Machine Learning Predicts the Oxidative Stress Subtypes Provide an Innovative Insight into Colorectal Cancer.

So far, it has been reached the academic consensus that the molecular subtypes are via genomic heterogeneity and immune infiltration patterns. Considering that oxidative stress (OS) is involved in tumorigenesis and prognosis prediction, we propose an innovative classification of colorectal cancer- (CRC-) OS subtypes. We obtain three datasets from The Cancer Genome Atlas Program (TCGA) and Gene Expression Omnibus (GEO) online databases. 1399 OS-related genes were selected from the GeneCards database. We remove the batch effect before conducting differentially expressed genes (DEGs) analyses between normal and tumor samples. Nonnegative matrix factorization (NMF) was used to perform an unsupervised cluster. Lasso regression and Cox regression were used to construct the signature model. DEGs, robust rank aggregation, and protein-protein interaction networks were used to select hub genes, and then use hub genes to predict OS subtypes by random forest algorithms. NMF identifies two OS-related subtypes of CRC patients. Eight OS-related gene signatures were built to predict the outcome of patients, based on the DEGs between two subtypes. A total of 61 DEGs overlap each dataset, and the RRA analysis shows that 17 genes are important in these three datasets, and 15 genes are shared genes between the two methods. PPI network suggests that five hub genes are confirmed, they are SPP1, SERPINE1, CAV1, PDGFRB, and PLAU. These five hub genes could predict the OS-related subtype of CRC accurately with AUC equal to 0.771. In our study, we identify two OS-related subtypes, which will provide an innovative insight into colorectal cancer.

[CT and MRI fusion based on generative adversarial network and convolutional neural networks under image enhancement].

Aiming at the problems of missing important features, inconspicuous details and unclear textures in the fusion of multimodal medical images, this paper proposes a method of computed tomography (CT) image and magnetic resonance imaging (MRI) image fusion using generative adversarial network (GAN) and convolutional neural network (CNN) under image enhancement. The generator aimed at high-frequency feature images and used double discriminators to target the fusion images after inverse transform; Then high-frequency feature images were fused by trained GAN model, and low-frequency feature images were fused by CNN pre-training model based on transfer learning. Experimental results showed that, compared with the current advanced fusion algorithm, the proposed method had more abundant texture details and clearer contour edge information in subjective representation. In the evaluation of objective indicators, Q AB/F, information entropy (IE), spatial frequency (SF), structural similarity (SSIM), mutual information (MI) and visual information fidelity for fusion (VIFF) were 2.0%, 6.3%, 7.0%, 5.5%, 9.0% and 3.3% higher than the best test results, respectively. The fused image can be effectively applied to medical diagnosis to further improve the diagnostic efficiency.

[Multiresolution discrete optimization registration method of ultrasound and magnetic resonance images based on key points].

The registration of preoperative magnetic resonance (MR) images and intraoperative ultrasound (US) images is very important in the planning of brain tumor surgery and during surgery. Considering that the two-modality images have different intensity range and resolution, and the US images are degraded by lots of speckle noises, a self-similarity context (SSC) descriptor based on local neighborhood information was adopted to define the similarity measure. The ultrasound images were considered as the reference, the corners were extracted as the key points using three-dimensional differential operators, and the dense displacement sampling discrete optimization algorithm was adopted for registration. The whole registration process was divided into two stages including the affine registration and the elastic registration. In the affine registration stage, the image was decomposed using multi-resolution scheme, and in the elastic registration stage, the displacement vectors of key points were regularized using the minimum convolution and mean field reasoning strategies. The registration experiment was performed on the preoperative MR images and intraoperative US images of 22 patients. The overall error after affine registration was (1.57 ± 0.30) mm, and the average computation time of each pair of images was only 1.36 s; while the overall error after elastic registration was further reduced to (1.40 ± 0.28) mm, and the average registration time was 1.53 s. The experimental results show that the proposed method has prominent registration accuracy and high computational efficiency.

[A meta-learning based method for segmentation of few-shot magnetic resonance images].

