An apparatus for diagnosing Parkinson''s disease based on artificial intelligence, which is an aspect of the present invention, includes an image acquisition unit that acquires a first image related to a multi-echo size and phase from an MRI of a patient''s brain； An image processing unit for post-processing the acquired first image to enable observation of the nigrosome 1 region and black matter used as image biomarkers of Parkinson''s disease； An image analysis unit that analyzes the post-processed first image to classify a second image including the nigrosome 1 region, and detects the nigrosome 1 region from the classified second image； And a diagnostic unit for diagnosing the presence of Parkinson''s disease in the patient by analyzing whether the detected Nygrosome 1 region is normal, wherein the image processing unit includes, based on a quantitative susceptibility mapping algorithm, to the first image. By applying a quantitative susceptibility map mask to generate a susceptibility map weighted imaging image, the post-processing is performed, and the image processing unit adjusts the angle, enlarges and reslices the image on the generated susceptibility map weighted imaging image. At least one of the operations may be further performed, and the diagnosis unit generates a plurality of learning models for diagnosing the presence or absence of Parkinson''s disease based on the same data set, and the detected Nygrosome 1 Based on the region, a plurality of prediction results by the plurality of learning models may be derived, and the presence or absence of Parkinson''s disease of the patient may be diagnosed based on the plurality of prediction results.본 발명의 일 양상인 인공지능 기반 파킨슨 병 진단 장치는, 환자의 뇌를 촬영한 MRI로부터, 멀티 에코(multi echo) 크기 및 위상과 관련된 제 1 영상을 획득하는 영상 획득부； 파킨슨 병의 영상 바이오 마커로 이용되는 흑질과 나이그로좀 1 영역의 관찰이 가능하도록, 상기 획득한 제 1 영상을 후처리하는 영상 처리부； 상기 후처리된 제 1 영상을 분석하여 상기 나이그로좀 1 영역이 포함된 제 2 영상을 분류하고, 상기 분류된 제 2 영상으로부터 상기 나이그로좀 1 영역을 검출하는 영상 분석부； 및 상기 검출된 나이그로좀 1 영역의 정상 여부를 분석하여,
