Estimating Gender and Age from Brain Structural MRI of Children and Adolescents: A 3D Convolutional Neural Network Multitask Learning Model

Despite recent advances, assessing biological measurements for neuropsychiatric disorders is still a challenge, where confounding variables such as gender and age (as a proxy for neurodevelopment) play an important role. This study explores brain structural magnetic resonance imaging (sMRI) from two public data sets (ABIDE-II and ADHD-200) with healthy control (HC, N = 894), autism spectrum disorder (ASD, N = 251), and attention deficit hyperactivity disorder (ADHD, N = 357) individuals. We used gray and white matter preprocessed via voxel-based morphometry (VBM) to train a 3D convolutional neural network with a multitask learning strategy to estimate gender, age, and mental health status from structural brain differences. Gradient-based methods were employed to generate attention maps, providing clinically relevant identification of most representative brain regions for models’ decision-making. This approach resulted in satisfactory predictions for gender and age. ADHD-200-trained models, evaluated in 10-fold cross-validation procedures on test set, obtained a mean absolute error (MAE) of 1.43 years (±0.22 SD) for age prediction and an area under the curve (AUC) of 0.85 (±0.04 SD) for gender classification. In out-of-sample validation, the best-performing ADHD-200 models satisfactorily predicted age (MAE = 1.57 years) and gender (AUC = 0.89) in the ABIDE-II data set. The models’ accuracy was in line with the current state-of-the-art machine learning applications in neuroimaging. Key regions for models’ accuracy were presented as a meaningful graphical output. New implementations, such as the use of VBM along with a 3D convolutional neural network multitask learning model and a brain imaging graphical output, reinforce the relevance of the proposed workflow.

Very basic R syntax.

R is a programming language that has a huge range of inbuilt statistical and graphical functions. Firstly, this chapter shows how R works by talking you through a number of exercises, often producing graphical output, so you will get to know how to write simple code and become familiar with some of the most commonly used R functions for manipulating data and doing simple calculations. For ease, the chapter will firstly use a non-biological type of example. Thereafter, it will enter, display and analyse a number of real biological or medical datasets as might be obtained in student class experiments or fieldwork projects. Further on, it will present an outline of statistical tests appropriate to various types of data that you will come across.

Very basic R syntax.

R is a programming language that has a huge range of inbuilt statistical and graphical functions. Firstly, this chapter shows how R works by talking you through a number of exercises, often producing graphical output, so you will get to know how to write simple code and become familiar with some of the most commonly used R functions for manipulating data and doing simple calculations. For ease, the chapter will firstly use a non-biological type of example. Thereafter, it will enter, display and analyse a number of real biological or medical datasets as might be obtained in student class experiments or fieldwork projects. Further on, it will present an outline of statistical tests appropriate to various types of data that you will come across.

MendelianRandomization v0.5.0: updates to an R package for performing Mendelian randomization analyses using summarized data

The MendelianRandomization package is a software package written for the R software environment that implements methods for Mendelian randomization based on summarized data. In this manuscript, we describe functions that have been added to the package or updated in recent years. These features can be divided into four categories: robust methods for Mendelian randomization, methods for multivariable Mendelian randomization, functions for data visualization, and the ability to load data into the package seamlessly from the PhenoScanner web-resource. We provide examples of the graphical output produced by the data visualization commands, as well as syntax for obtaining suitable data and performing a Mendelian randomization analysis in a single line of code.

MendelianRandomization v0.5.0: updates to an R package for performing Mendelian randomization analyses using summarized data

The MendelianRandomization package is a software package written for the R software environment that implements methods for Mendelian randomization based on summarized data. In this manuscript, we describe functions that have been added to the package or updated in recent years. These features can be divided into four categories: robust methods for Mendelian randomization, methods for multivariable Mendelian randomization, functions for data visualization, and the ability to load data into the package seamlessly from the PhenoScanner web-resource. We provide examples of the graphical output produced by the data visualization commands, as well as syntax for obtaining suitable data and performing a Mendelian randomization analysis in a single line of code.

CytoConverter: a web-based tool to convert karyotypes to genomic coordinates

Background Cytogenetic nomenclature is used to describe chromosomal aberrations (or lack thereof) in a collection of cells, referred to as the cells’ karyotype. The nomenclature identifies locations on chromosomes using a system of cytogenetic bands, each with a unique name and region on a chromosome. Each band is microscopically visible after staining, and encompasses a large portion of the chromosome. More modern analyses employ genomic coordinates, which precisely specify a chromosomal location according to its distance from the end of the chromosome. Currently, there is no tool to convert cytogenetic nomenclature into genomic coordinates. Since locations of genes and other genomic features are usually specified by genomic coordinates, a conversion tool will facilitate the identification of the features that are harbored in the regions of chromosomal gain and loss that are implied by a karyotype. Results Our tool, termed CytoConverter, takes as input either a single karyotype or a file consisting of multiple karyotypes from several individuals. All net chromosomal gains and losses implied by the karyotype are returned in standard genomic coordinates, along with the numbers of cells harboring each aberration if included in the input. CytoConverter also returns graphical output detailing areas of gains and losses of chromosomes and chromosomal segments. Conclusions CytoConverter is available as a web-based application at https://jxw773.shinyapps.io/Cytogenetic__software/ and as an R script at https://sourceforge.net/projects/cytoconverter/. Supplemental Material detailing the underlying algorithms is available.

Evaluating amount of satisfaction for visit capabilities and infrastructures of Gorgan city in separation of touristic entrance regions

The general aim of this research is evaluating amount of satisfaction for visit capabilities and infrastructures of Gorgan city in separation of touristic entrance regions. This study is applicable and explanatory-analytical method is used for study. Used statistical community is consisting entered tourists from seven touristic regions to Gorgan. In this study, probabilistic multistage cluster sampling method was used. So after calculation of sample numbers by using Kokeran’s formula, some regions were selected as research sample from all of touristic absorptions and questionnaires randomly were distributed among them and then were gathered. Anova test, Danken test and the mean of visitor’s opinions were employed for analysis of data. Also the graphical output of data was depicted through Arc Map software. The findings of research showed that Gorgan tourists have announced unsatisfaction of themselves about capabilities and touristic infrastructures of this city. Nevertheless among different regions there is a meaningful disagreeability. Finally with consideration to operated evaluations about satisfactory condition of tourists related to capabilities and infrastructures of the city for improving situation, suitable solutions have been offered.