MRI radiomics in the prediction of the volumetric response in meningiomas after gamma knife radiosurgery.

PURPOSE: This report presents the first investigation of the radiomics value in predicting the meningioma volumetric response to gamma knife radiosurgery (GKRS). METHODS: The retrospective study included 93 meningioma patients imaged by three Tesla MRI. Tumor morphology was quantified by calculating 337 shape, first- and second-order radiomic features from MRI obtained before GKRS. Analysis was performed on original 3D MR images and after their laplacian of gaussian (LoG), logarithm and exponential filtering. The prediction performance was evaluated by Pearson correlation, linear regression and ROC analysis, with meningioma volume change per month as the outcome. RESULTS: Sixty calculated features significantly correlated with the outcome. The feature selection based on LASSO and multivariate regression started from all available 337 radiomic and 12 non-radiomic features. It selected LoG-sigma-1-0-mm-3D_firstorder_InterquartileRange and logarithm_ngtdm_Busyness as the predictively most robust and non-redundant features. The radiomic score based on these two features produced an AUC = 0.81. Adding the non-radiomic karnofsky performance status (KPS) to the score has increased the AUC to 0.88. Low values of the radiomic score defined a homogeneous subgroup of 50 patients with consistent absence (0%) of tumor progression. CONCLUSION: This is the first report of a strong association between MRI radiomic features and volumetric meningioma response to radiosurgery. The clinical importance of the early and reliable prediction of meningioma responsiveness to radiosurgery is based on its potential to aid individualized therapy decision making.

Statistical and Machine Learning Link Selection Methods for Brain Functional Networks: Review and Comparison.

Network-based representations have introduced a revolution in neuroscience, expanding the understanding of the brain from the activity of individual regions to the interactions between them. This augmented network view comes at the cost of high dimensionality, which hinders both our capacity of deciphering the main mechanisms behind pathologies, and the significance of any statistical and/or machine learning task used in processing this data. A link selection method, allowing to remove irrelevant connections in a given scenario, is an obvious solution that provides improved utilization of these network representations. In this contribution we review a large set of statistical and machine learning link selection methods and evaluate them on real brain functional networks. Results indicate that most methods perform in a qualitatively similar way, with NBS (Network Based Statistics) winning in terms of quantity of retained information, AnovaNet in terms of stability and ExT (Extra Trees) in terms of lower computational cost. While machine learning methods are conceptually more complex than statistical ones, they do not yield a clear advantage. At the same time, the high heterogeneity in the set of links retained by each method suggests that they are offering complementary views to the data. The implications of these results in neuroscience tasks are finally discussed.

Is there an association between paternal age and aneuploidy? Evidence from young donor oocyte-derived embryos: a systematic review and individual patient data meta-analysis.

