Modeling three sources of uncertainty in assisted reproductive technologies with probabilistic graphical models

Embryo selection is a critical step in assisted reproduction: good selection criteria are expected to increase the probability of inducing a pregnancy. Machine learning techniques have been applied for implantation prediction or embryo quality assessment, which embryologists can use to make a decision about embryo selection. However, this is a highly uncertain real-world problem, and current proposals do not model always all the sources of uncertainty. We present a novel probabilistic graphical model that accounts for three different sources of uncertainty, the standard embryo and cycle viability, and a third one that represents any unknown factor that can drive a treatment to a failure in otherwise perfect conditions. We derive a parametric learning method based on the Expectation-Maximization strategy, which accounts for uncertainty issues. We empirically analyze the model within a real database consisting of 604 cycles (3125 embryos) carried out at Hospital Donostia (Spain). Embryologists followed the protocol of the Spanish Association for Reproduction Biology Studies (ASEBIR), based on morphological features, for embryo selection. Our model predictions are correlated with the ASEBIR protocol, which validates our model. The benefits of accounting for the different sources of uncertainty and the importance of the cycle characteristics are shown. Considering only transferred embryos, our model does not further discriminate them as implanted or failed, suggesting that the ASEBIR protocol could be understood as a thorough summary of the available morphological features.

Computer-Aided Detection of COVID-19 from CT Images Based on Gaussian Mixture Model and Kernel Support Vector Machines Classifier

COVID-19 is a virus that has been declared an epidemic by the world health organization and causes more than 2 million deaths in the world. To achieve this, computer-aided automatic diagnosis systems are created on medical images. In this study, an image processing and machine learning-based method is proposed that enables segmenting of CT images taken from COVID-19 patients and automatic detection of the virus through the segmented images. The main purpose of the study is to automatically diagnose the COVID-19 virus. The study consists of three basic steps: preprocessing, segmentation and classification. Image resizing, image sharpening, noise removal, contrast stretching processes are included in the preprocessing phase and segmentation of images with Expectation–Maximization-based Gaussian Mixture Model in the segmentation phase. In the classification stage, COVID-19 is classified as positive and negative by using kNN, decision tree, and two different ensemble methods together with the kernel support vector machines method. In the study, two different CT datasets that are open to the public and a mixed dataset created by combining these datasets were used. The best accuracy values for Dataset-1, Dataset-2 and Mixed Dataset are 98.5%, 86.3%, 94.5%, respectively. The achieved results prove that the proposed approach advances state-of-the-art performance. Within the scope of the study, a GUI that can automatically detect COVID-19 has been created.

Patch-based augmentation of Expectation-Maximization for brain MRI tissue segmentation at arbitrary age after premature birth

Accurate automated tissue segmentation of premature neonatal magnetic resonance images is a crucial task for quantification of brain injury and its impact on early postnatal growth and later cognitive development. In such studies it is common for scans to be acquired shortly after birth or later during the hospital stay and therefore occur at arbitrary gestational ages during a period of rapid developmental change. It is important to be able to segment any of these scans with comparable accuracy. Previous work on brain tissue segmentation in premature neonates has focused on segmentation at specific ages. Here we look at solving the more general problem using adaptations of age specific atlas based methods and evaluate this using a unique manually traced database of high resolution images spanning 20 gestational weeks of development. We examine the complimentary strengths of age specific atlas-based Expectation-Maximization approaches and patch-based methods for this problem and explore the development of two new hybrid techniques, patch-based augmentation of Expectation-Maximization with weighted fusion and a spatial variability constrained patch search. The former approach seeks to combine the advantages of both atlas- and patch-based methods by learning from the performance of the two techniques across the brain anatomy at different developmental ages, while the latter technique aims to use anatomical variability maps learnt from atlas training data to locally constrain the patch-based search range. The proposed approaches were evaluated using leave-one-out cross-validation. Compared with the conventional age specific atlas-based segmentation and direct patch based segmentation, both new approaches demonstrate improved accuracy in the automated labeling of cortical gray matter, white matter, ventricles and sulcal cortical-spinal fluid regions, while maintaining comparable results in deep gray matter.

Estimation of the serial interval of pertussis in Dutch households

Increasing incidence has led to the re-appearance of pertussis as a public health problem in developed countries. Pertussis infection is usually mild in vaccinated children and adults, but it can be fatal in infants who are too young for effective vaccination (≤3 months). Tailoring of control strategies to prevent infection of the infant hinges on the availability of estimates of key epidemiological quantities. Here we estimate the serial interval of pertussis, i.e., the time between symptoms onset in a case and its infector, using data from a household-based study carried out in the Netherlands in 2007-2009. We use statistical methodology to tie infected persons to probable infector persons, and obtain statistically supported stratifications of the data by person-type (infant, mother, father, sibling). The analyses show that the mean serial interval is 20 days (95% CI: 16-23 days) when the mother is the infector of the infant, and 28 days (95% CI: 23-33 days) when the infector is the father or a sibling. These time frames offer opportunities for early mitigation of the consequences of infection of an infant once a case has been detected in a household. If preventive measures such as social distancing or antimicrobial treatment are taken promptly they could decrease the probability of infection of the infant.

Mixture models for single-cell assays with applications to vaccine studies

Blood and tissue are composed of many functionally distinct cell subsets. In immunological studies, these can be measured accurately only using single-cell assays. The characterization of these small cell subsets is crucial to decipher system-level biological changes. For this reason, an increasing number of studies rely on assays that provide single-cell measurements of multiple genes and proteins from bulk cell samples. A common problem in the analysis of such data is to identify biomarkers (or combinations of biomarkers) that are differentially expressed between two biological conditions (e.g. before/after stimulation), where expression is defined as the proportion of cells expressing that biomarker (or biomarker combination) in the cell subset(s) of interest. Here, we present a Bayesian hierarchical framework based on a beta-binomial mixture model for testing for differential biomarker expression using single-cell assays. Our model allows the inference to be subject specific, as is typically required when assessing vaccine responses, while borrowing strength across subjects through common prior distributions. We propose two approaches for parameter estimation: an empirical-Bayes approach using an Expectation-Maximization algorithm and a fully Bayesian one based on a Markov chain Monte Carlo algorithm. We compare our method against classical approaches for single-cell assays including Fisher's exact test, a likelihood ratio test, and basic log-fold changes. Using several experimental assays measuring proteins or genes at single-cell level and simulations, we show that our method has higher sensitivity and specificity than alternative methods. Additional simulations show that our framework is also robust to model misspecification. Finally, we demonstrate how our approach can be extended to testing multivariate differential expression across multiple biomarker combinations using a Dirichlet-multinomial model and illustrate this approach using single-cell gene expression data and simulations.