AI Case Study

Researchers in South Korea demonstrate accuracy of 98.8% in diagnosing Parkinson's disease using convoluted neural networks

Researchers in South Korea have developed a deep learning-based interpretation system to refine the imaging diagnosis of Parkinson's disease. This has resulted in high classification accuracy comparable with the experts' evaluation referring quantification results.


Public And Social Sector

Education And Academia

Project Overview

"Parkinson's disease (PD) is diagnosed using dopamine transporter imaging such as FP-CIT SPECT. Until now, imaging interpreted by human has resulted in inconsistent diagnosis. Researchers in S.Korea have developed a deep learning-based FP-CIT SPECT interpretation system to refine the imaging diagnosis of Parkinson's disease. This system trained by SPECT images of PD patients and normal controls shows high classification accuracy comparable with the experts' evaluation referring quantification results. In addition, some patients clinically diagnosed as PD who have scans without evidence of dopaminergic deficit (SWEDD), an atypical subgroup of PD, could be reclassified by the new automated system. It could help imaging diagnosis of patients with uncertain Parkinsonism and provide objective patient group classification, particularly for SWEDD, in further clinical studies."

Reported Results

Using an independent dataset for evaluation, PD Net demonstrated scores of 98.6% (sensitivity), 100% (specificity), and 98.8% (accuracy) for disriminating Parkinson's disease. Furthermore, "ROC analysis revealed a trend of higher AUC value of PD Net than that of quantitative analysis using putaminal BR (0.997 ± 0.003 for PD Net and 0.968 ± 0.017 for putaminal BR; p = 0.081)."


"Deep convolutional neural network framework (PD Net) for interpretation of FP-CIT SPECT images. A FP-CIT SPECT volume with matrix size 91 × 109 × 91 is used for an input matrix of PD Net. It consists of multiple 3-dimensional convolutional layers which learn image features from training data. Each convolutional layer is followed by ReLU activation function and max-pooling layers subsample images. The final output of PD Net has two nodes, which respectively correspond to Parkinson's disease and normal control. Parameters of convolutional layers of PD Net were learned by training SPECT dataset to discriminate SPECT images of Parkinson's disease from those of normal controls. The accuracy of the classification was measured from two independent test datasets. Two expert readers interpreted same image data blinded to diagnosis. The accuracy of PD Net and the readers was compared. In addition, the classification using PD Net was tested in Parkinson's disease patients who have scans without evidence of dopaminergic deficit (SWEDD) whether PD Net interpreted those images as normal scans."


R And D

Core Research And Development


"In this study, we aimed to develop an automated FP-CIT SPECT interpretation system based on deep learning for the objective diagnosis. Recent development of deep learning is changing a variety of scientific and industrial fields. Deep convolutional neural networks (CNN), a type of deep learning, have dramatically improved the performance in image classification and detection. Recently, deep learning techniques have started to be applied to medical images for segmentation, lesion-detection, and disease classification. Our objective in terms of clinical application was to discriminate PD among patients with uncertain Parkinsonism. In this study, the system was developed using Parkinson's Progression Markers Initiative (PPMI) database. It was further validated in an independent data acquired from Seoul National University Hospital (SNUH) that consists of patients with PD and nonparkinsonian tremor."



"Data used in the preparation of this article were obtained from two different cohorts, the PPMI database ( and SNUH cohort. The subjects of the PPMI cohort in this study consisted of 431 patients with PD, 193 normal controls (NCs) and 77 patients with SWEDD. PD patients and NCs were divided into two datasets, training/validation set and test set, to develop the CNN and test its accuracy. Training/validation set consisted of 549 subjects (379 PD and 170 NCs). 75 subjects (52 PD and 23 NCs) were included in the PPMI test set to evaluate the accuracy of our framework. Training and test sets were randomly selected from the PPMI cohort. The two sets were divided so that the ratio between PD and NC was the same. SNUH cohort was applied as an independent test set from the training data. SNUH cohort included 82 patients initially suspected of PD who underwent FP-CIT SPECT from Mar 2014 to Sep 2016. FP-CIT SPECT scans were acquired to determine treatment plan and obtain accurate diagnosis."