When applying deep learning algorithms to magnetic resonance (MR) image segmentation, a large number of annotated images are required as data support. However, the specificity of MR images makes it difficult and costly to acquire large amounts of annotated image data. To reduce the dependence of MR image segmentation on a large amount of annotated data, this paper proposes a meta-learning U-shaped network (Meta-UNet) for few-shot MR image segmentation. Meta-UNet can use a small amount of annotated image data to complete the task of MR image segmentation and obtain good segmentation results. Meta-UNet improves U-Net by introducing dilated convolution, which can increase the receptive field of the model to improve the sensitivity to targets of different scales. We introduce the attention mechanism to improve the adaptability of the model to different scales. We introduce the meta-learning mechanism, and employ a composite loss function for well-supervised and effective bootstrapping of model training. We use the proposed Meta-UNet model to train on different segmentation tasks, and then use the trained model to evaluate on a new segmentation task, where the Meta-UNet model achieves high-precision segmentation of target images. Meta-UNet has a certain improvement in mean Dice similarity coefficient (DSC) compared with voxel morph network (VoxelMorph), data augmentation using learned transformations (DataAug) and label transfer network (LT-Net). Experiments show that the proposed method can effectively perform MR image segmentation using a small number of samples. It provides a reliable aid for clinical diagnosis and treatment.

[Modulation of motor responses and neural activities with transcranial ultrasound stimulation based on closed-loop control].

Closed-loop transcranial ultrasound stimulation technology is based on real-time feedback signals, and has the potential for precise regulation of neural activity. In this paper, firstly the local field potential (LFP) and electromyogram (EMG) signals of mice under different intensities of ultrasound stimulation were recorded, then the mathematical model of ultrasound intensity and mouse LFP peak/EMG mean was established offline based on the data, and the closed-loop control system of LFP peak and EMG mean based on PID neural network control algorithm was simulated and built to realize closed-loop control of LFP peak and EMG mean of mice. In addition, using the generalized minimum variance control algorithm, the closed-loop control of theta oscillation power was realized. There was no significant difference between the LFP peak, EMG mean and theta power under closed-loop ultrasound control and the given value, indicating a significant control effect on the LFP peak, EMG mean and theta power of mice. Transcranial ultrasound stimulation based on closed-loop control algorithms provides a direct tool for precise modulation of electrophysiological signals in mice.

[A non-contact continuous blood pressure measurement method based on video stream].

Hypertension is the primary disease that endangers human health. A convenient and accurate blood pressure measurement method can help to prevent the hypertension. This paper proposed a continuous blood pressure measurement method based on facial video signal. Firstly, color distortion filtering and independent component analysis were used to extract the video pulse wave of the region of interest in the facial video signal, and the multi-dimensional feature extraction of the pulse wave was preformed based on the time-frequency domain and physiological principles; Secondly, an integrated feature selection method was designed to extract the universal optimal feature subset; After that, we compared the single person blood pressure measurement models established by Elman neural network based on particle swarm optimization, support vector machine (SVM) and deep belief network; Finally, we used SVM algorithm to build a general blood pressure prediction model, which was compared and evaluated with the real blood pressure value. The experimental results showed that the blood pressure measurement results based on facial video were in good agreement with the standard blood pressure values. Comparing the estimated blood pressure from the video with standard blood pressure value, the mean absolute error (MAE) of systolic blood pressure was 4.9 mm Hg with a standard deviation (STD) of 5.9 mm Hg, and the MAE of diastolic blood pressure was 4.6 mm Hg with a STD of 5.0 mm Hg, which met the AAMI standards. The non-contact blood pressure measurement method based on video stream proposed in this paper can be used for blood pressure measurement.

[Automatic sleep staging algorithm for stochastic depth residual networks based on transfer learning].

