Evaluating the Impact of Different Factors on Voxel-Based Classification Methods of ADNI Structural MRI Brain Images

In this work we introduce the use of penalized logistic regression (PLR) to the problem of classification of MRI images and automatic detection of Alzheimer’s disease. Classification of sMRI is approached as a large scale regularization problem which uses voxels as input features. We evaluate how differences in sMRI pre-processing steps such as smoothing, normalization, and template selection affect the performance of high dimensional classification methods. 

In addition, we compared the relative performance of PLR to a different approach based on support vector machines. To study these questions we used data from the Alzheimer Disease Neuro imaging Initiative (ADNI). The ADNI project follows a protocol consisting of acquisition of two images in each session, image correction steps and further evaluation by experts to obtain the optimized images. We evaluated here the impact of this optimization process on the performance of high-dimensional machine learning techniques.

Meta-Analysis of Genomic Data: Between Strengths, Weaknesses and New Perspective

The rapid advances in high-throughput technologies, such as microarrays have revolutionizing the knowledge and understanding of biological systems and genetic signatures of human diseases. This has led to the generation and accumulation of a large amount of genomic data that need to beadequately integrated to obtain more reliable and valid results than those from individual experiments. Meta-analysis of microarray data is one of the most common statistical techniques used for combining multiple data sets. 

Despite its remarkable successes in discovering molecular subtypes, underlying pathways and biomarkers for the pathological process of interest, this method possesses several limitations. Here, we provided a briefly overview of current meta-analytic approaches together with the basic critical issues in performing meta-analysis of genomic data, with the aim of helping researchers to evaluate the quality of existing, published data and obtain more detailed information on what will be the best strategy to adopt to execute a good meta-analysis.