through a highly curated process, but the document does not elaborate on this.

Ask a specific question about this device

Brainlab Elements are software applications indicated for the processing of medical image data to support the intended user group to perform image guided surgery and radiation treatment planning.

Brainlab Elements Contouring provides an interface with tools and views to outline, refine, combine and manipulate structures in patient image data. The generated 3D structures are not intended to create physical replicas used for diagnostic purposes.

Brainlab Elements Image Fusion is an application for the co-registration of image data within medical procedures by using rigid and deformable registration methods. It is intended to align anatomical structures between data sets.

Brainlab Elements Fibertracking is an application of cranial white matter tracts based on Diffusion Tensor Imaging (DTI) data for use in treatment planning procedures.

Brainlab Elements BOLD MRI Mapping provides tools to analyze task based blood oxygen level dependent data (BOLD MRI Data) to visualize the activation signal.

Brainlab Elements Image Fusion Angio is a software application that is intended to be used for the co-registration of cerebrovascular image data.

The Brainlab Elements 6.0 are applications that transfer DICOM data to and from picture archiving and communication systems (PACS) and other storage media devices. They include modules for 2D & 3D image viewinq, imaqe processing, image co-registration, image seqmentation and 3D visualization of medical image data for treatment planning procedures.

They consist of the following software applications:

• 1. Contouring 4.5
• 2. Imaqe Fusion 4.5
• 3. Fibertracking 2.0
• 4. BOLD MRI Mapping 1.0
• 5. Image Fusion Angio 1.0

This device is a successor of the Predicate Device Brainlab Elements 5.0 (K212420).

Brainlab Elements Contouring provides an interface with tools and views to outline, edit, refine, combine and manipulate structures in patient image data. The output is saved as 3D DICOM seqmentation object and can be used for further processing and treatment planning.

Brainlab Elements Image Fusion is an application for the co-registration of image data within medical procedures by using rigid and deformable registration methods.

The co-registration consists on providing spatial alignment/fusion of medical imaging data, which are derived from different or same imaging modalities (e.g. CT, MRI, PET, SPECT, US). Once two image sets are fused, they can be viewed simultaneously. All planned content (e.g. objects and trajectories) defined in one image set is visible in any other fused image set. The algorithm used in Image Fusion matches two image sets together with common anatomical structures for optimal fusion results. Therefore, the two image sets must share the same common anatomical area.

Brainlab Elements Fibertracking is an application for the processing and visualization of information based upon Diffusion Tensor Imaging (DTI) data, i.e. to calculate and visualize cranial white matter tracts in selected regions of interest, which can be used for treatment planning procedures.

Diffusion Tensor Imaging (DTI) is a magnetic resonance technique, that allows the measurement of diffusion anisotropy in the brain using diffusion weighted images that were scanned with magnetic field gradients applied in several directions. The Fibertracking software uses the scans to calculate the diffusion direction of the water molecules alonq potential white matter fibers for the entire data volume.

Brainlab Elements Image Fusion Angio is a software application that is intended to be used for the co-registration of cerebrovascular image data. It allows to register digital subtraction anqiographies to vascular images in order to combine flow and location information. In particular, 2D DSA (digital subtraction angiography) sequences can be fused to MRA, CTA and 3D DSA sequences.

The provided text is a 510(k) Summary for Brainlab Elements 6.0 and related applications. It describes the device, its intended use, and argues for its substantial equivalence to predicate devices, including an older version of Brainlab Elements and iPlan.

However, the document does not contain the detailed performance study information requested in your prompt. Specifically, it lacks:

• A table of acceptance criteria and reported device performance. The document states "Verification and validation activities carried out established that the set requirements were met and that the device performs as claimed," but does not provide specific metrics or a table.
• Sample size and data provenance for a test set. It mentions a "test pool data" set aside for AI/ML algorithm evaluation but gives no size or details on provenance.
• Number and qualifications of experts for ground truth.
• Adjudication method for the test set.
• Details on any MRMC comparative effectiveness study, including effect size.
• Specific standalone performance results for the algorithm.
• Type of ground truth used (e.g., pathology, outcomes).
• Sample size and ground truth establishment for the training set.

The document primarily focuses on software verification and general clinical validation conclusions (e.g., "All applicable safety and performance requirements are fulfilled," "Clinical data collected establishes the performance and safety"). It mentions an AI/ML algorithm for tumor segmentation but provides no details on its performance, training, or testing methodology beyond general statements.

