Apparatus and method for extracting vascular function from brain-related information
Inventors
Park, Gyu Ha • Kim, Dohyun • Song, Soohwa
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12026883-B1
Publication Date
2024-07-02
Expiration Date
Abstract
An aspect of the present disclosure provides an apparatus for extracting a vascular function including an information reception unit configured to extract an original CT image from brain-related information received from the outside; an NIFTI image transformation unit configured to transform the original CT image into an NIFTI file format image to acquire time sequence data; a time interpolation unit configured to apply time interpolation to the original CT image through the time sequence data to transform the original CT image into each time-specific 3D CT image; a vessel segmentation unit configured to predict a vessel segmentation mask by passing the each time-specific 3D CT image through a deep learning-based vessel segmentation deep-learning model 141 and generate a 4D vessel mask image by stacking the 3D CT images based on a time axis; and a vascular function extraction unit configured to extract a vascular function from a vessel region of the 4D vessel mask image and calculate a blood flow parameter using an artery function which is one of the vascular functions.
Core Innovation
The disclosed invention extracts a vascular function from brain-related information by using an original CT image received from outside. The original CT image is transformed into a neuroimaging informatics technology initiative (NIFTI) file format to acquire time sequence data, and time interpolation is applied to produce each time-specific 3D CT image.
Vessels are segmented by passing each time-specific 3D CT image through a deep learning-based vessel segmentation deep-learning model to generate a vessel segmentation mask. A 4D vessel mask image is generated by stacking the 3D CT images based on a time axis, thereby representing vessel information over time.
A vascular function is extracted from a vessel region of the 4D vessel mask image, and a blood flow parameter is calculated using an artery function as one of the vascular functions. The described problem is acquiring vascular functions and blood-flow parameters from brain-related CT data by forming time-specific vessel representations and deriving vascular function from the vessel region.
Claims Coverage
The document includes two independent claims (apparatus and method), each centered on extracting a vascular function from brain-related information by converting brain-related CT into time-specific 3D CT images, segmenting vessels with a deep learning model to form a time-stacked 4D vessel mask, and computing a blood-flow parameter from an artery function.
Receiving brain-related CT image and extracting vascular function
An information reception unit configured to extract an original CT image from the brain-related information received from the outside, and a vascular function extraction unit configured to extract a vascular function from a vessel region of the 4D vessel mask image and calculate a blood flow parameter using an artery function which is one of the vascular functions.
NIFTI transformation and time interpolation to form time-specific 3D CT images
An NIFTI image transformation unit configured to transform the original CT image into a neuroimaging informatics technology initiative (NIFTI) file format image to acquire time sequence data; a time interpolation unit configured to apply time interpolation to the original CT image through the time sequence data to transform the original CT image into each time-specific 3D CT image.
Deep learning vessel segmentation and 4D vessel mask generation
A vessel segmentation unit configured to predict a vessel segmentation mask by passing the each time-specific 3D CT image through a deep learning-based vessel segmentation deep-learning model and generate a 4D vessel mask image by stacking the 3D CT images based on a time axis.
Method workflow for extracting vascular function from CT-based time sequence
A method comprising extracting an original CT image, transforming the original CT image into a NIFTI file format image to acquire time sequence data, applying time interpolation to transform the original CT image into each time-specific 3D CT image, predicting a vessel segmentation mask by passing each time-specific 3D CT image through a deep learning-based vessel segmentation deep-learning model and generating a 4D vessel mask image by stacking the 3D CT images based on a time axis, and extracting a vascular function from a vessel region of the 4D vessel mask image and calculating a blood flow parameter using an artery function which is one of the vascular functions.
Across the independent claims, the core coverage is the end-to-end pipeline that converts an original CT image into NIFTI time-sequence data, generates time-specific 3D CT images via time interpolation, uses a deep learning-based vessel segmentation model to create a time-stacked 4D vessel mask, and then extracts a vascular function and computes a blood-flow parameter using an artery function.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?