Search

NIR laser-induced photothermal therapy (PTT) through near-infrared agents has demonstrated the great potential in solid tumor ablation. However, the nonuniform heat distribution over tumors from PTT makes it insufficient to kill all tumor cells, resulting in tumor recurrence and inferior outcomes. To improve the tumor treatment efficacy, it is highly desirable to develop the combinational treatment of PTT with other modalities, especially with chemotherapeutic agents. Here we report a smart DOX/IR-780-loaded temperature-sensitive-liposome (DITSL) which can achieve NIR-laser-controlled drug release for chemo-photothermal synergistic tumor therapy. In this system, the liposoluble IR-780 was incorporated into the temperature-sensitive lipid bilayer and the soluble chemotherapeutic doxorubicin (DOX) was encapsulated in the hydrophilic core. The resulting DITSL is proved to be physiologically stable and can provide a fast and laser irradiation-controllable DOX release in the PBS and cellular conditions. We further employed this nanoparticle for tumor treatment, demonstrating significantly higher tumor inhibition efficacy than that of DOX-loaded temperature-sensitive-liposome (DTSL) or IR780-loaded temperature-sensitive-liposome (ITSL) in the in vitro cells and in vivo animals. Histological analysis further revealed much more apoptotic cells, confirming the advantageous anti-tumor effect of DITSL over DTSL or ITSL. Our study provides a promising strategy to realize chemo-photothermal synergistic combination therapy for breast tumors.

This paper establishes a fully automatic real-time image segmentation and recognition system for breast ultrasound intervention robots. It adopts the basic architecture of a U-shaped convolutional network (U-Net), analyses the actual application scenarios of semantic segmentation of breast ultrasound images, and adds dropout layers to the U-Net architecture to reduce the redundancy in texture details and prevent overfitting. The main innovation of this paper is proposing an expanded training approach to obtain an expanded of U-Net. The output map of the expanded U-Net can retain texture details and edge features of breast tumours. Using the grey-level probability labels to train the U-Net is faster than using ordinary labels. The average Dice coefficient (standard deviation) and the average IOU coefficient (standard deviation) are 90.5% (±0.02) and 82.7% (±0.02), respectively, when using the expanded training approach. The Dice coefficient of the expanded U-Net is 7.6 larger than that of a general U-Net, and the IOU coefficient of the expanded U-Net is 11 larger than that of the general U-Net. The context of breast ultrasound images can be extracted, and texture details and edge features of tumours can be retained by the expanded U-Net. Using an expanded U-Net can quickly and automatically achieve precise segmentation and multi-class recognition of breast ultrasound images.

Integrative clustering is used to identify groups of samples by jointly analysing multiple datasets describing the same set of biological samples, such as gene expression, copy number, methylation etc. Most existing algorithms for integrative clustering assume that there is a shared consistent set of clusters across all datasets, and most of the data samples follow this structure. However in practice, the structure across heterogeneous datasets can be more varied, with clusters being joined in some datasets and separated in others. In this paper, we present a probabilistic clustering method to identify groups across datasets that do not share the same cluster structure. The proposed algorithm, Clusternomics, identifies groups of samples that share their global behaviour across heterogeneous datasets. The algorithm models clusters on the level of individual datasets, while also extracting global structure that arises from the local cluster assignments. Clusters on both the local and the global level are modelled using a hierarchical Dirichlet mixture model to identify structure on both levels. We evaluated the model both on simulated and on real-world datasets. The simulated data exemplifies datasets with varying degrees of common structure. In such a setting Clusternomics outperforms existing algorithms for integrative and consensus clustering. In a real-world application, we used the algorithm for cancer subtyping, identifying subtypes of cancer from heterogeneous datasets. We applied the algorithm to TCGA breast cancer dataset, integrating gene expression, miRNA expression, DNA methylation and proteomics. The algorithm extracted clinically meaningful clusters with significantly different survival probabilities. We also evaluated the algorithm on lung and kidney cancer TCGA datasets with high dimensionality, again showing clinically significant results and scalability of the algorithm., Author summary Integrative clustering is the task of identifying groups of samples by combining information from several datasets. An example of this task is cancer subtyping, where we cluster tumour samples based on several datasets, such as gene expression, proteomics and others. Most existing algorithms assume that all such datasets share a similar cluster structure, with samples outside these clusters treated as noise. The structure can, however, be much more heterogeneous: some meaningful clusters may appear only in some datasets. In the paper, we introduce the Clusternomics algorithm that identifies groups of samples across heterogeneous datasets. It models both cluster structure of individual datasets, and the global structure that appears as a combination of local structures. The algorithm uses probabilistic modelling to identify the groups and share information across the local and global levels. We evaluated the algorithm on both simulated and real world datasets, where the algorithm found clinically significant clusters with different survival outcomes.

The ensemble method random forests has become a popular classification tool in bioinformatics and related fields. The out-of-bag error is an error estimation technique often used to evaluate the accuracy of a random forest and to select appropriate values for tuning parameters, such as the number of candidate predictors that are randomly drawn for a split, referred to as mtry. However, for binary classification problems with metric predictors it has been shown that the out-of-bag error can overestimate the true prediction error depending on the choices of random forests parameters. Based on simulated and real data this paper aims to identify settings for which this overestimation is likely. It is, moreover, questionable whether the out-of-bag error can be used in classification tasks for selecting tuning parameters like mtry, because the overestimation is seen to depend on the parameter mtry. The simulation-based and real-data based studies with metric predictor variables performed in this paper show that the overestimation is largest in balanced settings and in settings with few observations, a large number of predictor variables, small correlations between predictors and weak effects. There was hardly any impact of the overestimation on tuning parameter selection. However, although the prediction performance of random forests was not substantially affected when using the out-of-bag error for tuning parameter selection in the present studies, one cannot be sure that this applies to all future data. For settings with metric predictor variables it is therefore strongly recommended to use stratified subsampling with sampling fractions that are proportional to the class sizes for both tuning parameter selection and error estimation in random forests. This yielded less biased estimates of the true prediction error. In unbalanced settings, in which there is a strong interest in predicting observations from the smaller classes well, sampling the same number of observations from each class is a promising alternative.