Therefore, based solely on the provided text, it is not possible to answer your request for specific acceptance criteria and detailed proof of meeting those criteria. The document contains general statements about validation and verification but lacks the specific quantitative and methodological details needed to fill out your requested table and information points.

Ask a specific question about this device

Brainlab Elements Trajectory Planning software is intended for pre-, intra- and postoperative image-based planning and review of either open or minimally invasive neurosurgical procedures. Its use is indicated for any medical condition in which the use of stereotactic surgery may be appropriate for the placement of instruments/devices and where the position of the instrument/device can be identified relative to images of the anatomy.

This includes, but is not limited to, the following cranial procedures (including frame-based stereotaxy and frame alternative-based stereotaxy):

• Catheter placement
• Depth electrode placement (SEEG procedures)
• Lead placement and detection (DBS procedures)
• Probe placement
• Cranial biopsies

Brainlab Elements Trajectory Planning is a software used to plan minimally invasive possible pathways (Trajectories') for surgical instruments on scanned images. It is used for the processing and viewing of anatomical images (for example: axial, coronal and sagittal reconstructions, etc.) and corresponding planning contents (for example: co-registrations, seqmentations, fiber tracts created by compatible applications and stored as DICOM data) and the planning of trajectories based on this data. The device is also used for the creation of coordinates and measurements that can be used as input data for surgical intervention (e.g.: stereotactic arc settings or FHC STarFix platform settings). Depending on the workflow and available licenses, Brainlab Elements Trajectory Planning might be used in different roles where only specific application features are available.

The following roles are available for Trajectory Planning:

• Trajectory (Element): allows the creation of trajectories
• Stereotaxy (Element): allows the creation of trajectories and supports stereotactic procedures based on Stereotactic Arc Settings or FHC STarFix platform settings
• Lead Localization (Element): allows the creation of trajectories and automatic detection of leads in post-operative images.

All roles are enabled to be used for cranial trajectory planning procedures after installation of Trajectory as well as the corresponding workflow files for Cranial Planning, Stereotactic Planning or Post-Op Review.

The provided text describes the 510(k) premarket notification for the Brainlab Elements - Trajectory Planning (2.6) device. It acts as a K-number summary, primarily comparing the new device to existing predicate devices to establish substantial equivalence. While it discusses certain "performance data" and "verification," it does not present a detailed study with acceptance criteria and reported device performance in the format of clinical trial results or a validation study with specific metrics.

The document states that the objective of "validative tests" was to verify that the accuracy and robustness of automatically and semi-automatically detected WayPoint anchors used in FHC's 4mm and 5mm bone anchors were "non-inferior" to a specified predicate software application. It also states that "the acceptance criteria specified in the test plan regarding the Brainlab automatic and semi-automatic anchor detection algorithm were fulfilled." However, the specific acceptance criteria and the reported quantitative performance metrics are not included in this document.

Therefore, I cannot fulfill your request for a table of acceptance criteria and reported device performance, sample sizes, expert details, adjudication methods, MRMC study details, or specific ground truth methodologies for a standalone performance study, as these details are not provided in the given text.

Based on the information provided, here's what can be inferred and what remains unknown regarding the "study" mentioned:

Known Information (based on the provided text):

• Device Performance Focus: The performance data section focuses on "FHC anchor detection" and "summative usability evaluation."
• FHC Anchor Detection Objective: To verify that the accuracy and robustness of Brainlab's automatic and semi-automatic WayPoint anchor detection on CT data for FHC's 4mm and 5mm bone anchors are non-inferior to the predicate "SW application WayPoint™ Planner Software."
• Acceptance Criteria for Anchor Detection: The text states, "The acceptance criteria specified in the test plan regarding the Brainlab automatic and semi-automatic anchor detection algorithm were fulfilled." (However, the specific criteria are not provided.)
• Summative Usability Evaluation: This evaluation covered the support of STarFix platforms for DBS procedures, including detection of WayPoint bone anchors and platform planning. New GUI functionalities (locking of plans, overlay/blending of fused images, and new interaction with coordinates) were also included.
• Study Type Mentioned: "Validative tests" for anchor detection and "summative evaluation" for usability.
• Conclusion: The manufacturer concluded that "the performed verification and validation activities established that the set requirements were met and that the device performs as intended."

