Attention-enhanced dilated convolution for Parkinson's disease detection using transcranial sonography.

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. CONCLUSION: 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.

A highly selective and sensitive fluorescent sensor based on Tb3+-functionalized MOFs to determine arginine in urine: a potential application for the diagnosis of cystinuria.

A unique metal-organic framework with the formula [Cd4(H2L)2(L)·H2O]·3H2O (H4L = 5,5'-(1H-1,2,4-triazole-3,5-diyl)diisophthalic acid) was successfully constructed under solvothermal conditions. The frameworks with multiple free Lewis base sites and Lewis acid sites exhibited easily sensitized properties. After the encapsulation of Tb3+ cations, the as-synthesized Tb3+@Cd-MOF demonstrated strong luminescence induced by the efficient energy transfer from the bridging ligands to the Tb3+ cations, with the potential to serve as a chemical sensor. Interestingly, Tb3+@Cd-MOF was proven to be a very promising and highly selective and sensitive luminescent platform for the quantitative detection of arginine, which is the biomarker of cystinuria. The fluorescent probe presented high selectivity to arginine in urine with strong luminescence quenching. Furthermore, a convenient fluorescence-based test paper for the visual detection of arginine in applications was prepared. For the first time, arginine was quantified and monitored in urine by a highly efficient recyclable fluorescent sensor based on Tb3+-functionalized MOF hybrids, which may be a potential candidate for the further development of clinical diagnostic tools.