Molecular histopathology of matrix proteins through autofluorescence super-resolution microscopy.

Extracellular matrix diseases like fibrosis are elusive to diagnose early on, to avoid complete loss of organ function or even cancer progression, making early diagnosis crucial. Imaging the matrix densities of proteins like collagen in fixed tissue sections with suitable stains and labels is a standard for diagnosis and staging. However, fine changes in matrix density are difficult to realize by conventional histological staining and microscopy as the matrix fibrils are finer than the resolving capacity of these microscopes. The dyes further blur the outline of the matrix and add a background that bottlenecks high-precision early diagnosis of matrix diseases. Here we demonstrate the multiple signal classification method-MUSICAL-otherwise a computational super-resolution microscopy technique to precisely estimate matrix density in fixed tissue sections using fibril autofluorescence with image stacks acquired on a conventional epifluorescence microscope. We validated the diagnostic and staging performance of the method in extracted collagen fibrils, mouse skin during repair, and pre-cancers in human oral mucosa. The method enables early high-precision label-free diagnosis of matrix-associated fibrotic diseases without needing additional infrastructure or rigorous clinical training.

Detection of Neurogenic Voice Disorders Using the Fisher Vector Representation of Cepstral Features.

Neurogenic voice disorders (NVDs) are caused by damage or malfunction of the central or peripheral nervous system that controls vocal fold movement. In this paper, we investigate the potential of the Fisher vector (FV) encoding in automatic detection of people with NVDs. FVs are used to convert features from frame level (local descriptors) to utterance level (global descriptors). At the frame level, we extract two popular cepstral representations, namely, Mel-frequency cepstral coefficients (MFCCs) and perceptual linear prediction cepstral coefficients (PLPCCs), from acoustic voice signals. In addition, the MFCC features are also extracted from every frame of the glottal source signal computed using a glottal inverse filtering (GIF) technique. The global descriptors derived from the local descriptors are used to train a support vector machine (SVM) classifier. Experiments are conducted using voice signals from 80 healthy speakers and 80 patients with NVDs (40 with spasmodic dysphonia (SD) and 40 with recurrent laryngeal nerve palsy (RLNP)) taken from the Saarbruecken voice disorder (SVD) database. The overall results indicate that the use of the FV encoding leads to better identification of people with NVDs, compared to the defacto temporal encoding. Furthermore, the SVM trained using the combination of FVs derived from the cepstral and glottal features provides the overall best detection performance.

Identification and epidemiological characterization of Type-2 diabetes sub-population using an unsupervised machine learning approach.

BACKGROUND: Studies on Type-2 Diabetes Mellitus (T2DM) have revealed heterogeneous sub-populations in terms of underlying pathologies. However, the identification of sub-populations in epidemiological datasets remains unexplored. We here focus on the detection of T2DM clusters in epidemiological data, specifically analysing the National Family Health Survey-4 (NFHS-4) dataset from India containing a wide spectrum of features, including medical history, dietary and addiction habits, socio-economic and lifestyle patterns of 10,125 T2DM patients. METHODS: Epidemiological data provide challenges for analysis due to the diverse types of features in it. In this case, applying the state-of-the-art dimension reduction tool UMAP conventionally was found to be ineffective for the NFHS-4 dataset, which contains diverse feature types. We implemented a distributed clustering workflow combining different similarity measure settings of UMAP, for clustering continuous, ordinal and nominal features separately. We integrated the reduced dimensions from each feature-type-distributed clustering to obtain interpretable and unbiased clustering of the data. RESULTS: Our analysis reveals four significant clusters, with two of them comprising mainly of non-obese T2DM patients. These non-obese clusters have lower mean age and majorly comprises of rural residents. Surprisingly, one of the obese clusters had 90% of the T2DM patients practising a non-vegetarian diet though they did not show an increased intake of plant-based protein-rich foods. CONCLUSIONS: From a methodological perspective, we show that for diverse data types, frequent in epidemiological datasets, feature-type-distributed clustering using UMAP is effective as opposed to the conventional use of the UMAP algorithm. The application of UMAP-based clustering workflow for this type of dataset is novel in itself. Our findings demonstrate the presence of heterogeneity among Indian T2DM patients with regard to socio-demography and dietary patterns. From our analysis, we conclude that the existence of significant non-obese T2DM sub-populations characterized by younger age groups and economic disadvantage raises the need for different screening criteria for T2DM among rural Indian residents.