Unknown Information (not provided in the text):

1. Table of Acceptance Criteria and Reported Device Performance: This critical information is missing. The document only states that acceptance criteria were fulfilled, not what they were or the quantitative results achieved.
2. Sample Size Used for the Test Set and Data Provenance: The document does not specify the number of cases or images used in the FHC anchor detection or usability tests, nor does it state the country of origin of the data or if it was retrospective/prospective.
3. Number of Experts Used to Establish Ground Truth and Qualifications: The number and qualifications of experts involved in establishing ground truth (for anchor detection) or participating in the usability evaluation are not mentioned.
4. Adjudication Method: No information is provided regarding how disagreements or the ground truth was established for the test set.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study: The document does not describe an MRMC study comparing human readers with and without AI assistance. The non-inferiority claim for anchor detection is against a software application, not a human reader.
6. Standalone (Algorithm Only) Performance: While the "FHC anchor detection" seems to refer to algorithm performance, specific metrics (e.g., sensitivity, specificity, accuracy for anchor detection) of the algorithm in a standalone capacity are not provided. The non-inferiority is stated against another software product, not against a defined ground truth with quantitative metrics.
7. Type of Ground Truth Used: For the FHC anchor detection, it's implied that there's a ground truth for "accuracy and robustness" of anchor detection, likely based on known positions or expert annotations of anchors. However, the specific method (e.g., expert consensus, physical measurements) is not detailed. For usability, the ground truth would be user feedback and observed performance.
8. Sample Size for the Training Set: No information is provided about the training set for any machine learning components within the device (if any). The context suggests this is more about software functionality and accuracy validation rather than a deep learning model requiring a large training set.
9. How Ground Truth for the Training Set Was Established: This information is also absent.

Ask a specific question about this device

The device is intended for radiation treatment planning for use in stereotactic, conformal, computer planned, Linac based radiation treatment and indicated for cranial, head and neck and extracranial lesions.

RT Elements are computed-based software applications for radiation therapy treatment planning and dose optimization for linac-based conformal radiation treatments, i.e. stereotactic radiosurgery (SRS), fractionated stereotactic radiotherapy (SRT) or stereotactic ablative radiotherapy (SABR), also known as stereotactic body radiation therapy (SBRT) for use in stereotactic, conformal, computer planned, Linac based radiation treatment of cranial, head and neck, and extracranial lesions.

The following applications are included in RT Elements 4.0:

• -Multiple Brain Mets SRS
• -Cranial SRS
• -Spine SRS
• Cranial SRS w/ Cones -
• -RT QA
• -Dose Review
• -Retreatment Review

The given FDA 510(k) summary for Brainlab AG's RT Elements 4.0 provides a general overview of the device and its equivalence to a predicate device, but it lacks specific details regarding quantitative acceptance criteria and a structured study to prove these criteria were met.

The document focuses on substantiating equivalence by comparing features and functionality with the predicate device (RT Elements 3.0 K203681). While it mentions "Software Verification," "Bench Testing," "Usability Evaluation," and "Clinical Evaluation," it does not provide the detailed results of these studies in a format that directly addresses specific acceptance criteria with reported device performance metrics.

Therefore, many of the requested fields cannot be directly extracted from the provided text.

Here's an attempt to answer the questions based on the available information:

1. A table of acceptance criteria and the reported device performance

The document does not explicitly state quantitative acceptance criteria in a table format with corresponding reported performance for the new specific features. It mentions "Dose Calculation Accuracy" as existing criteria from the predicate device that remains the same.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document does not specify the sample size for any test sets used in the verification or validation activities. It also does not mention the data provenance (country of origin, retrospective/prospective).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not provided in the document.

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

The document does not mention any adjudication method.

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 document does not indicate that an MRMC comparative effectiveness study was conducted. The "Clinical Evaluation" is mentioned, but no details of such a study are provided, nor is there any mention of "AI assistance" or its effect size on human readers. The new "Treatment Time Bar" feature is described as "supports the user in decision making" and "gives the user a better overview of different treatment data," but this is not framed as an AI-assisted improvement study.

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

The document does not explicitly describe a standalone algorithm-only performance study. The focus is on the integrated software system for treatment planning.

