Search

Abstract The escalating prevalence of insulin resistance (IR) and type 2 diabetes mellitus (T2D) underscores the urgent need for improved early detection techniques and effective treatment strategies. In this context, our study presents a proteomic analysis of post-exercise skeletal muscle biopsies from individuals across a spectrum of glucose metabolism states: normal, prediabetes, and T2D. This enabled the identification of significant protein relationships indicative of each specific glycemic condition. Our investigation primarily leveraged the machine learning approach, employing the white-box algorithm relative evolutionary hierarchical analysis (REHA), to explore the impact of regulated, mixed mode exercise on skeletal muscle proteome in subjects with diverse glycemic status. This method aimed to advance the diagnosis of IR and T2D and elucidate the molecular pathways involved in its development and the response to exercise. Additionally, we used proteomics-specific statistical analysis to provide a comparative perspective, highlighting the nuanced differences identified by REHA. Validation of the REHA model with a comparable external dataset further demonstrated its efficacy in distinguishing between diverse proteomic profiles. Key metrics such as accuracy and the area under the ROC curve confirmed REHA’s capability to uncover novel molecular pathways and significant protein interactions, offering fresh insights into the effects of exercise on IR and T2D pathophysiology of skeletal muscle. The visualizations not only underscored significant proteins and their interactions but also showcased decision trees that effectively differentiate between various glycemic states, thereby enhancing our understanding of the biomolecular landscape of T2D.

Abstract This paper presents a novel semi-automatic method for lung segmentation in thoracic CT datasets. The fully three-dimensional algorithm is based on a level set representation of an active surface and integrates texture features to improve its robustness. The method’s performance is enhanced by the graphics processing unit (GPU) acceleration. The segmentation process starts with a manual initialisation of 2D contours on a few representative slices of the analysed volume. Next, the starting regions for the active surface are generated according to the probability maps of texture features. The active surface is then evolved to give the final segmentation result. The recent implementation employs features based on grey-level co-occurrence matrices and Gabor filters. The algorithm was evaluated on real medical imaging data from the LCTCS 2017 challenge. The results were also compared with the outcomes of other segmentation methods. The proposed approach provided high segmentation accuracy while offering very competitive performance.

Abstract Metabolomics combined with machine learning methods (MLMs), is a powerful tool for searching novel diagnostic panels. This study was intended to use targeted plasma metabolomics and advanced MLMs to develop strategies for diagnosing brain tumors. Measurement of 188 metabolites was performed on plasma samples collected from 95 patients with gliomas (grade I–IV), 70 with meningioma, and 71 healthy individuals as a control group. Four predictive models to diagnose glioma were prepared using 10 MLMs and a conventional approach. Based on the cross-validation results of the created models, the F1-scores were calculated, then obtained values were compared. Subsequently, the best algorithm was applied to perform five comparisons involving gliomas, meningiomas, and controls. The best results were obtained using the newly developed hybrid evolutionary heterogeneous decision tree (EvoHDTree) algorithm, which was validated using Leave-One-Out Cross-Validation, resulting in an F1-score for all comparisons in the range of 0.476–0.948 and the area under the ROC curves ranging from 0.660 to 0.873. Brain tumor diagnostic panels were constructed with unique metabolites, which reduces the likelihood of misdiagnosis. This study proposes a novel interdisciplinary method for brain tumor diagnosis based on metabolomics and EvoHDTree, exhibiting significant predictive coefficients.

This article presents a novel three-dimensional level set method for the segmentation of textured volumes. The algorithm combines sparse and multi-resolution schemes to speed up computations and utilise the multi-scale nature of extracted texture features. The method's performance is also enhanced by graphics processing unit (GPU) acceleration. The segmentation process starts with an initial surface at the coarsest resolution of the input volume and moves to progressively higher scales. The surface evolution is driven by a generalised data term that can consider multiple feature types and is not tied to specific descriptors. The proposed implementation of this approach uses features based on grey level co-occurrence matrices and discrete wavelet transform. Quantitative results from experiments performed on synthetic volumes showed a significant improvement in segmentation quality over traditional methods. Qualitative validation using real-world medical datasets, and comparison with other similar GPU-based algorithms, were also performed. In all cases, the proposed implementation provided good segmentation accuracy while maintaining competitive performance.

A Relative Expression Analysis (RXA) uses ordering relationships in a small collection of genes and is successfully applied to classiffication using microarray data. As checking all possible subsets of genes is computationally infeasible, the RXA algorithms require feature selection and multiple restrictive assumptions. Our main contribution is a specialized evolutionary algorithm (EA) for top-scoring pairs called EvoTSP which allows finding more advanced gene relations. We managed to unify the major variants of relative expression algorithms through EA and introduce weights to the top-scoring pairs. Experimental validation of EvoTSP on public available microarray datasets showed that the proposed solution significantly outperforms in terms of accuracy other relative expression algorithms and allows exploring much larger solution space.