MammoWave is a microwave imaging device for breast lesions detection, which operates using two (azimuthally rotating) antennas without any matching liquid. Images, subsequently obtained by resorting to Huygens Principle, are intensity maps, representing the homogeneity of tissues’ dielectric properties. In this paper, we propose to generate, for each breast, a set of conductivity weighted microwave images by using different values of conductivity in the Huygens Principle imaging algorithm. Next, microwave images’ parameters, i.e. features, are introduced to quantify the non-homogenous behaviour of the image. We empirically verify on 103 breasts that a selection of these features may allow distinction between breasts with no radiological finding (NF) and breasts with radiological findings (WF), i.e. with lesions which may be benign or malignant. Statistical significance was set at prule-of-thumb allowing breast assessment is introduced using a binary score S operating on an appropriate combination of features. Performances of such rule-of-thumb are evaluated empirically, obtaining a sensitivity of 74%, which increases to 82% when considering dense breasts only.

Identifying biomarkers that are associated with different types of cancer is an important goal in the field of bioinformatics. Different researcher groups have analyzed the expression profiles of many genes and found some certain genetic patterns that can promote the improvement of targeted therapies, but the significance of some genes is still ambiguous. More reliable and effective biomarkers identification methods are then needed to detect candidate cancer-related genes. In this paper, we proposed a novel method that combines the infinite latent feature selection (ILFS) method with the functional interaction (FIs) network to rank the biomarkers. We applied the proposed method to the expression data of five cancer types. The experiments indicated that our network-constrained ILFS (NCILFS) provides an improved prediction of the diagnosis of the samples and locates many more known oncogenes than the original ILFS and some other existing methods. We also performed functional enrichment analysis by inspecting the over-represented gene ontology (GO) biological process (BP) terms and applying the gene set enrichment analysis (GSEA) method on selected biomarkers for each feature selection method. The enrichments analysis reports show that our network-constraint ILFS can produce more biologically significant gene sets than other methods. The results suggest that network-constrained ILFS can identify cancer-related genes with a higher discriminative power and biological significance.

Elucidating the causal mechanisms responsible for disease can reveal potential therapeutic targets for pharmacological intervention and, accordingly, guide drug repositioning and discovery. In essence, the topology of a network can reveal the impact a drug candidate may have on a given biological state, leading the way for enhanced disease characterization and the design of advanced therapies. Network-based approaches, in particular, are highly suited for these purposes as they hold the capacity to identify the molecular mechanisms underlying disease. Here, we present drug2ways, a novel methodology that leverages multimodal causal networks for predicting drug candidates. Drug2ways implements an efficient algorithm which reasons over causal paths in large-scale biological networks to propose drug candidates for a given disease. We validate our approach using clinical trial information and demonstrate how drug2ways can be used for multiple applications to identify: i) single-target drug candidates, ii) candidates with polypharmacological properties that can optimize multiple targets, and iii) candidates for combination therapy. Finally, we make drug2ways available to the scientific community as a Python package that enables conducting these applications on multiple standard network formats., Author summary At any given time, a large set of biomolecules are interacting in ways that give rise to the normal functioning of a cell. By representing biological interactions as networks, we can reconstruct the complex molecular mechanisms that govern the physiology of a cell. These networks can then be analyzed to understand where the system fails and how that can give rise to disease. Similarly, using computational methods, we can also enrich these networks with drugs, diseases and disease phenotypes to estimate how a drug, or a combination of drugs, would behave in a system and whether it can be used to treat or alleviate the symptoms of a disease. In this paper, we present drug2ways, a novel methodology designed for drug discovery applications, that exploits the information contained in a biological network comprising causal relations between drugs, proteins, and diseases. Employing these networks and an efficient algorithm, drugways2 traverses over the ensemble of paths between a drug and a disease to propose the drugs that are most likely to cure the disease based on the information contained in the network. We hypothesize that this ensemble of paths could be used to simulate the mechanism of action of a drug and the directionality inferred through these paths could be used as a proxy to identify drug candidates. Through several experiments, we demonstrate how drug2ways can be used to find novel ways of using existing drugs, identify drug candidates, optimize treatments by targeting multiple disease phenotypes, and propose combination therapies. Owing to the generalizability of the algorithm and the accompanying software, we ambition that drug2ways could be applied to a variety of biological networks to generate new hypotheses for drug discovery and a better understanding of their mechanisms of action.

Deep learning has achieved a great success in natural image classification. To overcome data-scarcity in computational pathology, recent studies exploit transfer learning to reuse knowledge gained from natural images in pathology image analysis, aiming to build effective pathology image diagnosis models. Since transferability of knowledge heavily depends on the similarity of the original and target tasks, significant differences in image content and statistics between pathology images and natural images raise the questions: how much knowledge is transferable? Is the transferred information equally contributed by pre-trained layers? To answer these questions, this paper proposes a framework to quantify knowledge gain by a particular layer, conducts an empirical investigation in pathology image centered transfer learning, and reports some interesting observations. Particularly, compared to the performance baseline obtained by random-weight model, though transferability of off-the-shelf representations from deep layers heavily depend on specific pathology image sets, the general representation generated by early layers does convey transferred knowledge in various image classification applications. The observation in this study encourages further investigation of specific metric and tools to quantify effectiveness and feasibility of transfer learning in future., Comment: Experimentation data correction