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

The document does not specify the type of ground truth used for any of the evaluations. For "Dose Calculation Accuracy," the ground truth would typically be a highly accurate physical measurement or a reference dose calculation from a gold-standard system, but this is not explicitly stated.

8. The sample size for the training set

The document does not provide any details about a training set, as this is a software update and verification rather than a de novo AI model development described in typical machine learning submissions. The dose calculation models are well-established.

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

Not applicable based on the available information (no training set mentioned).

Ask a specific question about this device

Brainlab Elements Guide XT provides functionality to assist medical professionals in planning the programming of stimulation for patients receiving approved Boston Scientific deep brain stimulation (DBS) devices.

Brainlab Elements Guide XT is a software application designed to support neurosurgeons and neurologists in Deep Brain Stimulation (DBS) treatments. It enables stimulation field simulation and visualization of the stimulation field model in the context of anatomical images. This functionality can be used to aid in lead parameter adjustment. Brainlab Elements Guide XT is used in combination with other applications that provide functionality for image fusion, segmentation, etc. Guide XT is compatible with selected Boston Scientific leads and implantable pulse generators but does not directly interact with the surgeon. The subject device Brainlab Elements Guide XT consists of multiple software components including the Guide XT 3.0 application that provides the core functionality for stimulation field model creation and visualization in the context of the patient anatomy.

The provided text does not contain detailed acceptance criteria and performance data for the Brainlab Elements Guide XT device. It broadly states that "the device was demonstrated to be as safe and effective as the predicate device" based on "verification and non-clinical tests."

However, I can extract the information that is present and indicate where specific details are missing based on your request.

Here's a breakdown of the available information:

1. A table of acceptance criteria and the reported device performance

The document does not provide a specific table of acceptance criteria with corresponding performance metrics. It only mentions general testing and verification without quantifiable results.

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

The document states: "Additionally, the performance test for the VTA (Volume of Tissue Activated) simulation was conducted supporting the use of a proprietary heuristic methodology for the prediction of threshold current (Ith) maps in the vicinity of implanted leads stimulated by the Deep Brain Stimulation (DBS) system from Boston Scientific Neuromodulation (BSN)."

• Sample Size for Test Set: Not explicitly stated.
• Data Provenance: Not specified (e.g., country of origin). The study is described as a "performance test for the VTA simulation," suggesting it's likely a retrospective analysis of existing data or a simulated environment, but not explicitly stated as retrospective or prospective human subject data. "Clinical data was leveraged from the existing literature sources to validate the indications and intended use of the device," but this refers to the validation of the indications, not the direct performance test of the device itself. The device "was not used for any clinical tests for the purposes of this 510(k) submission."

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

This information is not provided. The document describes a "proprietary heuristic methodology" for VTA simulation, but it does not mention expert involvement in establishing ground truth for the performance test set.

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

This information is not provided.

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 document explicitly states: "The Subject Device was not used for any clinical tests for the purposes of this 510(k) submission." Therefore, an MRMC comparative effectiveness study was not conducted with human readers using the device. The device is a "planning software" to "assist medical professionals in planning," so human-in-the-loop performance would be relevant, but it was not tested in this submission.

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

Yes, a standalone performance test was done for the VTA simulation. The document states: "Additionally, the performance test for the VTA (Volume of Tissue Activated) simulation was conducted supporting the use of a proprietary heuristic methodology for the prediction of threshold current (Ith) maps in the vicinity of implanted leads stimulated by the Deep Brain Stimulation (DBS) system from Boston Scientific Neuromodulation (BSN)."

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

The document mentions that the VTA simulation performance test "supporting the use of a proprietary heuristic methodology." This implies the ground truth might have been established through a computational model or prior validated data from Boston Scientific, rather than directly from expert consensus, pathology, or outcomes data from independent cases for this specific performance test. The document does not definitively state the type of ground truth used for this VTA simulation performance evaluation.

8. The sample size for the training set

The document does not mention a training set or its sample size. The VTA simulation uses a "proprietary heuristic methodology," which might imply a model without explicit training data or a model trained externally, but no details are provided here.

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

Since no training set is mentioned, this information is not provided.

Ask a specific question about this device

Spine & Trauma Navigation System is intended as an intraoperative image-guided localization system to enable open and minimally invasive surgery. It links a freehand probe, tracked by a passive marker sensor system to virtual computer image space on a patient's preoperative or intraoperative 2D or 3D image data.

