Explore the vast range of titles available.

Functional near-infrared spectroscopy (fNIRS) research articles show a large heterogeneity in the analysis approaches and pre-processing procedures. Additionally, there is often a lack of a complete description of the methods applied, necessary for study replication or for results comparison. The aims of this paper were (i) to review and investigate which information is generally included in published fNIRS papers, and (ii) to define a signal pre-processing procedure to set a common ground for standardization guidelines. To this goal, we have reviewed 110 fNIRS articles published in 2016 in the field of cognitive neuroscience, and performed a simulation analysis with synthetic fNIRS data to optimize the signal filtering step before applying the GLM method for statistical inference. Our results highlight the fact that many papers lack important information, and there is a large variability in the filtering methods used. Our simulations demonstrated that the optimal approach to remove noise and recover the hemodynamic response from fNIRS data in a GLM framework is to use a 1000th order band-pass Finite Impulse Response filter. Based on these results, we give preliminary recommendations as to the first step toward improving the analysis of fNIRS data and dissemination of the results.

Lower-density Electroencephalography (EEG) recordings (from 1 to approximately 32 electrodes) are widely-used in research and clinical practice and enable scalable brain function measurement across a variety of settings and populations. Though a number of automated pipelines have recently been proposed to standardize and optimize EEG pre-processing for high-density systems with state-of-the-art methods, few solutions have emerged that are compatible with lower-density systems. However, lower-density data often include long recording times and/or large sample sizes that would benefit from similar standardization and automation with contemporary methods. To address this need, we propose the HAPPE In Low Electrode Electroencephalography (HAPPILEE) pipeline as a standardized, automated pipeline optimized for EEG recordings with lower density channel layouts of any size. HAPPILEE processes task-free (e.g., resting-state) and task-related EEG (including event-related potential data by interfacing with the HAPPE+ER pipeline), from raw files through a series of processing steps including filtering, line noise reduction, bad channel detection, artifact correction from continuous data, segmentation, and bad segment rejection that have all been optimized for lower density data. HAPPILEE also includes post-processing reports of data and pipeline quality metrics to facilitate the evaluation and reporting of data quality and processing-related changes to the data in a standardized manner. Here the HAPPILEE steps and their optimization with both recorded and simulated EEG data are described. HAPPILEE's performance is then compared relative to other artifact correction and rejection strategies. The HAPPILEE pipeline is freely available as part of HAPPE 2.0 software under the terms of the GNU General Public License at: https://github.com/PINE-Lab/HAPPE.

•We propose a pipeline for MEG research making analysis steps and parameters explicit.•The FLUX pipeline is developed to be used with MNE Python and FieldTrip and it includes the associated documented code.•The pipeline includes the state-of-the-art suggestions for noise cancellation as well as source modelling including pre-whitening and handling of rank-deficient data.•To facilitate pre-registration and precise reporting we provide concrete suggestions on parameters and text to document.•An example data set allows for the pipeline to be used in educational settings. Magnetoencephalography (MEG) allows for quantifying modulations of human neuronal activity on a millisecond time scale while also making it possible to estimate the location of the underlying neuronal sources. The technique relies heavily on signal processing and source modelling. To this end, there are several open-source toolboxes developed by the community. While these toolboxes are powerful as they provide a wealth of options for analyses, the many options also pose a challenge for reproducible research as well as for researchers new to the field. The FLUX pipeline aims to make the analyses steps and setting explicit for standard analysis done in cognitive neuroscience. It focuses on quantifying and source localization of oscillatory brain activity, but it can also be used for event-related fields and multivariate pattern analysis. The pipeline is derived from the Cogitate consortium addressing a set of concrete cognitive neuroscience questions. Specifically, the pipeline including documented code is defined for MNE Python (a Python toolbox) and FieldTrip (a Matlab toolbox), and a data set on visuospatial attention is used to illustrate the steps. The scripts are provided as notebooks implemented in Jupyter Notebook and MATLAB Live Editor providing explanations, justifications and graphical outputs for the essential steps. Furthermore, we also provide suggestions for text and parameter settings to be used in registrations and publications to improve replicability and facilitate pre-registrations. The FLUX can be used for education either in self-studies or guided workshops. We expect that the FLUX pipeline will strengthen the field of MEG by providing some standardization on the basic analysis steps and by aligning approaches across toolboxes. Furthermore, we also aim to support new researchers entering the field by providing education and training. The FLUX pipeline is not meant to be static; it will evolve with the development of the toolboxes and with new insights. Furthermore, with the anticipated increase in MEG systems based on the Optically Pumped Magnetometers, the pipeline will also evolve to embrace these developments.

