Kang Hongyu, Wang Xinyi, Sun Yu, Li Shuai, Sun Xin, Li Fangxian, Hou Chao, Lam Sai-Kit, Zhang Wei, Zheng Yong-Ping
Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China.
Research Institute of Smart Ageing, The Hong Kong Polytechnic University, Hong Kong SAR, China.
Bioengineering (Basel). 2024 Aug 31;11(9):889. doi: 10.3390/bioengineering11090889.
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), 1-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), 1-score (0.773 ± 0.037), and AUC (0.861 ± 0.047). Furthermore, the dual-channel CNXV2-DANet outperformed all other networks (all -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.
经颅超声检查（TCS）已被用于评估帕金森病（PD）患者中脑黑质的高回声；然而，其主观性和资源需求大的特点阻碍了它的广泛应用。一种基于人工智能的、由TCS驱动的PD分类工具的需求很大，但相关研究严重匮乏。因此，我们提出了一种新颖的双通道CNXV2-DANet，用于基于TCS的PD分类，使用了一个大型队列。我们从北京天坛医院回顾性收集了588名受试者的1176张TCS图像，涵盖了每个受试者中脑的左侧和右侧。整个数据集按照70%/15%/15%的比例分为训练集/验证集/测试集。在训练集上开发所提出的CNXV2-DANet，并比较单通道和双通道输入设置；在独立测试集上进行模型评估。将所提出的双通道CNXV2-DANet与三个最先进的网络（ConvNeXtV2、ConvNeXt、Swin Transformer）进行比较。结果表明，CNXV2-DANet和ConvNeXt V2在双通道输入下的表现均优于单通道输入。双通道CNXV2-DANet优于单通道，在准确率（0.839±0.028）、精确率（0.849±0.014）、召回率（0.845±0.043）、F1分数（0.820±0.038）和AUC（0.906±0.013）方面实现了更高的平均指标，而单通道在准确率（0.784±0.037）、精确率（0.817±0.090）、召回率（0.748±0.093）、F1分数（0.773±0.037）和AUC（0.861±0.047）方面的指标较低。此外，双通道CNXV2-DANet的表现优于所有其他网络（所有p值<0.001）。这些发现表明，所提出的双通道CNXV2-DANet可能为该领域提供一种基于人工智能的、由TCS驱动的PD评估工具。