Spine & Trauma Navigation System enables computer-assisted navigation of medical image data, which can either be acquired preoperatively or intraoperatively by an appropriate image acquisition system. The software offers screw and interbody device planning and navigation with surgical instruments.

The system is indicated for any medical condition in which the use of stereotactic surgery may be appropriate and where a reference to a rigid anatomical structure, such as the skull, the pelvis, a long bone or vertebra can be identified relative to the acquired image (CT, MR, 2D fluoroscopic image or 3D fluoroscopic image reconstruction) and/or an image data based model of the anatomy.

Spine Planning is intended for pre- and intraoperative planning of open- and minimal invasive spinal procedures. It displays digital bio imaging and allows measurement and planning of spinal implants like screws and rods.

The Subject Device Spine and Trauma Navigation System consists of the following software's and hardware.

Software:

• 1. Spine & Trauma 3D Navigation 1.5
• 2. Instrument Selection 1.6
• 3. Fluoro 3D 1.0
• 4. Registration Software Paired Point 3.5
• 5. Registration Software Spine Surface Matching 1.0
• 6. Spine Planning 1.0

Hardware:
The Hardware accessories for the Subject Device are Platforms and Surgical Instruments.

The provided text describes a 510(k) premarket notification for the Brainlab AG Spine & Trauma Navigation System. It outlines the device, its indications for use, and a summary of the performance data provided to the FDA. However, the document does not contain specific acceptance criteria, detailed results of a study proving the device meets these criteria, or information on aspects like sample size, expert ground truth establishment, or human reader studies.

The document states that "The verification of the Spine & Trauma Navigation System has been carried out thoroughly both at the top level and on underlying modules according to the verification plan and following internal processes. The verification was done to demonstrate that the design specifications are met." It also mentions "Bench Testing" for instruments. However, it does not provide the quantitative data necessary to populate the requested table or answer the specific questions about the study design and results.

Therefore, I cannot provide the requested information from the provided text. The output will explicitly state what information is and is not available in the input.

Information Not Found in the Provided Text:

The provided 510(k) summary does not contain the detailed performance study results, acceptance criteria, or specific aspects of a clinical or bench study needed to answer the questions comprehensively. While it mentions "Software Verification and Validation Testing" and "Bench Testing," it does not provide the quantitative data, methodology details (sample size, ground truth generation, expert qualifications, adjudication methods), or comparative effectiveness study results requested.

Therefore, the following sections will indicate where information is missing.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Sample Size for Test Set: Not specified in the provided document.
• Data Provenance: Not specified in the provided document. The document mentions "patient's preoperative or intraoperative 2D or 3D image data" but does not detail the origin or nature of the data used for verification/validation.
• Retrospective or Prospective: Not specified in the provided document.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Number of Experts: Not specified in the provided document.
• Qualifications of Experts: Not specified in the provided document.
• Ground Truth Establishment: The document refers to "preoperative or intraoperative scans" as the basis for navigation and planning, implying that these images serve as a form of ground truth for instrument placement relative to anatomy, but it does not describe a process involving human experts to establish ground truth for a test set to evaluate the device's accuracy against.

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

• Adjudication Method: Not specified in the provided document.

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

• MRMC Study: Not mentioned or described in the provided document. The device is a navigation system and planning software, not an AI-assisted diagnostic tool typically evaluated with MRMC studies focused on human reader improvement. The focus is on the system's ability to localize and guide instruments.
• Effect Size of Human Reader Improvement: Not applicable/not provided as no such study is described.

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

• The document implies that the device's software components (e.g., Spine & Trauma 3D Navigation, Spine Planning) perform specific functions, and their "verification and validation testing" was conducted. However, the exact nature of "standalone" performance testing (e.g., algorithm-only accuracy on a dataset without human interaction, specifically for AI/ML components) is not explicitly detailed with performance metrics. The device is intended for human-in-the-loop surgery.

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

• The document implies that the "acquired image (CT, MR, 2D fluoroscopic image or 3D fluoroscopic image reconstruction) and/or an image data based model of the anatomy" serves as the reference ("ground truth") against which the navigation system operates, by linking a tracked probe to this virtual computer image space. For planning, screws are proposed and reviewed ("approved") but the ultimate ground truth for the accuracy of a plan would typically relate to anatomical landmarks on these images, often confirmed by intraoperative imaging. No mention of expert consensus, pathology, or outcomes data being used as ground truth for a performance study is made.

