18033434. DETECTION OF SPINE VERTEBRAE IN IMAGE DATA simplified abstract (KONINKLIJKE PHILIPS N.V.)

From WikiPatents
Jump to navigation Jump to search

DETECTION OF SPINE VERTEBRAE IN IMAGE DATA

Organization Name

KONINKLIJKE PHILIPS N.V.

Inventor(s)

Amir Yaakobi of RA'ANANA (IL)

Ohad Silbert of RA'ANANA (IL)

Guy Engelhard of RA'ANANA (IL)

DETECTION OF SPINE VERTEBRAE IN IMAGE DATA - A simplified explanation of the abstract

This abstract first appeared for US patent application 18033434 titled 'DETECTION OF SPINE VERTEBRAE IN IMAGE DATA

Simplified Explanation

The patent application describes a method for detecting vertebrae in volumetric images of the spine using artificial intelligence. Here are the key points:

  • The method uses a trained neural network to detect individual vertebrae in sagittal images of the spine.
  • Two-dimensional bounding boxes are created around the detected vertebrae and combined to generate a three-dimensional model of the spine.
  • A panoramic image of the spine is generated based on the three-dimensional model, providing a straightened view of the spine.
  • The trained neural network is then used to detect individual vertebrae in the panoramic image.
  • Two-dimensional bounding boxes around the detected vertebrae in the panoramic image are translated to three-dimensional space, creating three-dimensional image data with three-dimensional bounding boxes.

Potential applications of this technology:

  • Medical imaging: The method can be used in medical imaging systems to automatically detect and analyze vertebrae in volumetric images of the spine.
  • Spinal surgery planning: The three-dimensional model of the spine generated by the method can assist surgeons in planning spinal surgeries by providing accurate information about the location and structure of the vertebrae.

Problems solved by this technology:

  • Manual detection: The method eliminates the need for manual detection of vertebrae in volumetric images, saving time and reducing the risk of human error.
  • Straightened view: The panoramic image generated by the method provides a straightened view of the spine, making it easier to analyze and diagnose spinal conditions.

Benefits of this technology:

  • Efficiency: The automated detection of vertebrae in volumetric images speeds up the analysis process, allowing for quicker diagnosis and treatment planning.
  • Accuracy: The trained neural network improves the accuracy of vertebrae detection, reducing the chance of misdiagnosis or missed abnormalities.
  • Visualization: The three-dimensional model and panoramic image provide a clear and detailed visualization of the spine, aiding in surgical planning and patient education.


Original Abstract Submitted

Vertebrae of the spine in volumetric image are detected using multi-stage detection with trained artificial intelligence. In one embodiment, a trained neural network () is employed in a first stage to detect individual vertebra in sagittal images. Two-dimensional bounding boxes around the detected vertebrae are combined to generate a three-dimensional model of the spine. A panoramic image of the spine is generated based on the three-dimensional model to create a straightened view of the spine. The trained neural network is employed in a second stage to detect individual vertebra in the panoramic image. Two-dimensional bounding boxes around the detected vertebrae in the panoramic image are translated to three-dimensional space to create three-dimensional image data with three-dimensional bounding boxes.

Retrieved from "http://wikipatents.org/index.php?title=18033434._DETECTION_OF_SPINE_VERTEBRAE_IN_IMAGE_DATA_simplified_abstract_(KONINKLIJKE_PHILIPS_N.V.)&oldid=18633"