The existing automatic sleep staging algorithms have the problems of too many model parameters and long training time, which in turn results in poor sleep staging efficiency. Using a single channel electroencephalogram (EEG) signal, this paper proposed an automatic sleep staging algorithm for stochastic depth residual networks based on transfer learning (TL-SDResNet). Firstly, a total of 30 single-channel (Fpz-Cz) EEG signals from 16 individuals were selected, and after preserving the effective sleep segments, the raw EEG signals were pre-processed using Butterworth filter and continuous wavelet transform to obtain two-dimensional images containing its time-frequency joint features as the input data for the staging model. Then, a ResNet50 pre-trained model trained on a publicly available dataset, the sleep database extension stored in European data format (Sleep-EDFx) was constructed, using a stochastic depth strategy and modifying the output layer to optimize the model structure. Finally, transfer learning was applied to the human sleep process throughout the night. The algorithm in this paper achieved a model staging accuracy of 87.95% after conducting several experiments. Experiments show that TL-SDResNet50 can accomplish fast training of a small amount of EEG data, and the overall effect is better than other staging algorithms and classical algorithms in recent years, which has certain practical value.

[Research on eye movement data classification using support vector machine with improved whale optimization algorithm].

When performing eye movement pattern classification for different tasks, support vector machines are greatly affected by parameters. To address this problem, we propose an algorithm based on the improved whale algorithm to optimize support vector machines to enhance the performance of eye movement data classification. According to the characteristics of eye movement data, this study first extracts 57 features related to fixation and saccade, then uses the ReliefF algorithm for feature selection. To address the problems of low convergence accuracy and easy falling into local minima of the whale algorithm, we introduce inertia weights to balance local search and global search to accelerate the convergence speed of the algorithm and also use the differential variation strategy to increase individual diversity to jump out of local optimum. In this paper, experiments are conducted on eight test functions, and the results show that the improved whale algorithm has the best convergence accuracy and convergence speed. Finally, this paper applies the optimized support vector machine model of the improved whale algorithm to the task of classifying eye movement data in autism, and the experimental results on the public dataset show that the accuracy of the eye movement data classification of this paper is greatly improved compared with that of the traditional support vector machine method. Compared with the standard whale algorithm and other optimization algorithms, the optimized model proposed in this paper has higher recognition accuracy and provides a new idea and method for eye movement pattern recognition. In the future, eye movement data can be obtained by combining it with eye trackers to assist in medical diagnosis.

[A survey of loss function of medical image segmentation algorithms].

Medical image segmentation based on deep learning has become a powerful tool in the field of medical image processing. Due to the special nature of medical images, image segmentation algorithms based on deep learning face problems such as sample imbalance, edge blur, false positive, false negative, etc. In view of these problems, researchers mostly improve the network structure, but rarely improve from the unstructured aspect. The loss function is an important part of the segmentation method based on deep learning. The improvement of the loss function can improve the segmentation effect of the network from the root, and the loss function is independent of the network structure, which can be used in various network models and segmentation tasks in plug and play. Starting from the difficulties in medical image segmentation, this paper first introduces the loss function and improvement strategies to solve the problems of sample imbalance, edge blur, false positive and false negative. Then the difficulties encountered in the improvement of the current loss function are analyzed. Finally, the future research directions are prospected. This paper provides a reference for the reasonable selection, improvement or innovation of loss function, and guides the direction for the follow-up research of loss function.

MBECS: Microbiome Batch Effects Correction Suite.

Despite the availability of batch effect correcting algorithms (BECA), no comprehensive tool that combines batch correction and evaluation of the results exists for microbiome datasets. This work outlines the Microbiome Batch Effects Correction Suite development that integrates several BECAs and evaluation metrics into a software package for the statistical computation framework R.

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application.

Tongue diagnosis is an essential technique of traditional Chinese medicine (TCM) diagnosis, and the need for objectifying tongue images through image processing technology is growing. The present study provides an overview of the progress made in tongue objectification over the past decade and compares segmentation models. Various deep learning models are constructed to verify and compare algorithms using real tongue image sets. The strengths and weaknesses of each model are analyzed. The findings indicate that the U-Net algorithm outperforms other models regarding precision accuracy (PA), recall, and mean intersection over union (MIoU) metrics. However, despite the significant progress in tongue image acquisition and processing, a uniform standard for objectifying tongue diagnosis has yet to be established. To facilitate the widespread application of tongue images captured using mobile devices in tongue diagnosis objectification, further research could address the challenges posed by tongue images captured in complex environments.

