PDF(Pubmed)
Abstract：
BACKGROUND: Transcranial sonography (TCS) plays a crucial role in diagnosing Parkinson\'s disease. However, the intricate nature of TCS pathological features, the lack of consistent diagnostic criteria, and the dependence on physicians\' expertise can hinder accurate diagnosis. Current TCS-based diagnostic methods, which rely on machine learning, often involve complex feature engineering and may struggle to capture deep image features. While deep learning offers advantages in image processing, it has not been tailored to address specific TCS and movement disorder considerations. Consequently, there is a scarcity of research on deep learning algorithms for TCS-based PD diagnosis.
METHODS: This study introduces a deep learning residual network model, augmented with attention mechanisms and multi-scale feature extraction, termed AMSNet, to assist in accurate diagnosis. Initially, a multi-scale feature extraction module is implemented to robustly handle the irregular morphological features and significant area information present in TCS images. This module effectively mitigates the effects of artifacts and noise. When combined with a convolutional attention module, it enhances the model\'s ability to learn features of lesion areas. Subsequently, a residual network architecture, integrated with channel attention, is utilized to capture hierarchical and detailed textures within the images, further enhancing the model\'s feature representation capabilities.
RESULTS: The study compiled TCS images and personal data from 1109 participants. Experiments conducted on this dataset demonstrated that AMSNet achieved remarkable classification accuracy (92.79%), precision (95.42%), and specificity (93.1%). It surpassed the performance of previously employed machine learning algorithms in this domain, as well as current general-purpose deep learning models.
CONCLUSIONS: The AMSNet proposed in this study deviates from traditional machine learning approaches that necessitate intricate feature engineering. It is capable of automatically extracting and learning deep pathological features, and has the capacity to comprehend and articulate complex data. This underscores the substantial potential of deep learning methods in the application of TCS images for the diagnosis of movement disorders.
METHODS: This study introduces a deep learning residual network model, augmented with attention mechanisms and multi-scale feature extraction, termed AMSNet, to assist in accurate diagnosis. Initially, a multi-scale feature extraction module is implemented to robustly handle the irregular morphological features and significant area information present in TCS images. This module effectively mitigates the effects of artifacts and noise. When combined with a convolutional attention module, it enhances the model\'s ability to learn features of lesion areas. Subsequently, a residual network architecture, integrated with channel attention, is utilized to capture hierarchical and detailed textures within the images, further enhancing the model\'s feature representation capabilities.
RESULTS: The study compiled TCS images and personal data from 1109 participants. Experiments conducted on this dataset demonstrated that AMSNet achieved remarkable classification accuracy (92.79%), precision (95.42%), and specificity (93.1%). It surpassed the performance of previously employed machine learning algorithms in this domain, as well as current general-purpose deep learning models.
CONCLUSIONS: The AMSNet proposed in this study deviates from traditional machine learning approaches that necessitate intricate feature engineering. It is capable of automatically extracting and learning deep pathological features, and has the capacity to comprehend and articulate complex data. This underscores the substantial potential of deep learning methods in the application of TCS images for the diagnosis of movement disorders.
摘要：
背景：经颅超声（TCS）在帕金森病的诊断中起着至关重要的作用。然而,TCS病理特征的复杂性，缺乏一致的诊断标准，对医生专业知识的依赖会阻碍准确的诊断。当前基于TCS的诊断方法，依赖于机器学习，通常涉及复杂的特征工程，并且可能难以捕获深层图像特征。虽然深度学习在图像处理方面具有优势，尚未针对特定的TCS和运动障碍考虑因素进行定制。因此,基于TCS的PD诊断的深度学习算法的研究很少。
方法：本研究引入了深度学习残差网络模型，增强了注意力机制和多尺度特征提取，称为AMSNet，协助准确诊断。最初，实现了多尺度特征提取模块，以鲁棒地处理TCS图像中存在的不规则形态特征和显著区域信息。该模块有效地减轻了伪影和噪声的影响。当与卷积注意模块结合时，它增强了模型学习病变区域特征的能力。随后，剩余的网络架构，与频道注意力相结合，用于捕获图像中的分层和详细的纹理，进一步增强模型的特征表示能力。
结果：该研究汇总了1109名参与者的TCS图像和个人数据。在该数据集上进行的实验表明，AMSNet取得了显著的分类准确率(92.79%)，精度（95.42%），和特异性（93.1％）。它超越了以前在该领域采用的机器学习算法的性能，以及当前的通用深度学习模型。
结论：本研究中提出的AMSNet偏离了需要复杂特征工程的传统机器学习方法。它能够自动提取和学习深度病理特征，并且有能力理解和表达复杂的数据。这强调了深度学习方法在应用TCS图像诊断运动障碍方面的巨大潜力。
方法：本研究引入了深度学习残差网络模型，增强了注意力机制和多尺度特征提取，称为AMSNet，协助准确诊断。最初，实现了多尺度特征提取模块，以鲁棒地处理TCS图像中存在的不规则形态特征和显著区域信息。该模块有效地减轻了伪影和噪声的影响。当与卷积注意模块结合时，它增强了模型学习病变区域特征的能力。随后，剩余的网络架构，与频道注意力相结合，用于捕获图像中的分层和详细的纹理，进一步增强模型的特征表示能力。
结果：该研究汇总了1109名参与者的TCS图像和个人数据。在该数据集上进行的实验表明，AMSNet取得了显著的分类准确率(92.79%)，精度（95.42%），和特异性（93.1％）。它超越了以前在该领域采用的机器学习算法的性能，以及当前的通用深度学习模型。
结论：本研究中提出的AMSNet偏离了需要复杂特征工程的传统机器学习方法。它能够自动提取和学习深度病理特征，并且有能力理解和表达复杂的数据。这强调了深度学习方法在应用TCS图像诊断运动障碍方面的巨大潜力。