Breast cancer prognosis is challenging due to the heterogeneity of the disease. Various computational methods using bulk RNA-seq data have been proposed for breast cancer prognosis. However, these methods suffer from limited performances or ambiguous biological relevance, as a result of the neglect of intra-tumor heterogeneity. Recently, single cell RNA-sequencing (scRNA-seq) has emerged for studying tumor heterogeneity at cellular levels. In this paper, we propose a novel method, scPrognosis, to improve breast cancer prognosis with scRNA-seq data. scPrognosis uses the scRNA-seq data of the biological process Epithelial-to-Mesenchymal Transition (EMT). It firstly infers the EMT pseudotime and a dynamic gene co-expression network, then uses an integrative model to select genes important in EMT based on their expression variation and differentiation in different stages of EMT, and their roles in the dynamic gene co-expression network. To validate and apply the selected signatures to breast cancer prognosis, we use them as the features to build a prediction model with bulk RNA-seq data. The experimental results show that scPrognosis outperforms other benchmark breast cancer prognosis methods that use bulk RNA-seq data. Moreover, the dynamic changes in the expression of the selected signature genes in EMT may provide clues to the link between EMT and clinical outcomes of breast cancer. scPrognosis will also be useful when applied to scRNA-seq datasets of different biological processes other than EMT., Author summary Various computational methods have been developed for breast cancer prognosis. However, those methods mainly use the gene expression data generated by the bulk RNA sequencing techniques, which average the expression level of a gene across different cell types. As breast cancer is a heterogenous disease, the bulk gene expression may not be the ideal resource for cancer prognosis. In this study, we propose a novel method to improve breast cancer prognosis using scRNA-seq data. The proposed method has been applied to the EMT scRNA-seq dataset for identifying breast cancer signatures for prognosis. In comparison with existing bulk expression data based methods in breast cancer prognosis, our method shows a better performance. Our single-cell-based signatures provide clues to the relation between EMT and clinical outcomes of breast cancer. In addition, the proposed method can also be useful when applied to scRNA-seq datasets of different biological processes other than EMT.

This paper identifies prognosis factors for survival in patients with acute myeloid leukemia (AML) using machine learning techniques. We have integrated machine learning with feature selection methods and have compared their performances to identify the most suitable factors in assessing the survival of AML patients. Here, six data mining algorithms including Decision Tree, Random Forrest, Logistic Regression, Naive Bayes, W-Bayes Net, and Gradient Boosted Tree (GBT) are employed for the detection model and implemented using the common data mining tool RapidMiner and open-source R package. To improve the predictive ability of our model, a set of features were selected by employing multiple feature selection methods. The accuracy of classification was obtained using 10-fold cross-validation for the various combinations of the feature selection methods and machine learning algorithms. The performance of the models was assessed by various measurement indexes including accuracy, kappa, sensitivity, specificity, positive predictive value, negative predictive value, and area under the ROC curve (AUC). Our results showed that GBT with an accuracy of 85.17%, AUC of 0.930, and the feature selection via the Relief algorithm has the best performance in predicting the survival rate of AML patients.

Immune checkpoint inhibitors have demonstrated, over the recent years, impressive clinical response in cancer patients, but some patients do not respond at all to checkpoint blockade, exhibiting primary resistance. Primary resistance to PD-1 blockade is reported to occur under conditions of immunosuppressive tumor environment, a condition caused by myeloid derived suppressor cells (MDSCs), and by T cells exclusion, due to increased level of T regulatory cells (Tregs). Since TGF-β activates Tregs, TGF-β inhibitor may overcome primary resistance to anti-PD-1. Indeed, recent mice experiments show that combining anti-PD-1 with anti-TGF-β yields significant therapeutic improvements compared to anti-TGF-β alone. The present paper introduces two cancer-specific parameters and, correspondingly, develops a mathematical model which explains how primary resistance to PD-1 blockade occurs, in terms of the two cancer-specific parameters, and how, in combination with anti-TGF-β, anti-PD-1 provides significant benefits. The model is represented by a system of partial differential equations and the simulations are in agreement with the recent mice experiments. In some cancer patients, treatment with anti-PD-1 results in rapid progression of the disease, known as hyperprogression disease (HPD). The mathematical model can also explain how this situation arises, and it predicts that HPD may be reversed by combining anti-TGF-β to anti-PD-1. The model is used to demonstrate how the two cancer-specific parameters may serve as biomarkers in predicting the efficacy of combination therapy with PD-1 and TGF-β inhibitors.

Tumor emergence and progression is a complex phenomenon that assumes special molecular and cellular interactions. The hierarchical structuring and communication via feedback signaling of different cell types, which are categorized as the stem, progenitor, and differentiated cells in dependence of their maturity level, plays an important role. Under healthy conditions, these cells build a dynamical system that is responsible for facilitating the homeostatic regulation of the tissue. Generally, in this hierarchical setting, stem and progenitor cells are yet likely to undergo a mutation, when a cell divides into two daughter cells. This may lead to the development of abnormal characteristics, i.e. mutation in the cell, yielding an unrestrained number of cells. Therefore, the regulation of a stem cell’s proliferation and differentiation rate is crucial for maintaining the balance in the overall cell population. In this paper, a maturity based mathematical model with feedback regulation is formulated for healthy and mutated cell lineages. It is given in the form of coupled ordinary and partial differential equations. The focus is laid on the dynamical effects resulting from acquiring a mutation in the hierarchical structure of stem, progenitor and fully differentiated cells. Additionally, the effects of nonlinear feedback regulation from mature cells into both stem and progenitor cell populations have been inspected. The steady-state solutions of the model are derived analytically. Numerical simulations and results based on a finite volume scheme underpin various expected behavioral patterns of the homeostatic regulation and cancer evolution. For instance, it has been found that the mutated cells can experience significant growth even with a single somatic mutation, but under homeostatic regulation acquire a steady-state and thus, ensuing healthy cell population to either a steady-state or a lower cell concentration. Furthermore, the model behavior has been validated with different experimentally measured tumor values from the literature.