Rapid identification of breast cancer subtypes using micro-FTIR and machine learning methods.

Breast cancer (BC) molecular subtypes diagnosis involves improving clinical uptake by Fourier transform infrared (FTIR) spectroscopic imaging, which is a non-destructive and powerful technique, enabling label free extraction of biochemical information towards prognostic stratification and evaluation of cell functionality. However, methods of measurements of samples demand a long time to achieve high quality images, making its clinical use impractical because of the data acquisition speed, poor signal to noise ratio, and deficiency of optimized computational framework procedures. To address those challenges, machine learning (ML) tools can facilitate obtaining an accurate classification of BC subtypes with high actionability and accuracy. Here, we propose a ML-algorithm-based method to distinguish computationally BC cell lines. The method is developed by coupling the K-neighbors classifier (KNN) with neighborhood components analysis (NCA), and hence, the NCA-KNN method enables to identify BC subtypes without increasing model size as well as adding additional computational parameters. By incorporating FTIR imaging data, we show that classification accuracy, specificity, and sensitivity improve, respectively, 97.5%, 96.3%, and 98.2%, even at very low co-added scans and short acquisition times. Moreover, a clear distinctive accuracy (up to 9 %) difference of our proposed method (NCA-KNN) was obtained in comparison with the second best supervised support vector machine model. Our results suggest a key diagnostic NCA-KNN method for BC subtypes classification that may translate to advancement of its consolidation in subtype-associated therapeutics.

Multiclass classification of environmental chemical stimuli from unbalanced plant electrophysiological data.

Plant electrophysiological response contains useful signature of its environment and health which can be utilized using suitable statistical analysis for developing an inverse model to classify the stimulus applied to the plant. In this paper, we have presented a statistical analysis pipeline to tackle a multiclass environmental stimuli classification problem with unbalanced plant electrophysiological data. The objective here is to classify three different environmental chemical stimuli, using fifteen statistical features, extracted from the plant electrical signals and compare the performance of eight different classification algorithms. A comparison using reduced dimensional projection of the high dimensional features via principal component analysis (PCA) has also been presented. Since the experimental data is highly unbalanced due to varying length of the experiments, we employ a random under-sampling approach for the two majority classes to create an ensemble of confusion matrices to compare the classification performances. Along with this, three other multi-classification performance metrics commonly used for unbalanced data viz. balanced accuracy, F1-score and Matthews correlation coefficient have also been analyzed. From the stacked confusion matrices and the derived performance metrics, we choose the best feature-classifier setting in terms of the classification performances carried out in the original high dimensional vs. the reduced feature space, for this highly unbalanced multiclass problem of plant signal classification due to different chemical stress. Difference in the classification performances in the high vs. reduced dimensions are also quantified using the multivariate analysis of variance (MANOVA) hypothesis testing. Our findings have potential real-world applications in precision agriculture for exploring multiclass classification problems with highly unbalanced datasets, employing a combination of existing machine learning algorithms. This work also advances existing studies on environmental pollution level monitoring using plant electrophysiological data.

Identification and Validation of NK Marker Genes in Ovarian Cancer by scRNA-seq Combined with WGCNA Algorithm.

