Automatic Transcranial Sonography-Based Classification of Parkinson's Disease Using a Novel Dual-Channel CNXV2-DANet

Abstract

Transcranial sonography (TCS) has been introduced to assess hyper-echogenicity in the substantia nigra of the midbrain for Parkinson's disease (PD); however, its subjective and resource-demanding nature has impeded its widespread application. An AI-empowered TCS-based PD classification tool is greatly demanding, yet relevant research is severely scarce. Therefore, we proposed a novel dual-channel CNXV2-DANet for TCS-based PD classification using a large cohort. A total of 1176 TCS images from 588 subjects were retrospectively enrolled from Beijing Tiantan Hospital, encompassing both the left and right side of the midbrain for each subject. The entire dataset was divided into a training/validation/testing set at a ratio of 70%/15%/15%. Development of the proposed CNXV2-DANet was performed on the training set with comparisons between the single-channel and dual-channel input settings; model evaluation was conducted on the independent testing set. The proposed dual-channel CNXV2-DANet was compared against three state-of-the-art networks (ConvNeXtV2, ConvNeXt, Swin Transformer). The results demonstrated that both CNXV2-DANet and ConvNeXt V2 performed more superiorly under dual-channel inputs than the single-channel input. The dual-channel CNXV2-DANet outperformed the single-channel, achieving superior average metrics for accuracy (0.839 ± 0.028), precision (0.849 ± 0.014), recall (0.845 ± 0.043), F1-score (0.820 ± 0.038), and AUC (0.906 ± 0.013) compared with the single channel metrics for accuracy (0.784 ± 0.037), precision (0.817 ± 0.090), recall (0.748 ± 0.093), F1-score (0.773 ± 0.037), and AUC (0.861 ± 0.047). Furthermore, the dual-channel CNXV2-DANet outperformed all other networks (all p-values < 0.001). These findings suggest that the proposed dual-channel CNXV2-DANet may provide the community with an AI-empowered TCS-based tool for PD assessment.

Keywords: Parkinson’s disease; auto-classification; deep learning; transcranial sonography.

Figure 1

A schematic diagram of the pre-processing approaches for the single-channel input images and dual-channel input images.

Figure 2

The DANet structure.

Figure 3

The architecture of CNXV2-DANet.

Figure 4

Classification results of CNXV2-DANet and ConvNeXt V2 on the testing set for single-channel and dual-channel methods: (a) confusion matrix and (b) ROC curve.

Figure 5

Comparison of the performance of the four studied models on the testing dataset (a) in terms of the averaged metrics of accuracy, precision, recall, and F1-score with the corresponding standard deviations across the 5 randomizations, and (b) in terms of ROC curves under one of the randomization seeds.