Pathologists generally pan, focus, zoom and scan tissue biopsies either under microscopes or on digital images for diagnosis. With the rapid development of whole-slide digital scanners for histopathology, computer-assisted digital pathology image analysis has attracted increasing clinical attention. Thus, the working style of pathologists is also beginning to change. Computer-assisted image analysis systems have been developed to help pathologists perform basic examinations. This paper presents a novel lightweight detection framework for automatic tumor detection in whole-slide histopathology images. We develop the Double Magnification Combination (DMC) classifier, which is a modified DenseNet-40 to make patch-level predictions with only 0.3 million parameters. To improve the detection performance of multiple instances, we propose an improved adaptive sampling method with superpixel segmentation and introduce a new heuristic factor, local sampling density, as the convergence condition of iterations. In postprocessing, we use a CNN model with 4 convolutional layers to regulate the patch-level predictions based on the predictions of adjacent sampling points and use linear interpolation to generate a tumor probability heatmap. The entire framework was trained and validated using the dataset from the Camelyon16 Grand Challenge and Hubei Cancer Hospital. In our experiments, the average AUC was 0.95 in the test set for pixel-level detection.

This study aims to analyze the formation of the frame of breast cancer research. To test our hypothesis that the research frame depends on the funding sources, we collected the abstracts of 48,448 breast cancer research papers from PubMed and applied structural topic modeling, word network analysis, and LASSO logistic regression to the data. In particular, we analyzed the relationship between funding sources and the molecularization of breast cancer knowledge. The results show that government-funded research is likely to have molecular objects or population as the unit of interest, whereas the research not funded by the government is likely to have individual patients as the unit of interest in relation to specific treatments. This phenomenon is attributed to the different interests of government institutions and the private sector. This study improves our understanding of molecularization and medical knowledge production.

The aim of this paper is to analyze the sequence of actions in the health system associated with a particular disease. In order to do that, using Electronic Health Records, we define a general methodology that allows us to: (I) identify the actions in the health system associated with a disease; (ii) identify those patients with a complete treatment for the disease; (iii) and discover common treatment pathways followed by the patients with a specific diagnosis. The methodology takes into account the characteristics of the EHRs, such as record heterogeneity and missing information. As an example, we use the proposed methodology to analyze breast cancer disease. For this diagnosis, 5 groups of treatments, which fit in with medical practice guidelines and expert knowledge, were obtained., Artificial Intelligence in BCAM number EXP. 2019/00432, PID2019-104966GB-I00, TIN2016-78365-R, IT1244-19.

Deconvolution of heterogeneous bulk tumor samples into distinct cellular populations is an important yet challenging problem, particularly when only partial references are available. A common approach to dealing with this problem is to deconvolve the mixed signals using available references and leverage the remaining signal as a new cell component. However, as indicated in our simulation, such an approach tends to over-estimate the proportions of known cell types and fails to detect novel cell types. Here, we propose PREDE, a partial reference-based deconvolution method using an iterative non-negative matrix factorization algorithm. Our method is verified to be effective in estimating cell proportions and expression profiles of unknown cell types based on simulated datasets at a variety of parameter settings. Applying our method to TCGA tumor samples, we found that proportions of pure cancer cells better indicate different subtypes of tumor samples. We also detected several cell types for each cancer type whose proportions successfully predicted patient survival. Our method makes a significant contribution to deconvolution of heterogeneous tumor samples and could be widely applied to varieties of high throughput bulk data. PREDE is implemented in R and is freely available from GitHub (https://xiaoqizheng.github.io/PREDE)., Author summary Tumor tissues are mixtures of different cell types. Identification and quantification of constitutional cell types within tumor tissues are important tasks in cancer research. The problem can be readily solved using regression-based methods if reference signals are available. But in most clinical applications, only partial references are available, which significantly reduces the deconvolution accuracy of the existing regression-based methods. In this paper, we propose a partial-reference based deconvolution model, PREDE, integrating the non-negative matrix factorization framework with an iterative optimization strategy. We conducted comprehensive evaluations for PREDE using both simulation and real data analyses, demonstrating better performance of our method than other existing methods.

Breast cancer is the most common cancer among women and it is one of the main causes of death for women worldwide. To attain an optimum medical treatment for breast cancer, an early breast cancer detection is crucial. This paper proposes a multi- stage feature selection method that extracts statistically significant features for breast cancer size detection using proposed data normalization techniques. Ultra-wideband (UWB) signals, controlled using microcontroller are transmitted via an antenna from one end of the breast phantom and are received on the other end. These ultra-wideband analogue signals are represented in both time and frequency domain. The preprocessed digital data is passed to the proposed multi- stage feature selection algorithm. This algorithm has four selection stages. It comprises of data normalization methods, feature extraction, data dimensional reduction and feature fusion. The output data is fused together to form the proposed datasets, namely, 8-HybridFeature, 9-HybridFeature and 10-HybridFeature datasets. The classification performance of these datasets is tested using the Support Vector Machine, Probabilistic Neural Network and Naïve Bayes classifiers for breast cancer size classification. The research findings indicate that the 8-HybridFeature dataset performs better in comparison to the other two datasets. For the 8-HybridFeature dataset, the Naïve Bayes classifier (91.98%) outperformed the Support Vector Machine (90.44%) and Probabilistic Neural Network (80.05%) classifiers in terms of classification accuracy. The finalized method is tested and visualized in the MATLAB based 2D and 3D environment.

For studying cancer and genetic diseases, the issue of identifying high correlation genes from high-dimensional data is an important problem. It is a great challenge to select relevant biomarkers from gene expression data that contains some important correlation structures, and some of the genes can be divided into different groups with a common biological function, chromosomal location or regulation. In this paper, we propose a penalized accelerated failure time model CHR-DE using a non-convex regularization (local search) with differential evolution (global search) in a wrapper-embedded memetic framework. The complex harmonic regularization (CHR) can approximate to the combination [Formula: see text] and ℓq (1 ≤ q < 2) for selecting biomarkers in group. And differential evolution (DE) is utilized to globally optimize the CHR's hyperparameters, which make CHR-DE achieve strong capability of selecting groups of genes in high-dimensional biological data. We also developed an efficient path seeking algorithm to optimize this penalized model. The proposed method is evaluated on synthetic and three gene expression datasets: breast cancer, hepatocellular carcinoma and colorectal cancer. The experimental results demonstrate that CHR-DE is a more effective tool for feature selection and learning prediction.