Seismic fault structures are important for the detection and exploitation of hydrocarbon resources. Due to their development and popularity in the geophysical community, deep-learning-based fault detection methods have been proposed and achieved SOTA results. Due to the efficiency and benefits of full spatial information extraction, 3D convolutional neural networks (CNNs) are used widely to directly detect faults on seismic data volumes. However, using 3D data for training requires expensive computational resources and can be limited by hardware facilities. Although 2D CNN methods are less computationally intensive, they lead to the loss of correlation between seismic slices. To mitigate the aforementioned problems, we propose to predict a 2D fault section using multiple neighboring seismic profiles, that is, 2.5D fault detection. In CNNs, convolution layers mainly extract local information and pooling layers may disrupt the edge features in seismic data, which tend to cause fault discontinuities. To this end, we incorporate the Transformer module in U-net for feature extraction to enhance prediction continuity. To reduce the data discrepancies between synthetic and different real seismic datasets, we apply a seismic data standardization workflow to improve the prediction stability on real datasets. Netherlands F3 real data tests show that, when training on synthetic data labels, the proposed 2.5D Transformer U-net-based method predicts more subtle faults and faults with higher spatial continuity than the baseline full 3D U-net model.

Background: This study investigated the performance of ensemble learning holomic models for the detection of breast cancer, receptor status, proliferation rate, and molecular subtypes from [18F]FDG-PET/CT images with and without incorporating data pre-processing algorithms. Additionally, machine learning (ML) models were compared with conventional data analysis using standard uptake value lesion classification. Methods: A cohort of 170 patients with 173 breast cancer tumors (132 malignant, 38 benign) was examined with [18F]FDG-PET/CT. Breast tumors were segmented and radiomic features were extracted following the imaging biomarker standardization initiative (IBSI) guidelines combined with optimized feature extraction. Ensemble learning including five supervised ML algorithms was utilized in a 100-fold Monte Carlo (MC) cross-validation scheme. Data pre-processing methods were incorporated prior to machine learning, including outlier and borderline noisy sample detection, feature selection, and class imbalance correction. Feature importance in each model was assessed by calculating feature occurrence by the R-squared method across MC folds. Results: Cross validation demonstrated high performance of the cancer detection model (80% sensitivity, 78% specificity, 80% accuracy, 0.81 area under the curve (AUC)), and of the triple negative tumor identification model (85% sensitivity, 78% specificity, 82% accuracy, 0.82 AUC). The individual receptor status and luminal A/B subtype models yielded low performance (0.46–0.68 AUC). SUVmax model yielded 0.76 AUC in cancer detection and 0.70 AUC in predicting triple negative subtype. Conclusions: Predictive models based on [18F]FDG-PET/CT images in combination with advanced data pre-processing steps aid in breast cancer diagnosis and in ML-based prediction of the aggressive triple negative breast cancer subtype.

Background: Recent studies have shown that hyperspectral imaging (HSI) combined with neural networks can detect colorectal cancer. Usually, different pre-processing techniques (e.g., wavelength selection and scaling, smoothing, denoising) are analyzed in detail to achieve a well-trained network. The impact of post-processing was studied less. Methods: We tested the following methods: (1) Two pre-processing techniques (Standardization and Normalization), with (2) Two 3D-CNN models: Inception-based and RemoteSensing (RS)-based, with (3) Two post-processing algorithms based on median filter: one applies a median filter to a raw predictions map, the other applies the filter to the predictions map after adopting a discrimination threshold. These approaches were evaluated on a dataset that contains ex vivo hyperspectral (HS) colorectal cancer records of 56 patients. Results: (1) Inception-based models perform better than RS-based, with the best results being 92% sensitivity and 94% specificity; (2) Inception-based models perform better with Normalization, RS-based with Standardization; (3) Our outcomes show that the post-processing step improves sensitivity and specificity by 6.6% in total. It was also found that both post-processing algorithms have the same effect, and this behavior was explained. Conclusion: HSI combined with tissue classification algorithms is a promising diagnostic approach whose performance can be additionally improved by the application of the right combination of pre- and post-processing.