8. The sample size for the training set

• Training Set Sample Size: Not applicable or not specified. The document describes a "verification" process for a regulated medical device, not explicit "training" of a machine learning model. While software verification and validation would use test data, this is distinct from a "training set" for AI/ML model development. The document does not indicate that the device uses an AI/ML model that requires a training set in the conventional sense.

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

• Ground Truth for Training Set: Not applicable or not specified, for the same reasons as in point 8.

Ask a specific question about this device

The Plasma Edge System single use bipolar resection electrodes are used for the ablation and hemostasis of tissues under endoscopic control, in association with endoscopic accessories. They are intended for endoscopic surgeries with saline irrigation, in the field of urology. The use of the Plasma Edge System is restricted to surgeons, specialized in urological surgery, for specific use in: - Transurethral resection of prostate (TURP) for benign prostatic hypertrophy - Transurethral incision of the prostate (TUIP) or bladder neck - Transurethral resection of bladder tumors (TURBT) - Cystodiathermy • Transurethral Vaporization of the prostate (TUVP/TVP) for benign prostatic hypertrophy, and for Transurethral Vaporization of bladder tumors. (MVVS and MVV models only)

The Plasma Edge system is a manual surgical device, consisting of a single-use electrode with cable range, an active and passive working element reusable and an adaptor to an HFgenerator compatible. The electrodes consist of an active tip, two wires threaded through ceramic tubes to connect the active tip to the body of the loop, allowing the HF energy to reach the active tip. It has to be used with continuous flow irrigation of saline solution (NaCl 0,9%) that reachesthe operative site through a resectoscope. The HF energy delivered from the generator tothe electrode ionizes the gas of the saline solution, creating a plasma for the cutting, coagulation and vaporization of tissues.

The provided text is a 510(k) Summary for the Plasma EDGE system, which is an endoscopic electrosurgical unit and accessories. It focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed study of the device's performance against specific acceptance criteria for diagnostic tasks.

Therefore, much of the requested information regarding diagnostic accuracy studies, sample sizes for test and training sets, expert qualifications, and ground truth establishment is not present in this document. The document describes engineering and safety testing.

Here's the information that can be extracted or deduced from the document:

1. A table of acceptance criteria and the reported device performance

The document lists performance tests conducted to ensure the device functions as intended and meets design specifications, based on in-house acceptance criteria derived from ISO-14971:2007 (Risk analysis) and various other standards. Specific quantitative acceptance criteria or reported performance results (e.g., in terms of measurements or thresholds) are not provided in detail in this summary, other than stating that the tests were completed successfully.

Study that Proves the Device Meets Acceptance Criteria:

The document refers to a series of performance tests and usability studies conducted to ensure the system functions as intended and meets design specifications. These studies are collectively referred to as "Performance testing" (Section iii).

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

This information is not provided in the document. The studies mentioned are engineering and safety tests, not clinical studies involving patient data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not applicable and therefore not provided, as the tests described are technical validations (biocompatibility, electrical safety, sterilization, bench-top) rather than clinical evaluations requiring expert-derived ground truth for diagnostic or therapeutic accuracy.

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

Not applicable, as this is related to expert review of clinical data, which is not described.

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

Not applicable. This is not a diagnostic AI device, but an electrosurgical system.

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

Not applicable. This is not an AI algorithm. The performance tests are focused on the device's technical and physical characteristics.

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

For the technical performance aspects, "ground truth" would be established through adherence to recognized standards (e.g., ISO, IEC), material specifications, and validated processes. For example:

• Biocompatibility: Results of standardized in-vitro and in-vivo tests according to ISO 10993 series.
• Electrical Safety/EMC: Compliance with IEC 60601 series, measured electrical parameters within specified limits.
• Sterilization: Demonstrated sterility assurance level (SAL) according to ISO 11135 and other related standards.
• Bench-top testing: Physical measurements, visual inspection, and functional verification against design specifications and predicate performance (e.g., cutting efficacy on ex vivo tissues).

8. The sample size for the training set

Not applicable, as this is not an AI/machine learning device.

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

Not applicable, as this is not an AI/machine learning device.

Ask a specific question about this device