Successful breast conserving cancer surgeries come along with tumor free resection margins and account for cosmetic outcome. Positive margins increase the likelihood of tumor recurrence. Intra-operative fluorescence molecular imaging (IFMI) aims to focus surgery on malignant tissue thus substantially lowering the presence of positive margins as compared with standard techniques of breast conservation (ST). A goal of this paper is to assess the incremental number of surgeries and costs of IFMI vs. ST. METHODS: We developed a decision analytical model and applied it for an early evaluation approach. Given uncertainty we considered that IFMI might reduce the proportion of positive margins found by ST from all to none and this proportion is assumed to be reduced to 10% for the base case. Inputs included data from the literature and a range of effect estimates. For the costs of IFMI, respective cost components were added to those of ST. RESULTS: The base case reduction lowered number of surgeries (mean [95% confidence interval]) by 0.22 [0.15; 0.30] and changed costs (mean [95% confidence interval]) by €-663 [€-1,584; €50]. A tornado diagram identified the Diagnosis Related Group (DRG) costs, the proportion of positive margins of ST, the staff time saving factor and the duration of frozen section analysis (FSA) as important determinants of this cost. CONCLUSIONS: These early results indicate that IFMI may be more effective than ST and through the reduction of positive margins it is possible to save follow-up surgeries-indicating further health risk-and to save costs through this margin reduction and the avoidance of FSA.

In this paper we address the problem of automated grading of invasive breast carcinoma through the encoding of histological images as VLAD (Vector of Locally Aggregated Descriptors) representations on the Grassmann manifold. The proposed method considers each image as a set of multidimensional spatially-evolving signals that can be efficiently modeled through a higher-order linear dynamical systems analysis. Subsequently, each H&E (Hematoxylin and Eosin) stained breast cancer histological image is represented as a cloud of points on the Grassmann manifold, while a vector representation approach is applied aiming to aggregate the Grassmannian points based on a locality criterion on the manifold. To evaluate the efficiency of the proposed methodology, two datasets with different characteristics were used. More specifically, we created a new medium-sized dataset consisting of 300 annotated images (collected from 21 patients) of grades 1, 2 and 3, while we also provide experimental results using a large dataset, namely BreaKHis, containing 7,909 breast cancer histological images, collected from 82 patients, of both benign and malignant cases. Experimental results have shown that the proposed method outperforms a number of state of the art approaches providing average classification rates of 95.8% and 91.38% with our dataset and the BreaKHis dataset, respectively.

Breast cancer is a common gynecological disease that poses a great threat to women health due to its high malignant rate. Breast cancer screening tests are used to find any warning signs or symptoms for early detection and currently, Ultrasound screening is the preferred method for breast cancer diagnosis. The localization and segmentation of the lesions in breast ultrasound (BUS) images are helpful for clinical diagnosis of the disease. In this paper, an RDAU-NET (Residual-Dilated-Attention-Gate-UNet) model is proposed and employed to segment the tumors in BUS images. The model is based on the conventional U-Net, but the plain neural units are replaced with residual units to enhance the edge information and overcome the network performance degradation problem associated with deep networks. To increase the receptive field and acquire more characteristic information, dilated convolutions were used to process the feature maps obtained from the encoder stages. The traditional cropping and copying between the encoder-decoder pipelines were replaced by the Attention Gate modules which enhanced the learning capabilities through suppression of background information. The model, when tested with BUS images with benign and malignant tumor presented excellent segmentation results as compared to other Deep Networks. A variety of quantitative indicators including Accuracy, Dice coefficient, AUC(Area-Under-Curve), Precision, Sensitivity, Specificity, Recall, F1score and M-IOU (Mean-Intersection-Over-Union) provided performances above 80%. The experimental results illustrate that the proposed RDAU-NET model can accurately segment breast lesions when compared to other deep learning models and thus has a good prospect for clinical diagnosis.

BackgroundMalignant diseases have been believed to be more common in some areas of Eastern Morocco, but until now, cancer patterns have not been reported for this region. In this paper we present for the first time the cancer prevalence analysis in Eastern Morocco.MethodsCross-sectional study carried out among all patients diagnosed and/or treated with cancer at the Hassan II Regional Oncology Center (ROC) since it was established in October 2005 until December 2012. The ROC is the only hospital specialized in cancer care in Eastern Morocco.ResultsA total of 8,508 cases of cancer were registered among residents in Eastern Morocco, with a female to male ratio of 2.1. The mean age at diagnosis was 53.9 ± 15.2 years (median age = 53 years). Thus, unlike in Western countries, cancer in Eastern Morocco afflicts younger population. The areas of Eastern Morocco did not differ significantly by mean age at diagnosis (p = 0.061). However, these regions differed significantly by sex ratio (p < 0.001). The highest sex ratio was observed in Figuig, with a female to male ratio of 3.1 (75.4% of the registered case were females), followed respectively by Taourirt, Oujda-Angad, Berkane, Nador-Driouch and Jerada. Clear variation in the distribution of cancer types between areas of Eastern Morocco was observed, both in males and females (p < 0.001). Furthermore, the areas of Eastern Morocco differed significantly by cancer prevalence (p < 0.001). The highest age-standardized five-year prevalence proportion was observed in Oujda-Angad with 420.2 per 100,000, followed respectively by Berkane (311.4), Jerada (287.8), Taourirt (269.3), Nador-Driouch (213.6) and Figuig (194.4). Trends in the five-year prevalence proportions decreased in Oujda-Angad, Berkane and Jerada throughout the study period, while an increasing trend was observed in Nador-Driouch, Taourirt and Figuig.ConclusionsFor the first time, our study presents the pattern and distribution of diagnosed cancers in Eastern Morocco. Our study illustrates substantial differences in cancer patterns between areas of Eastern Morocco. These findings are important for cancer control and highlight the need to develop program aiming at controlling and preventing the spread of major cancer sites in Eastern Morocco, particularly in areas with increased cancer prevalence rates.