Cracks are one of the forms of damage to concrete structures that debase the strength and durability of the building material and may pose a danger to the living being associated with it. Proper and regular diagnosis of concrete cracks is therefore necessary. Nowadays, for the more accurate identification and classification of cracks, various automated crack detection techniques are employed over a manual human inspection. Convolution Neural Network (CNN) has shown excellent performance in image processing. Thus, it is becoming the mainstream choice to replace the manual crack classification techniques, but this technique requires huge labeled data for training. Transfer learning is a strategy that tackles this issue by using pre-trained models. This work first time strives to classify concrete surface cracks by re-training of six pre-trained deep CNN models such as VGG-16, DenseNet-121, Inception-v3, ResNet-50, Xception, and InceptionResNet-v2 using transfer learning and comparing them with different metrics, such as Accuracy, Precision, Recall, F1-Score, Cohen Kappa, ROC AUC, and Error Rate in order to find the model with the best suitability. A dataset from two separate sources is considered for the re-training of pre-trained models, for the classification of cracks on concrete surfaces. Initially, the selective crack and non-crack images of the Mendeley dataset are considered, and later, a new dataset is used. As a result, the re-trained classifier of CNN models provides a consistent performance with an accuracy range of 0.95 to 0.99 on the first dataset and 0.85 to 0.98 on the new dataset. The results show that these CNN variants can produce the best outcome when finding cracks in the real situation and have strong generalization capabilities.

Accurate forecast of the magnitude and timing of the flood peak river discharge and the extent of inundated areas during major storm events are a vital component of early warning systems around the world that are responsible for saving countless lives every year. This study assesses the forecast accuracy of two different linear and non-linear approaches to predict the daily river discharge. A new linear stochastic method is produced by evaluating a detailed comparison between three pre-processing approaches, differencing, standardization, spectral analysis, and trend removal. Daily river discharge values of the Bow River with strong seasonal and non-seasonal correlations located in Alberta, Canada were utilized in this study. The stochastic term for this daily flow time series is calculated with an auto-regressive integrated moving average. We found that seasonal differencing is the best stationarization method for periodic effect elimination. Moreover, the proposed non-linear Group Method of Data Handling (GMDH) model could overcome the known accuracy limitations of the classical GMDH models that use only two inputs in each neuron from the adjacent layer. The proposed new non-linear GMDH-based method (named GS-GMDH) can improve the structure of the classical linear GMDH. The GS-GMDH model produced the most accurate forecasts in the Bow River case study with statistical indices such as the coefficient of determination and Nash-Sutcliffe for the daily discharge time series higher than 97% and relative error less than 6%. Finally, an explicit equation for estimation of the daily discharge of the Bow River is developed using the proposed GS-GMDH model to showcase the practical application of the new method in flood forecasting and management.

This paper analyzed the performance of the basic K-Means clustering algorithm with two major data pre-processing techniques and superlative similarity measure with automatic initialization of seed values on the dataset. Further experiment was conducted with simulated data sets to prove the accuracy of the new method. The new method presented in this paper gave a good and promising performance for the different types of data sets. The sum of the squares clustering errors reduced significantly for the new method as compared with basic K-Means method whereas inter-distances between clusters are preserved to be as large as possible for better clusters identification.

The application of metabolomics technology to epidemiological studies is emerging as a new approach to elucidate disease etiology and for biomarker discovery. However, analysis of metabolomics data is complex and there is an urgent need for the standardization of analysis workflow and reporting of study findings. To inform the development of such guidelines, we conducted a survey of 47 cohort representatives from the Consortium of Metabolomics Studies (COMETS) to gain insights into the current strategies and procedures used for analyzing metabolomics data in epidemiological studies worldwide. The results indicated a variety of applied analytical strategies, from biospecimen and data pre-processing and quality control to statistical analysis and reporting of study findings. These strategies included methods commonly used within the metabolomics community and applied in epidemiological research, as well as novel approaches to pre-processing pipelines and data analysis. To help with these discrepancies, we propose use of open-source initiatives such as the online web-based tool COMETS Analytics, which includes helpful tools to guide analytical workflow and the standardized reporting of findings from metabolomics analyses within epidemiological studies. Ultimately, this will improve the quality of statistical analyses, research findings, and study reproducibility.