Arecanut-induced fibrosis display dual phases of reorganising glycans and amides in skin extracellular matrix.

The habit of chewing arecanut leads to fibrosis in the oral tissues, which can lead to cancer. Despite high mortality, fibrosis has limited clinical success owing to organ-specific variations, genetic predispositions, and slow progression. Fibrosis is a progressive condition that is unresponsive to medications in the severe phase. To understand underlying macromolecular changes we studied the extracellular matrix's (ECM) key molecular modifications in the early and late phase of arecanut-induced fibrosis in skin. To study the fibrosis, we topically applied arecanut extract on the mice skin. We observed that the matrix changes observe early and late phases based on ECM characteristics including the matrix proteins and the glycans. A spike in the levels of proteoglycans and ß-sheet structures are noted in the early phase. A significant drop in the proteoglycans and strengthening of amide covalent interactions is observed in the late phase. Although, almost no physical changes are noticeable only in the early phase; the late phase observes thick collagen bundling and a 4-fold stiffening of the skin tissue. The study indicates that the temporal interplay of proteins and glycans determine the matrix's severity state while opening avenues to research directed towards the phase-specific clinical discovery.

Relation Prediction of Co-Morbid Diseases Using Knowledge Graph Completion.

Co-morbid disease condition refers to the simultaneous presence of one or more diseases along with the primary disease. A patient suffering from co-morbid diseases possess more mortality risk than with a disease alone. So, it is necessary to predict co-morbid disease pairs. In past years, though several methods have been proposed by researchers for predicting the co-morbid diseases, not much work is done in prediction using knowledge graph embedding using tensor factorization. Moreover, the complex-valued vector-based tensor factorization is not being used in any knowledge graph with biological and biomedical entities. We propose a tensor factorization based approach on biological knowledge graphs. Our method introduces the concept of complex-valued embedding in knowledge graphs with biological entities. Here, we build a knowledge graph with disease-gene associations and their corresponding background information. To predict the association between prevalent diseases, we use ComplEx embedding based tensor decomposition method. Besides, we obtain new prevalent disease pairs using the MCL algorithm in a disease-gene-gene network and check their corresponding inter-relations using edge prediction task.

Structural mechanics modeling reveals stress-adaptive features of cutaneous scars.

The scar is a predominant outcome of adult mammalian wound healing despite being associated with partial function loss. Here in this paper, we have described the structure of a full-thickness normal scar as a "di-fork" with dual biomechanical compartments using in vivo and ex vivo experiments. We used structural mechanics simulations to model the deformation fields computationally and stress distribution in the scar in response to external forces. Despite its loss of tissue components, we have found that the scar has stress-adaptive features that cushion the underlying tissues from external mechanical impacts. Thus, this new finding can motivate research to understand the biomechanical advantages of a scar in maintaining the primary function of the skin, i.e., mechanical barrier despite permanent loss of some tissues and specialized functions.

Attenuation corrected-optical coherence tomography for quantitative assessment of skin wound healing and scar morphology.

Imaging the structural modifications of underlying tissues is vital to monitor wound healing. Optical coherence tomography (OCT) images high-resolution sub-surface information, but suffers a loss of intensity with depth, limiting quantification. Hence correcting the attenuation loss is important. We performed swept source-OCT of full-thickness excision wounds for 300 days in mice skin. We used single-scatter attenuation models to determine and correct the attenuation loss in the images. The phantom studies established the correspondence of corrected-OCT intensity (reflectivity) with matrix density and hydration. We histologically validated the corrected-OCT and measured the wound healing rate. We noted two distinct phases of healing-rapid and steady-state. We also detected two compartments in normal scars using corrected OCT that otherwise were not visible in the OCT scans. The OCT reflectivity in the scar compartments corresponded to distinct cell populations, mechanical properties and composition. OCT reflectivity has potential applications in evaluating the therapeutic efficacy of healing and characterizing scars.

Anatomical Structure Segmentation in Ultrasound Volumes Using Cross Frame Belief Propagating Iterative Random Walks.

