Search Results

The Precise Position is intended for use with Philips Incisive CT systems. The following guided workflow.

• Patient orientation identification
• Surview range recommendation
• Automatic centering the patient anatomy
• Provide visual images of patient on the table

Precise position is indicated for use for CT imaging of the head, chest, abdomen, pelvis, and combination of those anatomies.

Patient population limitation: Patient younger than 16 years are not supported.

Precise Position is an optional feature to assist user for position the patient before the body examination such as CT scan. The purpose of this feature is to reduce the patient position time via the camera detection and calculation result. It includes automatic detect patient orientation, patient anatomy scan range and center of patient anatomy.

Precise Position including a camera with both color and depth function is installed in the ceiling of the scan room, in such a way to cover the entire patient on the patient table. The camera control and image data transmit via the high speed fiber and copper hybrid USB cable. The power supply of the camera is from the gantry. Precise position adopts the AI algorithm (Convolution Neural Network) to detect the joints of the patient body, and then identify surview start/end position and patient orientation. The algorithm can also support detect center of patient anatomy.

Limitation for Precise Position
There is no limitation for Precise Position except below items:
• Patients below the age of 16 are not supported.
• Decubitus orientations are not supported.

The Precise Position display results may get affected by the following conditions:
• When the patient is covered by sheet, blanket etc.,
• When the patient is not completely covered by the ceiling camera view, e.g. blocked by the gantry or out of camera's FOV etc.
• When the patient is wearing clothes that reflects light, e.g. plastic-like clothes.
• When the patient is wearing black clothes.
• When the patient is wearing thick clothes.
• When there are other people around the patient.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Total 80 clinical scan positions.
  • 40 cases used with Precise Position.
  • 40 cases without the usage of Precise Position.
• Data Provenance: The document does not explicitly state the country of origin for the data or if it was retrospective or prospective. However, it mentions a "clinical evaluation… done by 5 Clinical experts" and volunteers not receiving radiation, implying a prospective study conducted for the purpose of this evaluation. The manufacturer is Philips Healthcare (Suzhou) Co., Ltd., which suggests the study likely occurred in China.

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

• Number of Experts: 5 Clinical experts.
• Qualifications: The specific qualifications (e.g., number of years of experience, specific specialty like "radiologist") are not explicitly stated beyond "Clinical experts."

4. Adjudication Method for the Test Set

• The document does not specify an explicit adjudication method (e.g., 2+1, 3+1). It states that the "thorough clinical evaluation of this feature is done by 5 Clinical experts," implying they collectively contributed to the evaluation, but the exact consensus or adjudication process is not detailed.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size

• This was not a typical MRMC comparative effectiveness study in the sense of multiple readers interpreting cases with and without AI.
• Instead, it was a comparative study on operational efficiency and positioning accuracy. It compared:
  • Time taken for patient positioning by users with and without the Precise Position feature.
  • Accuracy of vertical (iso)center positioning by users with and without the Precise Position feature.
  • Consistency (standard deviation) of positioning by users with and without the Precise Position feature.
• Effect Size (Human Improvement with AI):
  • Time Reduction: Users achieved up to 23% time reduction in patient positioning with the "Precise Positioning workflow" (which includes the AI).
  • Vertical Position Accuracy: Users achieved an increase of up to 50% in vertical position accuracy with "Precise Position."
  • Positioning Consistency (Vertical and Horizontal): Users achieved an increase of up to 70% in consistency with "Precise Position."
    These metrics indicate the improvement in human operators' performance when assisted by the AI-powered Precise Position device.

6. If a Standalone (Algorithm Only) Performance Study Was Done

• The document does not explicitly state whether a standalone (algorithm only, without human-in-the-loop) performance study was conducted for the AI component of the Precise Position device. The clinical evaluation focuses on the human-with-AI system performance. The AI algorithm (Convolution Neural Network) is described as being used to detect joints and then determine positioning parameters, suggesting its performance is evaluated as part of the overall integrated system.

7. The Type of Ground Truth Used

• For the clinical evaluation, the ground truth for measuring time, accuracy, and consistency appears to be based on:
  • Direct measurements of time taken for positioning.
  • Measurements of offset in mm for vertical (iso) center position.
  • Standard deviation calculations for vertical (iso)center positioning and surview (horizontal) start position.
  • These measurements were likely compared against an ideal or intended positioning, which would be implicitly defined by the CT system's requirements and presumably verified by the clinical experts. It's not "pathology," "outcomes data," or a direct "expert consensus" on disease presence/absence, but rather a consensus on the correctness and optimal nature of the patient positioning parameters established by the device.

8. The Sample Size for the Training Set

• The document does not provide the sample size for the training set used for the AI algorithm (Convolution Neural Network). It only discusses the test set used for validating the combined human-AI system.

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

• The document does not describe how the ground truth for the training set of the AI algorithm was established. It only mentions that the AI algorithm (Convolution Neural Network) is used to detect "joints of the patient body" to then identify surview start/end position and patient orientation, and support detection of the center of patient anatomy. This implies annotation of patient body parts and anatomical landmarks in imaging data for training purposes, but specific details on its establishment are not provided.

Ask a specific question about this device