Background: As an innate immune system effector, natural killer cells (NK cells) play a significant role in tumor immunotherapy response and clinical outcomes. Methods: In our investigation, we collected ovarian cancer samples from TCGA and GEO cohorts, and a total of 1793 samples were included. In addition, four high-grade serous ovarian cancer scRNA-seq data were included for screening NK cell marker genes. Weighted gene coexpression network analysis (WGCNA) identified core modules and central genes associated with NK cells. The "TIMER," "CIBERSORT," "MCPcounter," "xCell," and "EPIC" algorithms were performed to predict the infiltration characteristics of different immune cell types in each sample. The LASSO-COX algorithm was employed to build risk models to predict prognosis. Finally, drug sensitivity screening was performed. Results: We first scored the NK cell infiltration of each sample and found that the level of NK cell infiltration affected the clinical outcome of ovarian cancer patients. Therefore, we analyzed four high-grade serous ovarian cancer scRNA-seq data, screening NK cell marker genes at the single-cell level. The WGCNA algorithm screens NK cell marker genes based on bulk RNA transcriptome patterns. Finally, a total of 42 NK cell marker genes were included in our investigation. Among which, 14 NK cell marker genes were then used to develop a 14-gene prognostic model for the meta-GPL570 cohort, dividing patients into high-risk and low-risk subgroups. The predictive performance of this model has been well-verified in different external cohorts. Tumor immune microenvironment analysis showed that the high-risk score of the prognostic model was positively correlated with M2 macrophages, cancer-associated fibroblast, hematopoietic stem cell, stromal score, and negatively correlated with NK cell, cytotoxicity score, B cell, and T cell CD4+Th1. In addition, we found that bleomycin, cisplatin, docetaxel, doxorubicin, gemcitabine, and etoposide were more effective in the high-risk group, while paclitaxel had a better therapeutic effect on patients in the low-risk group. Conclusion: By utilizing NK cell marker genes in our investigation, we developed a new feature that is capable of predicting patients' clinical outcomes and treatment strategies.

A traveler-centric mobility game: Efficiency and stability under rationality and prospect theory.

In this paper, we study a routing and travel-mode choice problem for mobility systems with a multimodal transportation network as a "mobility game" with coupled action sets. We formulate an atomic routing game to focus on the travelers' preferences and study the impact on the efficiency of the travelers' behavioral decision-making under rationality and prospect theory. To control the innate inefficiencies, we introduce a mobility "pricing mechanism," in which we model traffic congestion using linear cost functions while also considering the waiting times at different transport hubs. We show that the travelers' selfish actions lead to a pure-strategy Nash equilibrium. We then perform a Price of Anarchy and Price of Stability analysis to establish that the mobility system's inefficiencies remain relatively low and the social welfare at a NE remains close to the social optimum as the number of travelers increases. We deviate from the standard game-theoretic analysis of decision-making by extending our mobility game to capture the subjective behavior of travelers using prospect theory. Finally, we provide a detailed discussion of implementing our proposed mobility game.

Identification of Potential Biomarkers for Group I Pulmonary Hypertension Based on Machine Learning and Bioinformatics Analysis.

A number of processes and pathways have been reported in the development of Group I pulmonary hypertension (Group I PAH); however, novel biomarkers need to be identified for a better diagnosis and management. We employed a robust rank aggregation (RRA) algorithm to shortlist the key differentially expressed genes (DEGs) between Group I PAH patients and controls. An optimal diagnostic model was obtained by comparing seven machine learning algorithms and was verified in an independent dataset. The functional roles of key DEGs and biomarkers were analyzed using various in silico methods. Finally, the biomarkers and a set of key candidates were experimentally validated using patient samples and a cell line model. A total of 48 key DEGs with preferable diagnostic value were identified. A gradient boosting decision tree algorithm was utilized to build a diagnostic model with three biomarkers, PBRM1, CA1, and TXLNG. An immune-cell infiltration analysis revealed significant differences in the relative abundances of seven immune cells between controls and PAH patients and a correlation with the biomarkers. Experimental validation confirmed the upregulation of the three biomarkers in Group I PAH patients. In conclusion, machine learning and a bioinformatics analysis along with experimental techniques identified PBRM1, CA1, and TXLNG as potential biomarkers for Group I PAH.

An Unsupervised Classification Algorithm for Heterogeneous Cryo-EM Projection Images Based on Autoencoders.