Ultrasound (US) is widely used as a low-cost alternative to computed tomography or magnetic resonance and primarily for preliminary imaging. Since speckle intensity in US images is inherently stochastic, readers are often challenged in their ability to identify the pathological regions in a volume of a large number of images. This paper introduces a generalized approach for volumetric segmentation of structures in US images and volumes. We employ an iterative random walks (IRW) solver, a random forest learning model, and a gradient vector flow (GVF) based interframe belief propagation technique for achieving cross-frame volumetric segmentation. At the start, a weak estimate of the tissue structure is obtained using estimates of parameters of a statistical mechanics model of US tissue interaction. Ensemble learning of these parameters further using a random forest is used to initialize the segmentation pipeline. IRW is used for correcting the contour in various steps of the algorithm. Subsequently, a GVF-based interframe belief propagation is applied to adjacent frames based on the initialization of contour using information in the current frame to segment the complete volume by frame-wise processing. We have experimentally evaluated our approach using two different datasets. Intravascular ultrasound (IVUS) segmentation was evaluated using 10 pullbacks acquired at 20 MHz and thyroid US segmentation is evaluated on 16 volumes acquired at [Formula: see text] MHz. Our approach obtains a Jaccard score of [Formula: see text] for IVUS segmentation and [Formula: see text] for thyroid segmentation while processing each frame in [Formula: see text] for the IVUS and in [Formula: see text] for thyroid segmentation without the need of any computing accelerators such as GPUs.

Removal of Eye Blink Artifacts From EEG Signals Using Sparsity.

Neural activities recorded using electroencephalography (EEG) are mostly contaminated with eye blink (EB) artifact. This results in undesired activation of brain-computer interface (BCI) systems. Hence, removal of EB artifact is an important issue in EEG signal analysis. Of late, several artifact removal methods have been reported in the literature and they are based on independent component analysis (ICA), thresholding, wavelet transformation, etc. These methods are computationally expensive and result in information loss which makes them unsuitable for online BCI system development. To address the above problems, we have investigated sparsity-based EB artifact removal methods. Two sparsity-based techniques namely morphological component analysis (MCA) and K-SVD-based artifact removal method have been evaluated in our work. MCA-based algorithm exploits the morphological characteristics of EEG and EB using predefined Dirac and discrete cosine transform (DCT) dictionaries. Next, in K-SVD-based algorithm an overcomplete dictionary is learned from the EEG data itself and is designed to model EB characteristics. To substantiate the efficacy of the two algorithms, we have carried out our experiments with both synthetic and real EEG data. We observe that the K-SVD algorithm, which uses a learned dictionary, delivers superior performance for suppressing EB artifacts when compared to MCA technique. Finally, the results of both the techniques are compared with the recent state-of-the-art FORCe method. We demonstrate that the proposed sparsity-based algorithms perform equal to the state-of-the-art technique. It is shown that without using any computationally expensive algorithms, only with the use of over-complete dictionaries the proposed sparsity-based algorithms eliminate EB artifacts accurately from the EEG signals.

Modeling continuum of epithelial mesenchymal transition plasticity.

Living systems respond to ambient pathophysiological changes by altering their phenotype, a phenomenon called 'phenotypic plasticity'. This program contains information about adaptive biological dynamism. Epithelial-mesenchymal transition (EMT) is one such process found to be crucial in development, wound healing, and cancer wherein the epithelial cells with restricted migratory potential develop motile functions by acquiring mesenchymal characteristics. In the present study, phase contrast microscopy images of EMT induced HaCaT cells were acquired at 24 h intervals for 96 h. The expression study of relevant pivotal molecules viz. F-actin, vimentin, fibronectin and N-cadherin was carried out to confirm the EMT process. Cells were intuitively categorized into five distinct morphological phenotypes. A population of 500 cells for each temporal point was selected to quantify their frequency of occurrence. The plastic interplay of cell phenotypes from the observations was described as a Markovian process. A model was formulated empirically using simple linear algebra, to depict the possible mechanisms of cellular transformation among the five phenotypes. This work employed qualitative, semi-quantitative and quantitative tools towards illustration and establishment of the EMT continuum. Thus, it provides a newer perspective to understand the embedded plasticity across the EMT spectrum.

