Search Results

EFAI HNSeg is a software device intended to assist trained radiation oncology professionals, including, but not limited to, radiation oncologists, medical physicists, and dosimetrists, during their clinical workflows of radiation therapy treatment planning by providing initial contours of organs at risk in the head and neck region on non-contrast CT images. EFAI HNSeg is intended to be used on adult patients only.

The contours are generated by deep-learning algorithms and then transferred to radiation therapy treatment planning systems. EFAI HNSeg must be used in conjunction with a DICOM-compliant treatment planning system to review and edit results generated. EFAI HNSeg is not intended to be used for decision making or to detect lesions.

EFAI HNSeg is an adjunct tool and is not intended to replace a clinician's judgment and manual contouring of the normal organs on CT. Clinicians must not use the software generated output alone without review as the primary interpretation.

EFAI RTSuite CT HN-Segmentation System, herein referred to as EFAI HNSeg, is a standalone software that is designed to be used by trained radiation oncology professionals to automatically delineate head-and-neck organs-at-risk (OARs) on CT images. This auto-contouring of OARs is intended to facilitate radiation therapy workflows.

The device receives CT images in DICOM format as input and automatically generates the contours of OARs, which are stored in DICOM format and in RTSTRUCT modality. The device does not offer a user interface and must be used in conjunction with a DICOM-compliant treatment planning system to review and edit results. Once data is routed to EFAI HNSeg, the data will be processed and no user interaction is required, nor provided.

The deployment environment is recommended to be in a local network with an existing hospitalgrade IT system in place. EFAI HNSeg should be installed on a specialized server supporting deep learning processing. The configurations are only being operated by the manufacturer:

• Local network setting of input and output destinations;
• Presentation of labels and their color;
• Processed image management and output (RTSTRUCT) file management.

Here is a summary of the acceptance criteria and study information for the EFAI RTSuite CT HN-Segmentation System based on the provided document:

Acceptance Criteria and Reported Device Performance

Study Information

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

   • Test Set Size: Not explicitly stated in the provided text.
   • Data Provenance: Not explicitly stated in the provided text (e.g., country of origin, retrospective or prospective).

2. Number of experts used to establish the ground truth for the test set and their qualifications: Not explicitly stated in the provided text for the test set.

3. Adjudication method for the test set: Not explicitly stated in the provided text.

4. Multi-Reader Multi-Case (MRMC) comparative effectiveness study: No, an MRMC study was not conducted. The study was a "non-inferiority standalone performance test" comparing the device's output to a predicate device. It did not involve comparing human readers with and without AI assistance to determine an effect size.

5. Standalone performance study: Yes, a standalone performance test was done. The document states: "To establish the contour performance of EFAI HNSeg, a non-inferiority standalone performance test was performed." This study compared the device's automatically generated contours against those of a predicate device.

6. Type of ground truth used: The ground truth for contour performance, though not explicitly detailed in its establishment, was used to compare against the device's output and the predicate device's output. Given the context of segmenting "organs at risk," it can be inferred that the ground truth would typically be expert-annotated contours. The comparison was specifically against the performance of a legally marketed predicate device (AccuContour™) which itself would have established its own performance against a form of ground truth or clinical standard.

7. Sample size for the training set: Not explicitly stated in the provided text.

8. How the ground truth for the training set was established: Not explicitly stated in the provided text. However, for deep learning models like EFAI HNSeg, training set ground truth for segmentation would typically be established through expert manual contouring of OARs on CT images by qualified professionals (e.g., radiation oncologists, medical physicists, dosimetrists).

Ask a specific question about this device