Radial basis function neural network optimization algorithm based on dynamic inertial weight particle swarm optimization for separating overlapping peaks in ion mobility spectrometry.

RATIONALE: Ion mobility spectrometry (IMS), as a promising analytical tool, has been widely employed in the structural characterization of biomolecules. Nevertheless, the inherent limitation in the structural resolution of IMS frequently results in peak overlap during the analysis of isomers exhibiting comparable structures. METHODS: The radial basis function (RBF) neural network optimization algorithm based on dynamic inertial weight particle swarm optimization (DIWPSO) was proposed for separating overlapping peaks in IMS. The RBF network structure and parameters were optimized using the DIWPSO algorithm. By extensively training using a large dataset, an adaptive model was developed to effectively separate overlapping peaks in IMS data. This approach successfully overcomes issues related to local optima, ensuring efficient and precise separation of overlapping peaks. RESULTS: The method's performance was evaluated using experimental validation and analysis of overlapping peaks in the IMS spectra of two sets of isomers: 3'/6'-sialyllactose; fructose-6-phosphate, glucose-1-phosphate, and glucose-6-phosphate. A comparative analysis was conducted using other algorithms, including the sparrow search algorithm, DIWPSO algorithm, and multi-objective dynamic teaching-learning-based optimization algorithm. The comparison results show that the DIWPSO-RBF algorithm achieved remarkably low maximum relative errors of only 0.42%, 0.092%, and 0.41% for ion height, mobility, and half peak width, respectively. These error rates are significantly lower than those obtained using the other three algorithms. CONCLUSIONS: The experimental results convincingly demonstrate that this method can adaptively, rapidly, and accurately separate overlapping peaks of multiple components, improving the structural resolution of IMS.

Automatic detection of mild cognitive impairment based on deep learning and radiomics of MR imaging.

Purpose: Early and rapid diagnosis of mild cognitive impairment (MCI) has important clinical value in improving the prognosis of Alzheimer's disease (AD). The hippocampus and parahippocampal gyrus play crucial roles in the occurrence of cognitive function decline. In this study, deep learning and radiomics techniques were used to automatically detect MCI from healthy controls (HCs). Method: This study included 115 MCI patients and 133 normal individuals with 3D-T1 weighted MR structural images from the ADNI database. The identification and segmentation of the hippocampus and parahippocampal gyrus were automatically performed with a VB-net, and radiomics features were extracted. Relief, Minimum Redundancy Maximum Correlation, Recursive Feature Elimination and the minimum absolute shrinkage and selection operator (LASSO) were used to reduce the dimensionality and select the optimal features. Five independent machine learning classifiers including Support Vector Machine (SVM), Random forest (RF), Logistic Regression (LR), Bagging Decision Tree (BDT), and Gaussian Process (GP) were trained on the training set, and validated on the testing set to detect the MCI. The Delong test was used to assess the performance of different models. Result: Our VB-net could automatically identify and segment the bilateral hippocampus and parahippocampal gyrus. After four steps of feature dimensionality reduction, the GP models based on combined features (11 features from the hippocampus, and 4 features from the parahippocampal gyrus) showed the best performance for the MCI and normal control subject discrimination. The AUC of the training set and test set were 0.954 (95% CI: 0.929-0.979) and 0.866 (95% CI: 0.757-0.976), respectively. Decision curve analysis showed that the clinical benefit of the line graph model was high. Conclusion: The GP classifier based on 15 radiomics features of bilateral hippocampal and parahippocampal gyrus could detect MCI from normal controls with high accuracy based on conventional MR images. Our fully automatic model could rapidly process the MRI data and give results in 1 minute, which provided important clinical value in assisted diagnosis.

Automatic diagnosis of Parkinson's disease using artificial intelligence base on routine T1-weighted MRI.

Background: Parkinson's disease (PD) is the second most common neurodegenerative disease. An objective diagnosis method is urgently needed in clinical practice. In this study, deep learning and radiomics techniques were studied to automatically diagnose PD from healthy controls (HCs). Methods: 155 PD patients and 154 HCs were randomly divided into a training set (246 patients) and a testing set (63 patients). The brain subregions identification and segmentation were automatically performed with a VB-net, and radiomics features of billateral thalamus, caudatum, putamen and pallidum were extracted. Five independent machine learning classifiers [Support Vector Machine (SVM), Stochastic gradient descent (SGD), random forest (RF), quadratic discriminant analysis (QDA) and decision tree (DT)] were trained on the training set, and validated on the testing. Delong test was used to compare the performance of different models. Results: Our VB-net could automatically identify and segment the brain into 109 regions. 2,264 radiomics features were automatically extracted from the billateral thalamus, caudatum, putamen or pallidum of each patient. After four step of features dimensionality reduction, Delong tests showed that the SVM model based on combined features had the best performance, with AUCs of 0.988 (95% CI: 0.979 ~ 0.998, specificity = 91.1%, sensitivity =100%, accuracy = 89.4% and precision = 88.2%) and 0.976 (95% CI: 0.942 ~ 1.000, specificity = 100%, sensitivity = 87.1%, accuracy = 93.5% and precision = 88.6%) in the training set and testing set, respectively. Decision curve analysis showed that the clinical benefit of the line graph model was high. Conclusion: The SVM model based on combined features could be used to diagnose PD with high accuracy. Our fully automatic model could rapidly process the MRI data and distinguish PD and HCs in one minute. It greatly improved the diagnostic efficiency and has a great potential value in clinical practice to help the early diagnosis of PD.

