Search Results

The Monaco system is used to make treatment plans for patients with prescriptions for external beam radiation therapy. The system calculates dose for photon, electron, and proton treatment plans and displays, on-screen and in hard-copy, two- or three-dimensional radiation dose distributions inside patients for given treatment plan set-ups. The Monaco product line is intended for use in radiation treatment planning. It uses generally accepted methods for:

contouring
image manipulation
simulation
image fusion
plan optimization
QA and plan review

Device Description

The Monaco RTP System accepts patient diagnostic imaging data from CT and MR scans, and source dosimetry data, typically from a linear accelerator. The system then permits the user to display and define (contour) the target volume to be treated and critical structures which must not receive above a certain level of radiation, on these diagnostic images. Based on the prescribed dose, the user, a Dosimetrist or Medical Physicist, can then create multiple treatment scenarios involving the number, position(s) and energy of radiation beams and the use of a beam modifier (MLC, block, etc.) between the source of radiation and the patient to shape the beam. Monaco RTP system then produces a display of radiation dose distribution within the patient, indicating not only doses to the target volume but to surrounding tissue and structures. The optimal plan satisfying the prescription is then selected, one that maximizes dose to the target volume while minimizing dose to surrounding healthy volumes.

The parameters of the plan are output for later reference and for inclusion in the patient file. Monaco planning methods and modalities:

Intensity Modulated Radiation Treatment (IMRT) planning
Electron, photon and proton treatment planning
Planning for dynamic delivery methods (e.g., dMLC, dynamic conformal)
Volumetric Modulated Arc Therapy (VMAT)
Stereotactic planning and support of cone-based stereotactic
3D conformal planning
Distributed planning configurations (e.g., for conventional linac)
Adaptive planning capabilities (e.g., for MR-Linac & conventional linac)
Auto planning features (e.g., for conventional linac)

Monaco basic systems tools, characteristics, and functions:

Plan review tools
Manual and automated contouring tools (Segmentation component for MR images)
DICOM connectivity
Windows operating system
Simulation
Support for a variety of beam modifiers (e.g. MLCs, blocks, etc.)
Standardized uptake value (SUV)
Specialty Image Creation (MIP, MinIP, and Avg)
Monaco dose and Monitor Unit (MU) calculation
Dose calculation algorithms for electron, photon, proton planning

Monaco is programmed using C, C++ and C# computer programming languages. Monaco runs on Windows operating system and off-the-shelf computer server/hardware.

AI/ML Overview

The provided FDA 510(k) clearance letter and summary for the Monaco RTP System (6.3) outlines the acceptance criteria and a study supporting the substantial equivalence of the new features. Here's a breakdown of the requested information:

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

Changed Feature	Acceptance Criteria	Reported Device Performance
Segmentation component for invoking MR auto-segmentation algorithms (AI-based)	Primary metric: Average Hausdorff Distance (AVD) ≤ 3 mm. Secondary metric (value of interest): DICE or AUC ≥ 0.7 for specific structures. Additionally, qualitative analysis based on a 5-point Likert scale to determine if automatically generated structures provide a valuable starting point for clinical delineation. Investigation of any failures to meet the DICE confidence value of 0.7, with findings included as "Limitations." Sub-group analysis based on patient size, pixel size, slice spacing, and number of slices.	For all evaluated structures across all models (Female Pelvis Intact & Hysterectomy, Male Pelvis, and Head & Neck), the mean Absolute Volume Difference (AVD) was less than 3 mm. Structure-specific statistical analyses supported this conclusion. Patterns of failure for any structure failing the DICE confidence value of 0.7 were investigated and included as "Limitations." Qualitative analysis concluded that automatically generated structures provided a valuable starting point for clinical delineation.
Auto-planning	All pre-defined acceptance criteria related to workflow performance, protocol management, plan creation, interoperability, and error handling must be met. Plans generated must be clinically acceptable for the intended use and not introduce new safety or effectiveness concerns.	All testing met pre-defined acceptance criteria. Treatment plans generated were reviewed within the clinical workflow and determined to be suitable for clinical use, without introducing new safety or effectiveness concerns.
Extending adaptive planning capabilities to EMLA for offline adaptive planning	Correct system behavior during image registration, structure propagation, dose recalculation/re-optimization, offline adaptive plan generation, and workflow execution under representative clinical scenarios. No defects, unexpected behavior, or data integrity issues. Plans generated must be clinically acceptable for the intended use. All predefined acceptance criteria for verification and validation must be met.	No defects, unexpected behavior, or data integrity issues were identified during testing. Validation demonstrated that offline adaptive planning using CT‑to‑CBCT supports the creation of clinically acceptable treatment plans for the intended use. Offline adaptive plans were reviewed within the clinical workflow and determined to be suitable for use. Verification and validation testing met pre-defined acceptance criteria.
Interoperability with 3rd party software for image management and contouring	Correct DICOM export functionality, preservation of data integrity, and successful creation of an offline adaptive plan using third-party contouring. Third-party contouring outputs must be clinically acceptable and comparable to reference contours produced by qualified users. All planned Solution Interoperability test cases successfully executed and passed. All verification and validation testing met predefined acceptance criteria.	All verification and validation testing met the predefined acceptance criteria. All planned Solution Interoperability test cases have been successfully executed and passed.

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

AI-based segmentation component:
- Female Pelvis Intact & Hysterectomy models: 529 images (joint image set).
- Male Pelvis model: 250 images.
- Head & Neck model: 1862 images.
Data Provenance: Not explicitly stated regarding country of origin or whether the data was retrospective or prospective.

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

AI-based segmentation component: "reference contours produced by qualified users" and "clinical delineation." The exact number or specific qualifications (e.g., radiologist with X years of experience) of these experts are not specified in the provided document.

4. Adjudication method for the test set

AI-based segmentation component: For the qualitative analysis, it states "a conclusion that the automatically generated structures provided a valuable starting point for clinical delineation." This implies human review and evaluation. However, a formal adjudication method like "2+1" or "3+1" is not explicitly mentioned.
For other features (Auto-planning, Adaptive planning, Interoperability), reviews mention evaluation within the "clinical workflow" and determination of "suitability for clinical use," but a specific adjudication method beyond internal reviews is not detailed.

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

A formal MRMC comparative effectiveness study to quantify human reader improvement with AI assistance is not mentioned in the provided text. The AI component was evaluated in a standalone manner for its segmentation accuracy, and qualitatively for its utility as a "starting point for clinical delineation."

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

Yes, for the AI-based segmentation component, a standalone algorithm-only performance evaluation was done using metrics like Average Hausdorff Distance (AVD), DICE, and AUC.

7. The type of ground truth used

For the AI-based segmentation component, the ground truth for the test set involved "reference contours produced by qualified users" and "clinical delineation." This implies expert consensus/delineation rather than pathology or outcomes data.
For other features, "clinically acceptable treatment plans" and "suitable for clinical use" imply evaluation against accepted clinical standards, likely by qualified personnel.

8. The sample size for the training set

The training set sample sizes are indicated for the AI-based segmentation models:
- Female Pelvis Intact & Hysterectomy: 529 images (joint image set used for training).
- Male Pelvis: 250 images (used for training).
- Head & Neck: 1862 images (used for training).

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

The document implies that the training data for the AI-based segmentation models would have been expertly annotated to establish the ground truth, given the mention of "reference contours produced by qualified users" for evaluation. However, the exact method for establishing ground truth for the training set is not explicitly detailed beyond this inference.

Ask a Question

Ask a specific question about this device

Page 1 of 1