Using an artificial intelligence-based Parkinson's disease diagnosis apparatus including an image acquisition unit, an image processing unit, an image analysis unit, a diagnosis unit, and a central management unit, which is an aspect of the present invention, the probability of successful clinical trials is determined by selecting a group of patients with Parkinson's disease. In the method of increasing, the image acquisition unit acquires a plurality of first images related to the size and phase of a multi-echo from MRI photographing the brains of a plurality of patients who are candidates for a clinical trial experiment for proving drug efficacy. Level 1; A second step of post-processing the acquired plurality of first images by the image processing unit to enable observation of the nigrosome 1 region and the black matter used as image biomarkers of Parkinson's disease; A third step of classifying a plurality of second images including the nigrosome 1 region by analyzing the plurality of post-processed first images by the image analysis unit; A fourth step of detecting, by the image analysis unit, the nigrosome 1 region from the classified second images; A fifth step of providing information on the detected Nygrosome 1 region to the diagnosis unit in order to diagnose the presence or absence of Parkinson's disease in the patient; A sixth step of receiving, by the central management unit, information on at least one first patient with Parkinson's disease among the plurality of patients from the diagnosis unit; And a seventh step in which the central management unit proves the efficacy of the drug on the basis of a clinical trial on the first patient. It may include.
展开▼