In the current era of big data, the amount of data available is continuously increasing. Both the number and types of samples, or features, are on the rise. The mixing of distinct features often makes interpretation more difficult. However, separate analysis of individual types requires subsequent integration. A tensor is a useful framework to deal with distinct types of features in an integrated manner without mixing them. On the other hand, tensor data is not easy to obtain since it requires the measurements of huge numbers of combinations of distinct features; if there are m kinds of features, each of which has N dimensions, the number of measurements needed are as many as Nm, which is often too large to measure. In this paper, I propose a new method where a tensor is generated from individual features without combinatorial measurements, and the generated tensor was decomposed back to matrices, by which unsupervised feature extraction was performed. In order to demonstrate the usefulness of the proposed strategy, it was applied to synthetic data, as well as three omics datasets. It outperformed other matrix-based methodologies.

Precise detection of invasive cancer on whole-slide images (WSI) is a critical first step in digital pathology tasks of diagnosis and grading. Convolutional neural network (CNN) is the most popular representation learning method for computer vision tasks, which have been successfully applied in digital pathology, including tumor and mitosis detection. However, CNNs are typically only tenable with relatively small image sizes (200 × 200 pixels). Only recently, Fully convolutional networks (FCN) are able to deal with larger image sizes (500 × 500 pixels) for semantic segmentation. Hence, the direct application of CNNs to WSI is not computationally feasible because for a WSI, a CNN would require billions or trillions of parameters. To alleviate this issue, this paper presents a novel method, High-throughput Adaptive Sampling for whole-slide Histopathology Image analysis (HASHI), which involves: i) a new efficient adaptive sampling method based on probability gradient and quasi-Monte Carlo sampling, and, ii) a powerful representation learning classifier based on CNNs. We applied HASHI to automated detection of invasive breast cancer on WSI. HASHI was trained and validated using three different data cohorts involving near 500 cases and then independently tested on 195 studies from The Cancer Genome Atlas. The results show that (1) the adaptive sampling method is an effective strategy to deal with WSI without compromising prediction accuracy by obtaining comparative results of a dense sampling (∼6 million of samples in 24 hours) with far fewer samples (∼2,000 samples in 1 minute), and (2) on an independent test dataset, HASHI is effective and robust to data from multiple sites, scanners, and platforms, achieving an average Dice coefficient of 76%.

Microarray technology is important to simultaneously express multiple genes over a number of time points. Multiple classifier models, such as sparse representation (SR)-based method, have been developed to classify microarray gene expression data. These methods allocate the gene data points to different clusters. In this paper, we propose a novel collaborative representation (CR)-based classification with regularized least square to classify gene data. First, the CR codes a testing sample as a sparse linear combination of all training samples and then classifies the testing sample by evaluating which class leads to the minimum representation error. This CR-based classification approach is remarkably less complex than traditional classification methods but leads to very competitive classification results. In addition, compressive sensing approach is adopted to project the high-dimensional gene expression dataset to a lower-dimensional space which nearly contains the whole information. This compression without loss is beneficial to reduce the computational load. Experiments to detect subtypes of diseases, such as leukemia and autism spectrum disorders, are performed by analyzing the gene expression. The results show that the proposed CR-based algorithm exhibits significantly higher stability and accuracy than the traditional classifiers, such as support vector machine algorithm.

Genetic risk prediction is an important goal in human genetics research and precision medicine. Accurate prediction models will have great impacts on both disease prevention and early treatment strategies. Despite the identification of thousands of disease-associated genetic variants through genome wide association studies (GWAS), genetic risk prediction accuracy remains moderate for most diseases, which is largely due to the challenges in both identifying all the functionally relevant variants and accurately estimating their effect sizes in the presence of linkage disequilibrium. In this paper, we introduce AnnoPred, a principled framework that leverages diverse types of genomic and epigenomic functional annotations in genetic risk prediction for complex diseases. AnnoPred is trained using GWAS summary statistics in a Bayesian framework in which we explicitly model various functional annotations and allow for linkage disequilibrium estimated from reference genotype data. Compared with state-of-the-art risk prediction methods, AnnoPred achieves consistently improved prediction accuracy in both extensive simulations and real data., Author summary Genetic risk prediction plays a significant role in precision medicine. Accurate prediction models could have great impact on disease prevention and early treatment strategies. For example, mutations in BRCA1 and BRCA2 have been used to evaluate women’s breast cancer risk and as a guideline for early screening. However, genetic risk prediction models also present important challenges, including extreme high-dimensionality, limited access to and efficient computational methods for individual-level genotype data. To make use of rich GWAS summary statistics, we propose a novel method to address these challenges by integrating genomic functional annotations, which have been successfully applied in GWAS to generate biological insights. We demonstrate the improvement in accuracy in both extensive simulation studies and real data analysis of breast cancer, Crohn’s disease, celiac disease, rheumatoid arthritis and type-II diabetes.

Background Breast cancer (BC) has been described as the leading cause of cancer deaths among women especially in the developing world including sub Saharan Africa (SSA). Delayed presentation and late diagnosis at health facilities are parts of the contributing factors of high BC mortality in Africa. This review aimed to appraise the contributing factors to delayed breast cancer presentation and diagnosis among SSA women. Methods Five databases encompassing medical and social sciences were systematically searched using predefined search terms linked with breast cancer presentation and diagnosis and sub Saharan Africa. Reference lists of relevant papers were also hand searched. Quality of quantitative and qualitative articles were assessed using the National Institute of Health (NIH) Quality Assessment Tool for Observational Cohort and Cross-Sectional Studies and the Critical Appraisal Skills Programme (CASP) quality appraisal checklist. Thematic analysis was used to synthesize the qualitative studies to integrate findings. Results Fourteen (14) quantitative studies, two (2) qualitative studies and one (1) mixed method study merited inclusion for analysis. This review identified low knowledge of breast cancer among SSA women. This review also found lack of awareness of early detection treatment, poor perception of BC, socio-cultural factors such as belief, traditions and fear as factors impacting African women’s health seeking behavior in relation to breast cancer. Conclusion Improving African women’s knowledge and understanding will improve behaviors related to breast cancer and facilitate early presentation and detection and enhance proper management and treatment of breast cancer.