A case report of primary signet ring cell carcinoma of the lung: imaging study and literature review.

Signet ring cell carcinoma (SRCC) is a subtype of adenocarcinoma with characteristics of strong invasion and a poor prognosis. While it can occur in various organs, including the stomach, colon, esophagus, bladder, prostate, pancreas, and breast, primary lung SRCC is rare, and most SRCC found there are from gastrointestinal metastasis. Reports on primary lung SRCC are few and the aim of this study is to describe the imaging, histopathological, and immunohistochemical characteristics of a case of primary lung SRCC in our hospital. A 68-year-old female with no smoking history was admitted with recurrent cough, chest pain, and dyspnea of 2 months duration. Computed tomographic (CT) chest showed multiple solids nodules of different sizes and mass in the left upper lobe, lower lobe, and subpleural region. Multiple enlarged lymph nodes were seen in the mediastinum and left hilum. The aim of this paper is to improve the understanding of this tumor. A literature review identified 15 cases of primary lung SRCC with available CT imaging. Except for two patients with multiple ground glass nodules and multiple small nodules, the rest were solid, and ranged in size from 1.0 to 8 cm. Only one patient had a cavity in the solid lesion. Immunohistochemical stains for thyroid transcription factor-1 (TTF-1) (13/13) and CK7 (12/12) showed positive reaction in all cases evaluated, and napsin A (3/4) were also positive, while all cases including CK20 (12/12) and CDX2 (6/6) were negative.

Morphological characteristics associated with the rupture risk of mirror posterior communicating artery aneurysms.

OBJECTIVE: Patient related clinical factors and intracranial aneurysms (IAs) at different locations may lead to statistical bias when investigating the rupture risk of IAs. Thus the purpose of this study was to identify the morphological parameters that are related to the rupture of mirror posterior communicating artery aneurysms (PComAAs). METHODS: Between August 2011 and July 2017, 68 patients with mirror PComAAs and aneurysmal subarachnoid hemorrhage were diagnosed by CT angiography at three medical centers. Morphological characteristics for PComAAs included bifurcation, shape, neck width, width, depth, maximum size, flow angle, parent vessel diameter, aspect ratio (AR), depth/width ratio, bottleneck factor, and size ratio (SR). Multiple logistic regression analysis was performed to determine the independent risk factors for rupture. Receiver operating characteristic curve analysis was performed to obtain the optimal thresholds. RESULTS: AR (OR 5.623) and SR (OR 5.570) were more commonly observed in the ruptured cohort. The threshold values of AR and SR were 0.98 and 1.21, respectively. CONCLUSIONS: Mirror PComAAs are a useful model to investigate the rupture risk of PComAAs. AR (≥0.98) and SR (≥1.21) are better predictors of ruptured PComAAs.

Arctigenin reduces blood pressure by modulation of nitric oxide synthase and NADPH oxidase expression in spontaneously hypertensive rats.

Arctigenin is a bioactive constituent from dried seeds of Arctium lappa L., which was traditionally used as medicine. Arctigenin exhibits various bioactivities, but its effects on blood pressure regulation are still not widely studied. In this study, we investigated antihypertensive effects of arctigenin by long-term treatment in spontaneously hypertensive rats (SHRs). Arctigenin (50 mg/kg) or vehicle was administered to SHRs or Wistar rats as negative control by oral gavage once a day for total 8 weeks. Nifedipine (3 mg/kg) was used as a positive drug control. After treatment, hemodynamic and physical parameters, vascular reactivity in aorta, the concentration of plasma arctigenin and serum thromboxane B2, NO release and vascular p-eNOS, p-Akt, caveolin-1 protein expression, and vascular superoxide anion generation and p47phox protein expression were detected and analyzed. The results showed that arctigenin significantly reduced systolic blood pressure and ameliorated endothelial dysfunction of SHRs. Arctigenin reduced the levels of thromboxane B2 in plasma and superoxide anion in thoracic aorta of SHRs. Furthermore, arctigenin increased the NO production by enhancing the phosphorylation of Akt and eNOS (Ser 1177), and inhibiting the expression of NADPH oxidase in thoracic aorta of SHRs. Our data suggested that antihypertensive mechanisms of arctigenin were associated with enhanced eNOS phosphorylation and decreased NADPH oxidase-mediated superoxide anion generation.

[Study on the inhibitory effects of juice of tomato on the growth of human prostate carcinoma PC-3 cells].

OBJECTIVE: To study on the inhibitory effects of juice of tomato on the growth of human prostate carcinoma PC-3 cells and its possible mechanism. METHODS: PC-3 cells were treated with the juice of tomato in different concentration (40, 80, 120 ul/ml) for 48h; the proliferation of PC-3 cells were measured by MTT assay, the comet assay was used to measure the DNA damage of PC-3 cells. RESULTS: Juice of tomato could inhibit the proliferation of PC-3 cells, the growth inhibitory rate of experimental groups were significantly higher than that of control group, with very statistical significance; and it could induce the breakage of DNA single strand of PC-3 cells and resulted in comet cells with tail, Rate of DNA tail and the tail length of DNA increased with the increasing of concentration of juice of tomato, showing the obvious dose effect relationship. CONCLUSION: Juice of tomato could lead to DNA damage of PC-3 cells, it was related to that could inhibit the proliferation of PC-3 cells.