Parkinson's disease diagnosing apparatus and method
Inventors
Shin, Dong Hoon • HEO, Hwan • KIM, Eung Yeop • SUNG, Young Hee
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11016160-B2
Publication Date
2021-05-25
Expiration Date
Abstract
Disclosed are Parkinson's disease diagnosing apparatus and method and a configuration which includes an image acquiring unit which acquires a multi-echo magnitude and a phase image from MRI obtained by capturing a brain of a patient, an image processing unit which post-processes only substantia nigra and a nigrosome-1 region proposed as an imaging biomarker of the Parkinson's disease from the acquired image to be observed; an image analyzing unit which classifies images including the nigrosome-1 region by analyzing the processed images and detects the nigrosome-1 region from the classified image, and a diagnosing unit which determines whether the nigrosome-1 region is normal in the classified image to diagnose the Parkinson's disease is provided so that only the image which includes the nigrosome-1 region is classified in the MRI and the nigrosome-1 region is analyzed from the classified image to diagnose the Parkinson's disease.
Core Innovation
The invention is an apparatus for detecting Parkinson’s disease that uses magnetic resonance imaging (MRI) to acquire a plurality of multi-echo magnitude and phase images from a patient’s brain. The acquired magnitude and phase information is post-processed to focus on a substantia nigra and a nigrosome-1 region, which are imaging biomarkers of Parkinson’s disease. Processed representations are generated that include frequency images derived from the acquired phase images, and processed frequency images in which background phase is removed using a Laplacian operator.
The invention further applies a quantitative susceptibility map mask to the processed frequency images based on a quantitative susceptibility mapping algorithm to visualize the nigrosome-1 region. A QSM mask is used to form SMWI (susceptibility map-weighted imaging) by combining the QSM processing output with multi-echo magnitude information, thereby improving visualization of the nigrosome-1 region for subsequent analysis.
The invention analyzes the processed images with machine learning to classify images based on whether an image includes the nigrosome-1 region, and then detects the nigrosome-1 region in images classified as including it. Using an analysis of the detected nigrosome-1 region performed using machine learning, the apparatus determines whether the nigrosome-1 region is normal according to a correlation between concentration of iron in the patient’s brain and susceptibility to Parkinson’s disease.
Claims Coverage
The independent claim clm-00001 defines a Parkinson’s disease detecting apparatus that combines multi-echo MRI acquisition, QSM-related preprocessing focused on substantia nigra/nigrosome-1, and machine-learning-based determination of whether the detected nigrosome-1 region is normal. It includes three main inventive feature groupings: (i) multi-echo MRI acquisition and QSM-focused post-processing, (ii) machine-learning classification and nigrosome-1 region detection, and (iii) ML-based normal/abnormal determination based on an iron–Parkinson’s susceptibility correlation. No other independent claims are explicitly provided in the supplied claim list.
Multi-echo MRI acquisition and substantia nigra/nigrosome-1 focused post-processing
Remove portions of the acquired multi-echo magnitude and phase images other than a substantia nigra and a nigrosome-1 region; generate frequency images from the acquired phase images; generate processed frequency images by removing a background phase using a Laplacian operator.
Quantitative susceptibility map mask applied for visualizing nigrosome-1 region
Apply a quantitative susceptibility map mask to the processed frequency images based on a quantitative susceptibility mapping algorithm for visualizing the nigrosome-1 region.
Machine-learning classification and detection of nigrosome-1 region
Analyze the processed images to classify each processed image based on whether an image includes the nigrosome-1 region; detect the nigrosome-1 region in the images classified as including the nigrosome-1 region, according to an analysis performed using machine learning.
ML-based normality determination using iron–Parkinson’s susceptibility correlation
Determine whether the nigrosome-1 region is normal in each image classified as including the nigrosome-1 region, according to a correlation between concentration of iron in the patient’s brain and susceptibility to Parkinson’s disease, based on an analysis of the nigrosome-1 region performed using machine learning.
Overall claim coverage centers on transforming multi-echo magnitude and phase MRI into QSM-mask-based representations for visualizing and detecting the nigrosome-1 region, followed by machine-learning classification and determination of whether the nigrosome-1 region is normal using an iron concentration–Parkinson’s susceptibility correlation.
Stated Advantages
Improved nigrosome-1 visibility enabling more precise diagnosis using commonly available 3T MRI and susceptibility-based correlation to brain iron.
Documented Applications
Diagnosing Parkinson’s disease by detecting and analyzing the nigrosome-1 region using QSM processing and machine learning, with determination of whether the nigrosome-1 region is normal.
Interested in licensing this patent?