Dysregulation of iron metabolism in cancer is well documented and it has been suggested that there is interdependence between excess iron and increased cancer incidence and progression. In an effort to better understand the linkages between iron metabolism and breast cancer, a predictive mathematical model of an expanded iron homeostasis pathway was constructed that includes species involved in iron utilization, oxidative stress response and oncogenic pathways. The model leads to three predictions. The first is that overexpression of iron regulatory protein 2 (IRP2) recapitulates many aspects of the alterations in free iron and iron-related proteins in cancer cells without affecting the oxidative stress response or the oncogenic pathways included in the model. This prediction was validated by experimentation. The second prediction is that iron-related proteins are dramatically affected by mitochondrial ferritin overexpression. This prediction was validated by results in the pertinent literature not used for model construction. The third prediction is that oncogenic Ras pathways contribute to altered iron homeostasis in cancer cells. This prediction was validated by a combination of simulation experiments of Ras overexpression and catalase knockout in conjunction with the literature. The model successfully captures key aspects of iron metabolism in breast cancer cells and provides a framework upon which more detailed models can be built., Author Summary Iron is required for cellular metabolism and growth, but can be toxic due to its ability to cause high oxidative stress and consequently DNA damage. To prevent damage, all organisms that require iron have developed mechanisms to tightly control iron levels. Dysregulation of iron metabolism is detrimental and can contribute to a wide range of diseases, including cancer. This paper presents a predictive mathematical model of iron regulation linked to iron utilization, oxidative stress, and the oncogenic response specific to normal breast epithelial cells. The model uses a discrete modeling framework to generate novel biological hypotheses for an investigation of how normal breast cells become malignant cells, capturing a breast cancer phenotype of iron homeostasis through overexpression and knockout simulations. The new biology discovered is (1) IRP2 overexpression alters the iron homeostasis pathway in breast cells, without affecting the oxidative stress response or oncogenic pathways, (2) an activated oncogenic pathway disrupts iron regulation in breast cancer cells.

Identification of miRNA-disease association is a fundamental challenge in human health clinic. However, the known miRNA-disease associations are rare and experimental verification methods are expensive and time-consuming. Therefore, there is a strong incentive to develop computational methods. In this paper, we calculate the similarity score for each miRNAs pair by integrating miRNA functional similarity and miRNA family information. We use the disease phenotype similarity data to construct the disease similarity network. Then we introduce a new miRNA-disease association prediction method (NETwork Group Similarity, NetGS) to explore the global network similarity, capturing the relationship between the disease and other diseases, the similarity between the potential disease-related miRNA and other miRNAs. Finally based on the consistency of diffusion profiles we get the miRNA-disease association scores. NetGS is tested by the leave-one-out cross validation and achieves an AUC value of 0.8450, which improves the prediction accuracy. NetGS can also be applied to solve the new miRNA-disease association and obtain reliable accuracy. Moreover, we use NetGS to predict new causing miRNAs of three cancers including breast cancer, lung cancer and Hepatocellular cancer. And the top predictions have been confirmed in the online databases. The encouraging results indicate that NetGS might play an essential role for future scientific research.

The practice of precision medicine will ultimately require databases of genes and mutations for healthcare providers to reference in order to understand the clinical implications of each patient’s genetic makeup. Although the highest quality databases require manual curation, text mining tools can facilitate the curation process, increasing accuracy, coverage, and productivity. However, to date there are no available text mining tools that offer high-accuracy performance for extracting such triplets from biomedical literature. In this paper we propose a high-performance machine learning approach to automate the extraction of disease-gene-variant triplets from biomedical literature. Our approach is unique because we identify the genes and protein products associated with each mutation from not just the local text content, but from a global context as well (from the Internet and from all literature in PubMed). Our approach also incorporates protein sequence validation and disease association using a novel text-mining-based machine learning approach. We extract disease-gene-variant triplets from all abstracts in PubMed related to a set of ten important diseases (breast cancer, prostate cancer, pancreatic cancer, lung cancer, acute myeloid leukemia, Alzheimer’s disease, hemochromatosis, age-related macular degeneration (AMD), diabetes mellitus, and cystic fibrosis). We then evaluate our approach in two ways: (1) a direct comparison with the state of the art using benchmark datasets; (2) a validation study comparing the results of our approach with entries in a popular human-curated database (UniProt) for each of the previously mentioned diseases. In the benchmark comparison, our full approach achieves a 28% improvement in F1-measure (from 0.62 to 0.79) over the state-of-the-art results. For the validation study with UniProt Knowledgebase (KB), we present a thorough analysis of the results and errors. Across all diseases, our approach returned 272 triplets (disease-gene-variant) that overlapped with entries in UniProt and 5,384 triplets without overlap in UniProt. Analysis of the overlapping triplets and of a stratified sample of the non-overlapping triplets revealed accuracies of 93% and 80% for the respective categories (cumulative accuracy, 77%). We conclude that our process represents an important and broadly applicable improvement to the state of the art for curation of disease-gene-variant relationships., Author Summary To provide personalized health care it is important to understand patients’ genomic variations and the effect these variants have in protecting or predisposing patients to disease. Several projects aim at providing this information by manually curating such genotype-phenotype relationships in organized databases using data from clinical trials and biomedical literature. However, the exponentially increasing size of biomedical literature and the limited ability of manual curators to discover the genotype-phenotype relationships “hidden” in text has led to delays in keeping such databases updated with the current findings. The result is a bottleneck in leveraging valuable information that is currently available to develop personalized health care solutions. In the past, a few computational techniques have attempted to speed up the curation efforts by using text mining techniques to automatically mine genotype-phenotype information from biomedical literature. However, such computational approaches have not been able to achieve accuracy levels sufficient to make them appealing for practical use. In this work, we present a highly accurate machine-learning-based text mining approach for mining complete genotype-phenotype relationships from biomedical literature. We test the performance of this approach on ten well-known diseases and demonstrate the validity of our approach and its potential utility for practical purposes. We are currently working towards generating genotype-phenotype relationships for all PubMed data with the goal of developing an exhaustive database of all the known diseases in life science. We believe that this work will provide very important and needed support for implementation of personalized health care using genomic data.

