Search Results

AdvantageSim™ MD is used to prepare geometric and anatomical data relating to a proposed external beam radiotherapy treatment prior to dosimetry planning. Anatomical volumes can be defined automatically or manually in three dimensions using a set of CT images acquired with the patient in the proposed treatment position. Definition of the anatomical volumes may be assisted by additional CT, MR or PET studies that have been co-registered with the planning CT scan. Additionally, CT & PET data from a respiratory tracked examination may be used to allow the user to define the target or treatment volume over a defined range of the respiratory cycle.

The geometric parameters of a proposed treatment field are selected to allow non-dosimetric, interactive optimization of field coverage. Defined anatomical structures and geometric treatments fields are displayed on transverse images, on reformatted sagittal, coronal or oblique images, on 3 D views created from the images, or on a beam eye's view display with or without the display of defined structures with or without the display of digitally reconstructed radiograph.

AdvantageSim™ MD is a CT/MR/PET oncology application used by clinicians (radiologist, radiation oncologist, medical oncologist nuclear medicine physicians and trained healthcare professional) to assist treatment planning.

AdvantageSim MD with MR pelvic organ at risk segmentation Option is used to provide MR based prostate and pelvic organs-at-risk segmentation. A suite of semi-automated MR based organ segmentation contouring allows generating complex structures around organs at risk. These contours overlay on the co-registered CT planning image.

The segmentation methods in the modified device are semi-automatic. The user has to place seed points to identify an inner point of the organ to contour.

The software offers a suite of manual contour editing tools enabling the user to edit, modify, or change contours generated from the MR segmentation tools to their desired configuration based on their medical and clinical knowledge and experience. The results provided by the software needs to be approved by the experienced clinician and can always be modified or corrected by him/her. It is up to the expert user to accept the result without any change, reject it completely and delineate manually, or modify the result and then save it. The software does not provide any auto-detection or auto-saving functionalities.

Same as the predicate devices, the clinician retains the ultimate responsibility for making the pertinent diagnosis and patient management decisions based on their standard practices and visual comparison of the individual images, regardless of the accuracy of the output generated by the software.

Here's an analysis of the provided text to fulfill your request:

Acceptance Criteria and Study for GE Healthcare AdvantageSim™ MD with MR pelvic organ at risk segmentation Option

1. Table of Acceptance Criteria and Reported Device Performance:

Important Note: The document focuses on demonstrating substantial equivalence to predicate devices rather than providing specific numerical acceptance criteria and performance metrics (e.g., Dice coefficients, Hausdorff distances, specific time savings). The reported performance is generally qualitative or comparative.

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

• Sample Size for Test Set: Not explicitly stated. The document mentions "consented clinical images" but does not specify the number of cases.
• Data Provenance: "consented clinical images" - the country of origin is not specified, but the submission is from GE Hungary Kft. The study appears to be retrospective as it uses existing clinical images.

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

• Number of Experts: Three.
• Qualifications of Experts: "board certified Radiation Oncologists who were considered experts."

4. Adjudication Method for the Test Set:

• The document does not explicitly state a formal adjudication method (e.g., 2+1, 3+1). It describes the experts assessing accuracy, precision, and efficiency, and providing qualitative feedback. It implies each expert evaluated the software's performance, but not how disagreements were resolved to establish a single ground truth.

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

• The study described is a usability study that compared the new software against manual methods (implied through efficiency and inter-operator variability assessment). It involved "three board certified Radiation Oncologists". While it involved multiple readers, it is not explicitly labeled as an "MRMC comparative effectiveness study" in the sense of a formal statistical study with defined effect sizes of improvement with AI assistance.
• Effect Size of Human Reader Improvement: Not quantitatively reported. The document states it has "the potential to reduce inter-operator variability" and provides "statistically significant and practically meaningful clinical efficiency improvements," but no numerical effect size is given.

6. Standalone Performance Study:

• Yes, a standalone performance was performed. The device's segmentation methods are described as "semi-automatic" where "the user has to place seed points to identify an inner point of the organ to contour." The software then generates contours. The study assessed the software's output in terms of accuracy, precision, and efficiency, even though a clinician would typically review and edit the results. The clinicians evaluated the device's output and how it facilitated their workflow.

7. Type of Ground Truth Used:

• The ground truth for the test set was established by expert consensus/opinion among the three board-certified Radiation Oncologists. They likely compared the device's segmentations against their clinical knowledge and potentially manual segmentations, though this is not explicitly detailed.

8. Sample Size for the Training Set:

• Not specified. The document does not provide any information about the training data or its size.

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

• Not specified. As the training set size and details are absent, the method for establishing its ground truth is also not mentioned.

Ask a specific question about this device