Heterogeneous three-dimensional (3D) reconstruction in single-particle cryo-electron microscopy (cryo-EM) is an important but very challenging technique for recovering the conformational heterogeneity of flexible biological macromolecules such as proteins in different functional states. Heterogeneous projection image classification is a feasible solution to solve the structural heterogeneity problem in single-particle cryo-EM. The majority of heterogeneous projection image classification methods are developed using supervised learning technology or require a large amount of a priori knowledge, such as the orientations or common lines of the projection images, which leads to certain limitations in their practical applications. In this paper, an unsupervised heterogeneous cryo-EM projection image classification algorithm based on autoencoders is proposed, which only needs to know the number of heterogeneous 3D structures in the dataset and does not require any labeling information of the projection images or other a priori knowledge. A simple autoencoder with multi-layer perceptrons trained in iterative mode and a complex autoencoder with residual networks trained in one-pass learning mode are implemented to convert heterogeneous projection images into latent variables. The extracted high-dimensional features are reduced to two dimensions using the uniform manifold approximation and projection dimensionality reduction algorithm, and then clustered using the spectral clustering algorithm. The proposed algorithm is applied to two heterogeneous cryo-EM datasets for heterogeneous 3D reconstruction. Experimental results show that the proposed algorithm can effectively extract category features of heterogeneous projection images and achieve high classification and reconstruction accuracy, indicating that the proposed algorithm is effective for heterogeneous 3D reconstruction in single-particle cryo-EM.

A Comprehensive Review on Machine Learning in Healthcare Industry: Classification, Restrictions, Opportunities and Challenges.

Recently, various sophisticated methods, including machine learning and artificial intelligence, have been employed to examine health-related data. Medical professionals are acquiring enhanced diagnostic and treatment abilities by utilizing machine learning applications in the healthcare domain. Medical data have been used by many researchers to detect diseases and identify patterns. In the current literature, there are very few studies that address machine learning algorithms to improve healthcare data accuracy and efficiency. We examined the effectiveness of machine learning algorithms in improving time series healthcare metrics for heart rate data transmission (accuracy and efficiency). In this paper, we reviewed several machine learning algorithms in healthcare applications. After a comprehensive overview and investigation of supervised and unsupervised machine learning algorithms, we also demonstrated time series tasks based on past values (along with reviewing their feasibility for both small and large datasets).

Algorithms and Techniques for the Structural Health Monitoring of Bridges: Systematic Literature Review.

Structural health monitoring (SHM) systems are used to analyze the health of infrastructures such as bridges, using data from various types of sensors. While SHM systems consist of various stages, feature extraction and pattern recognition steps are the most important. Consequently, signal processing techniques in the feature extraction stage and machine learning algorithms in the pattern recognition stage play an effective role in analyzing the health of bridges. In other words, there exists a plethora of signal processing techniques and machine learning algorithms, and the selection of the appropriate technique/algorithm is guided by the limitations of each technique/algorithm. The selection also depends on the requirements of SHM in terms of damage identification level and operating conditions. This has provided the motivation to conduct a Systematic literature review (SLR) of feature extraction techniques and pattern recognition algorithms for the structural health monitoring of bridges. The existing literature reviews describe the current trends in the field with different focus aspects. However, a systematic literature review that presents an in-depth comparative study of different applications of machine learning algorithms in the field of SHM of bridges does not exist. Furthermore, there is a lack of analytical studies that investigate the SHM systems in terms of several design considerations including feature extraction techniques, analytical approaches (classification/ regression), operational functionality levels (diagnosis/prognosis) and system implementation techniques (data-driven/model-based). Consequently, this paper identifies 45 recent research practices (during 2016-2023), pertaining to feature extraction techniques and pattern recognition algorithms in SHM for bridges through an SLR process. First, the identified research studies are classified into three different categories: supervised learning algorithms, neural networks and a combination of both. Subsequently, an in-depth analysis of various machine learning algorithms is performed in each category. Moreover, the analysis of selected research studies (total = 45) in terms of feature extraction techniques is made, and 25 different techniques are identified. Furthermore, this article also explores other design considerations like analytical approaches in the pattern recognition process, operational functionality and system implementation. It is expected that the outcomes of this research may facilitate the researchers and practitioners of the domain during the selection of appropriate feature extraction techniques, machine learning algorithms and other design considerations according to the SHM system requirements.