Prediction of Parkinson’s disease by transcranial sonography-based deep learning

• Published in: Neurological sciences 2024-06, Vol.45 (6), p.2641-2650
• Main Authors: Ding, Chang Wei, Ren, Ya Kun, Wang, Cai Shan, Zhang, Ying Chun, Zhang, Ying, Yang, Min, Mao, Pan, Sheng, Yu Jing, Chen, Xiao Fang, Liu, Chun Feng
• Format: Article
• Language: English
• Subjects: Accuracy; Age differences; Datasets; Deep learning; Medicine; Medicine & Public Health; Movement disorders; Neural networks; Neurodegenerative diseases; Neuroimaging; Neurology; Neuroradiology; Neurosurgery; Original Article; Parkinson's disease; Psychiatry; Ultrasonic imaging
• ISSN: 1590-1874; 1590-3478
• DOI: 10.1007/s10072-023-07154-4

Objectives Transcranial sonography has been used as a valid neuroimaging tool to diagnose Parkinson’s disease (PD). This study aimed to develop a modified transcranial sonography (TCS) technique based on a deep convolutional neural network (DCNN) model to predict Parkinson’s disease. Methods This retrospective diagnostic study was conducted using 1529 transcranial sonography images collected from 854 patients with PD and 775 normal controls admitted to the Second Affiliated Hospital of Soochow University (Suzhou, Jiangsu, China) between September 2019 and May 2022. The data set was divided into training cohorts (570 PD patients and 541 normal controls), and the validation set (184 PD patients and 234 normal controls). Using these datasets, we developed four different DCNN models (ResNet18, ResNet50, ResNet152, and DenseNet121). We then assessed their diagnostic performance, including the area under the receiver operating characteristic (AUROC) curve, specificity, sensitivity, positive predictive value (PPV), negative predictive value (NPV), and F1 score and compared with traditional diagnostic criteria. Results Among the 1529 TCS images, 570 PD patients and 541 normal controls from 4 of 6 sonographers of the TCS team were selected as the training cohort, and 184 PD patients and 234 normal controls from the other 2 sonographers were chosen as the validation cohort. There were no sex and age differences between PD patients and normal control subjects in the training and validation cohorts ( P values > 0.05). All DCNN models achieved good performance in distinguishing PD patients from normal control subjects on the validation datasets, with diagnostic AUROCs and accuracy of 0.949 (95% CI 0.925, 0.965) and 86.60 for the RestNet18 model, 0.949 (95% CI 0.929, 0.971) and 87.56 for ResNet50, 0.945 (95% CI 0.931, 0.969) and 88.04 for ResNet152, 0.953 (95% CI 0.935, 0.971) and 87.80 for DenseNet121, respectively. On the other hand, the diagnostic accuracy of the traditional diagnostic method was 82.30. The accuracy of all DCNN models was higher than that of traditional diagnostic method. Moreover, the 5k-fold cross-validation results in train datasets showed that these DCNN models are robust. Conclusion The developed transcranial sonography-based DCNN models performed better than traditional diagnostic criteria, thus improving the sonographer’s accuracy in diagnosing PD.