Alzheimer's disease prediction algorithm based on de-correlation constraint and multi-modal feature interaction.

Alzheimer's disease (AD) is a neurodegenerative disease characterized by various pathological changes. Utilizing multimodal data from Fluorodeoxyglucose positron emission tomography(FDG-PET) and Magnetic Resonance Imaging(MRI) of the brain can offer comprehensive information about the lesions from different perspectives and improve the accuracy of prediction. However, there are significant differences in the feature space of multimodal data. Commonly, the simple concatenation of multimodal features can cause the model to struggle in distinguishing and utilizing the complementary information between different modalities, thus affecting the accuracy of predictions. Therefore, we propose an AD prediction model based on de-correlation constraint and multi-modal feature interaction. This model consists of the following three parts: (1) The feature extractor employs residual connections and attention mechanisms to capture distinctive lesion features from FDG-PET and MRI data within their respective modalities. (2) The de-correlation constraint function enhances the model's capacity to extract complementary information from different modalities by reducing the feature similarity between them. (3) The mutual attention feature fusion module interacts with the features within and between modalities to enhance the modal-specific features and adaptively adjust the weights of these features based on information from other modalities. The experimental results on ADNI database demonstrate that the proposed model achieves a prediction accuracy of 86.79% for AD, MCI and NC, which is higher than the existing multi-modal AD prediction models.

A near-infrared ratiometric fluorescent probe for hydrazine and its application for gaseous sensing and cell imaging.

Hydrazine (N2H4) is a widely used raw material in the chemical industry, but at the same time hydrazine has extremely high toxicity. Therefore, the development of efficient detection methods is crucial for monitoring hydrazine in the environment and evaluating the biological toxicity of hydrazine. This study reports a near-infrared ratiometric fluorescent probe (DCPBCl2-Hz) for the detection of hydrazine by coupling a chlorine-substituted D-π-A fluorophore (DCPBCl2) to the recognition group acetyl. Due to the halogen effect of chlorine substitution, the fluorophore has an elevated fluorescence efficiency and a lowered pKa value and is suitable for physiological pH conditions. Hydrazine can specifically react with the acetyl group of the fluorescent probe to release the fluorophore DCPBCl2, so the fluorescence emission of the probe system significantly shifted from 490 nm to 660 nm. The fluorescent probe has many advantages, such as good selectivity, high sensitivity, large Stokes shift, and wide applicable pH range. The probe-loaded silica plates can realize convenient sensing gaseous hydrazine with content down to 1 ppm (mg/m3). Subsequently, DCPBCl2-Hz was successfully applied to detect hydrazine in soils. In addition, the probe can also penetrate living cells and allow the visualization of intracellular hydrazine. It can be anticipated that probe DCPBCl2-Hz will be a useful tool for sensing hydrazine in biological and environmental applications.

Alzheimer's Disease Prediction Algorithm Based on Group Convolution and a Joint Loss Function.

Alzheimer's disease (AD) can effectively predict by 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) of the brain, but current PET images still suffer from indistinct lesion features, low signal-to-noise ratios, and severe artefacts, resulting in poor prediction accuracy for patients with mild cognitive impairment (MCI) and unclear lesion features. In this paper, an AD prediction algorithm based on group convolution and a joint loss function is proposed. First, a group convolutional backbone network based on ResNet18 is designed to extract lesion features from multiple channels, which makes the expression ability of the network improved to a great extent. Then, a hybrid attention mechanism is presented, which enables the network to focus on target regions and learn feature weights, so as to enhance the network's learning ability of the lesion regions that are relevant to disease diagnosis. Finally, a joint loss function, that avoids the overfitting phenomenon, increases the generalization of the model, and improves prediction accuracy by adding a regularization loss function to the conventional cross-entropy function, is proposed. Experiments conducted on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset show that the algorithm we proposed gives a prediction accuracy improvement of 2.4% over that of the current AD prediction algorithm, thus proving the effectiveness and availability of the new algorithm.

[Clinical value of DC and DRs in warning sudden cardiac death of patients with coronary artery disease].

OBJECTIVE: To make risk stratification of aged patients with coronary artery disease by deceleration capacity of rate (DC) and heart rate deceleration runs (DRs) and to investigate the value of the two detection technologies in warning sudden cardiac death. METHODS: Two hundrend and eighteen patients diagnosed with coronary artery disease (CAD) by coronary angiography (CAG) were selected as observa-tion group:including 55 patients with latent coronary artery disease (LCHD), 56 patients with acute myocardial infarction (AMI), 53 patients with angina pectoris (AP), 54 patients with ischemic heart failure. Fifty-five healthy controls in our hospital were selected at the same time (control group). All patients were detected by 24-hour dynamic electrocardiogram while values of DC and DRs were automatically analyzed and calculated by software. RESULTS: The values of DC and DRs descended significantly in all CHD groups (AMI group, AP group, Ischemic Heart Failure group, LCHD group) and the difference was statistically significant (P < 0.01) compared with normal group; DC and DRs indicated the risk classification of each CAD subgroup was obviously higher than those in normal group and the difference was statistically significant(P < 0.01); CAG showed that the more coronary lesions, the larger the rage, prompt the heavier the illness, which was consistent with the risk classification of each CHD subgroup indicated by DC and DRs. CONCLUSIONS: DC and DRs can be used to analyze the function of vagus nerve, it also can be used to make risk classification of patients with CHD, and it has a higher value of pre-warning for high-risk groups. DC and DRs can be used as sensitive indexes in warning sudden cardiac death of patients with CHD.