Automated in vivo delineation of lumen wall using intravascular ultrasound imaging.

This paper presents a novel methodology for automated detection and extraction of the lumen wall from Intravascular Ultrasound (IVUS) frames. IVUS is an in-vivo pull back imaging technique and provides a sequential frame of images for diagnosis of atherosclerotic heart disease. The detection and segmentation of lumen wall is necessary for predicting the arterial wall blockage. Lumen wall is recognized and segmented with the help of seed refinement and random walks algorithms, in tunica and lumen area. The proposed methodology was tested on 147 frames of 13 patients. Proposed method achieves significant performances for automated lumen wall detection and extraction as compared with existing literature.

Learning a Probabilistic Boolean Network model from biological pathways and time-series expression data.

The problem of inferring a stochastic model for gene regulatory networks is addressed here. The prior biological data includes biological pathways and time-series expression data. We propose a novel algorithm to use both of these data to construct a Probabilistic Boolean Network (PBN) which models the observed dynamics of genes with a high degree of precision. Our algorithm constructs a pathway tree and uses the time-series expression data to select an optimal level of tree, whose nodes are used to infer the PBN.

Graph-based unsupervised feature selection and multiview clustering for microarray data.

A challenge in bioinformatics is to analyse volumes of gene expression data generated through microarray experiments and obtain useful information. Consequently, most microarray studies demand complex data analysis to infer biologically meaningful information from such high-throughput data. Selection of informative genes is an important data analysis step to identify a set of genes which can further help in finding the biological information embedded in microarray data, and thus assists in diagnosis, prognosis and treatment of the disease. In this article we present an unsupervised feature selection technique which attempts to address the goal of explorative data analysis, unfolding the multi-faceted nature of data. It focuses on extracting multiple clustering views considering the diversity of each view from high-dimensional data. We evaluated our technique on benchmark data sets and the experimental results indicates the potential and effectiveness of the proposed model in comparison to the traditional single view clustering models, as well as other existing methods used in the literature for the studied datasets.

Deep neural network and random forest hybrid architecture for learning to detect retinal vessels in fundus images.

Vision impairment due to pathological damage of the retina can largely be prevented through periodic screening using fundus color imaging. However the challenge with large-scale screening is the inability to exhaustively detect fine blood vessels crucial to disease diagnosis. In this work we present a computational imaging framework using deep and ensemble learning based hybrid architecture for reliable detection of blood vessels in fundus color images. A deep neural network (DNN) is used for unsupervised learning of vesselness dictionaries using sparse trained denoising auto-encoders (DAE), followed by supervised learning of the DNN response using a random forest for detecting vessels in color fundus images. In experimental evaluation with the DRIVE database, we achieve the objective of vessel detection with max. avg. accuracy of 0.9327 and area under ROC curve of 0.9195.

Feature selection techniques for maximum entropy based biomedical named entity recognition.

Named entity recognition is an extremely important and fundamental task of biomedical text mining. Biomedical named entities include mentions of proteins, genes, DNA, RNA, etc which often have complex structures, but it is challenging to identify and classify such entities. Machine learning methods like CRF, MEMM and SVM have been widely used for learning to recognize such entities from an annotated corpus. The identification of appropriate feature templates and the selection of the important feature values play a very important role in the success of these methods. In this paper, we provide a study on word clustering and selection based feature reduction approaches for named entity recognition using a maximum entropy classifier. The identification and selection of features are largely done automatically without using domain knowledge. The performance of the system is found to be superior to existing systems which do not use domain knowledge.

A probabilistic active support vector learning algorithm.

The paper describes a probabilistic active learning strategy for support vector machine (SVM) design in large data applications. The learning strategy is motivated by the statistical query model. While most existing methods of active SVM learning query for points based on their proximity to the current separating hyperplane, the proposed method queries for a set of points according to a distribution as determined by the current separating hyperplane and a newly defined concept of an adaptive confidence factor. This enables the algorithm to have more robust and efficient learning capabilities. The confidence factor is estimated from local information using the k nearest neighbor principle. The effectiveness of the method is demonstrated on real-life data sets both in terms of generalization performance, query complexity, and training time.