BACKGROUND: Delayed parenthood, by both women and men, has become more common in developed countries. The adverse effect of advanced maternal age on embryo aneuploidy and reproductive outcomes is well known. However, whether there is an association between paternal age (PA) and embryonic chromosomal aberrations remains controversial. Oocyte donation (OD) is often utilized to minimize maternal age effects on oocyte and embryo aneuploidy, thus providing an optimal model to assess the effect of PA. Several studies have revealed a higher than expected rate of aneuploidy in embryos derived from young oocyte donors, which warrants examination as to whether this may be attributed to advanced PA (APA). OBJECTIVE AND RATIONALE: The objective of this systematic review and individual patient data (IPD) meta-analysis is to evaluate existing evidence regarding an association between PA and chromosomal aberrations in an OD model. SEARCH METHODS: This review was conducted according to PRISMA guidelines for systematic reviews and meta-analyses. Medline, Embase and Cochrane databases were searched from inception through March 2020 using the (MeSH) terms: chromosome aberrations, preimplantation genetic screening and IVF. Original research articles, reporting on the types and/or frequency of chromosomal aberrations in embryos derived from donor oocytes, including data regarding PA, were included. Studies reporting results of IVF cycles using only autologous oocytes were excluded. Quality appraisal of included studies was conducted independently by two reviewers using a modified Newcastle-Ottawa Assessment Scale. A one-stage IPD meta-analysis was performed to evaluate whether an association exists between PA and aneuploidy. Meta-analysis was performed using a generalized linear mixed model to account for clustering of embryos within patients and clustering of patients within studies. OUTCOMES: The search identified 13 032 references, independently screened by 2 reviewers, yielding 6 studies encompassing a total of 2637 IVF-OD cycles (n = 20 024 embryos). Two 'low' quality studies using FISH to screen 12 chromosomes on Day 3 embryos (n = 649) reported higher total aneuploidy rates and specifically higher rates of trisomy 21, 18 and 13 in men ≥50 years. One 'moderate' and three 'high' quality studies, which used 24-chromosome screening, found no association between PA and aneuploidy in Day 5/6 embryos (n = 12 559). The IPD meta-analysis, which included three 'high' quality studies (n = 10 830 Day 5/6 embryos), found no significant effect of PA on the rate of aneuploidy (odds ratio (OR) 0.97 per decade of age, 95% CI 0.91-1.03), which was robust to sensitivity analyses. There was no association between PA and individual chromosome aneuploidy or segmental aberrations, including for chromosomes X and Y (OR 1.06 per decade of age, 95% CI 0.92-1.21). Monosomy was most frequent for chromosome 16 (217/10802, 2.01%, 95% CI 1.76-2.29%) and trisomy was also most frequent for chromosome 16 (194/10802, 1.80%, 95% CI 1.56-2.06%). WIDER IMPLICATIONS: We conclude, based on the available evidence, that APA is not associated with higher rates of aneuploidy in embryos derived from OD. These results will help fertility practitioners when providing preconception counselling, particularly to older men who desire to have a child.

SHOPIN: Semantic Homogeneity Optimization in Protein Interaction Networks.

Protein interaction networks (PINs) are argued to be the richest source of hidden knowledge of the intrinsic physical and/or functional meanings of the involved proteins. We propose a novel method for computational protein function prediction based on semantic homogeneity optimization in PIN (SHOPIN). The SHOPIN method creates graph representations of the PIN augmented by inclusion of the semantics of the proteins and their interacting contexts. Network wide semantic relationships, modeled using random walks, are used to map the augmented PIN graphs in a new semantic metric space. The method produces a hierarchical partitioning of the PIN optimal in terms of semantic homogeneity by iterative optimization of the ratio of between clusters dissimilarities and within clusters similarities in the new semantic metric space. Function prediction is done using cluster wide-hierarchy high function enrichment. Results validate the rationale of the SHOPIN method placing it right next to state-of-the-art approaches performance wise.

Exploring function prediction in protein interaction networks via clustering methods.

Complex networks have recently become the focus of research in many fields. Their structure reveals crucial information for the nodes, how they connect and share information. In our work we analyze protein interaction networks as complex networks for their functional modular structure and later use that information in the functional annotation of proteins within the network. We propose several graph representations for the protein interaction network, each having different level of complexity and inclusion of the annotation information within the graph. We aim to explore what the benefits and the drawbacks of these proposed graphs are, when they are used in the function prediction process via clustering methods. For making this cluster based prediction, we adopt well established approaches for cluster detection in complex networks using most recent representative algorithms that have been proven as efficient in the task at hand. The experiments are performed using a purified and reliable Saccharomyces cerevisiae protein interaction network, which is then used to generate the different graph representations. Each of the graph representations is later analysed in combination with each of the clustering algorithms, which have been possibly modified and implemented to fit the specific graph. We evaluate results in regards of biological validity and function prediction performance. Our results indicate that the novel ways of presenting the complex graph improve the prediction process, although the computational complexity should be taken into account when deciding on a particular approach.