Artificial intelligence based Parkinson's disease diagnostic device and method

摘要

PROBLEM TO BE SOLVED: To provide a device and method for diagnosing Parkinson's disease based on artificial intelligence. An artificial intelligence-based Parkinson's disease diagnostic apparatus according to one aspect of the present invention acquires a first image associated with the size and phase of a multi-echo from an MRI of a brain of a patient. Image acquisition unit; Image processing unit that post-processes the acquired first image so that the substantia nigra and nigrosome 1 region used as an image biomarker for Parkinson's disease can be observed; the post-processed first An image analysis unit that analyzes the image to classify the second image including the nigrosome 1 region, and detects the nigrosome 1 region from the classified second image; and the detected nigrosome 1 region is normal. And a diagnosis unit for diagnosing the presence or absence of Parkinson's disease in the patient, the image processing unit based on a quantitative magnetic susceptibility mapping algorithm. By applying a susceptibility map mask to generate a susceptibility map weighted imaging image, the post-processing is performed, the image processing unit, with respect to the generated susceptibility map weighted imaging image, angle adjustment, At least one operation of image enlargement and reslice may be further performed. [Selection diagram] Figure 2