Primary angiosarcoma of the breast (PAB) accounts for 0.04% of all breast malignant tumors. It affects young women usually at third or fourth decades of life. PAB clinically manifests as a painless, movable mass with sharp limits. A bluish red discoloration of the overlying skin is often observed. Enlargement of axillary lymph nodes generally does not occur. Angiosarcoma of the breast has a very poor prognosis due to the tendency to metastasize haematogenously and high frequency of local recurrence. Mastectomy and chemotherapy are preferable treatment choices. This paper presents a case of primary angiosarcoma of the breast with a syndrome of disseminated intravascular coagulation (DIC).

Purpose Many studies have reported that carbohydrate antigen 153 (CA153) in breast secretions (BS) can discriminate breast cancer (BC) patients from healthy individuals, indicating CA153 in BS as a potential index for BC. This meta-analysis aimed to evaluate the actual diagnostic value of CA153 in BS. Methods Related papers were obtained from Pubmed, Embase, Scopus, Ovid, Sciverse, the Cochrane library, Chinese Biomedical literature Database (CBM), Technology of Chongqing (VIP), Wan Fang Data, and Chinese National Knowledge Infrastructure (CNKI). Pooled sensitivity, specificity, and diagnostic odds ratio (DOR) of CA153 in BS for BC diagnosis were analyzed with the random effect model. SROC and the area under the curve (AUC) were applied to assess overall diagnostic efficiency. Results This meta-analysis included five studies with a total of 329 BC patients and 381 healthy subjects. For CA153 in BS, the summary sensitivity, specificity, and DOR to diagnose BC were 0.63 (95% confidence interval (CI): 0.57∼0.68), 0.82 (95% CI: 0.78∼0.86), and 9.18 (95% CI: 4.22∼19.95), respectively. Furthermore, the AUC of BS CA153 in the diagnosis of BC was 0.8614. Conclusions CA153 in BS is a valuable molecular marker in diagnosing BC and should be applied in standard clinical practices of BC screening upon confirmation of our findings in a larger prospective study.

The maximal information coefficient (MIC) captures dependences between paired variables, including both functional and non-functional relationships. In this paper, we develop a new method, ChiMIC, to calculate the MIC values. The ChiMIC algorithm uses the chi-square test to terminate grid optimization and then removes the restriction of maximal grid size limitation of original ApproxMaxMI algorithm. Computational experiments show that ChiMIC algorithm can maintain same MIC values for noiseless functional relationships, but gives much smaller MIC values for independent variables. For noise functional relationship, the ChiMIC algorithm can reach the optimal partition much faster. Furthermore, the MCN values based on MIC calculated by ChiMIC can capture the complexity of functional relationships in a better way, and the statistical powers of MIC calculated by ChiMIC are higher than those calculated by ApproxMaxMI. Moreover, the computational costs of ChiMIC are much less than those of ApproxMaxMI. We apply the MIC values tofeature selection and obtain better classification accuracy using features selected by the MIC values from ChiMIC.

The protein tyrosine phosphatase receptor J, PTPRJ, is a tumor suppressor gene that has been implicated in a range of cancers, including breast cancer, yet little is known about its role in normal breast physiology or in mammary gland tumorigenesis. In this paper we show that PTPRJ mRNA is expressed in normal breast tissue and reduced in corresponding tumors. Meta-analysis revealed that the gene encoding PTPRJ is frequently lost in breast tumors and that low expression of the transcript associated with poorer overall survival at 20 years. Immunohistochemistry of PTPRJ protein in normal human breast tissue revealed a distinctive apical localisation in the luminal cells of alveoli and ducts. Qualitative analysis of a cohort of invasive ductal carcinomas revealed retention of normal apical PTPRJ localization where tubule formation was maintained but that tumors mostly exhibited diffuse cytoplasmic staining, indicating that dysregulation of localisation associated with loss of tissue architecture in tumorigenesis. The murine ortholog, Ptprj, exhibited a similar localisation in normal mammary gland, and was differentially regulated throughout lactational development, and in an in vitro model of mammary epithelial differentiation. Furthermore, ectopic expression of human PTPRJ in HC11 murine mammary epithelial cells inhibited dome formation. These data indicate that PTPRJ may regulate differentiation of normal mammary epithelia and that dysregulation of protein localisation may be associated with tumorigenesis.

Tumorigenesis is a dynamic biological process that involves distinct cancer cell subpopulations proliferating at different rates and interconverting between them. In this paper we proposed a mathematical framework of population dynamics that considers both distinctive growth rates and intercellular transitions between cancer cell populations. Our mathematical framework showed that both growth and transition influence the ratio of cancer cell subpopulations but the latter is more significant. We derived the condition that different cancer cell types can maintain distinctive subpopulations and we also explain why there always exists a stable fixed ratio after cell sorting based on putative surface markers. The cell fraction ratio can be shifted by changing either the growth rates of the subpopulations (Darwinism selection) or by environment-instructed transitions (Lamarckism induction). This insight can help us to understand the dynamics of the heterogeneity of cancer cells and lead us to new strategies to overcome cancer drug resistance.

AimsDDX3 is an RNA helicase that has antiapoptotic properties, and promotes proliferation and transformation. In addition, DDX3 was shown to be a direct downstream target of HIF-1α (the master regulatory of the hypoxia response) in breast cancer cell lines. However, the relation between DDX3 and hypoxia has not been addressed in human tumors. In this paper, we studied the relation between DDX3 and the hypoxic responsive proteins in human breast cancer.Methods and resultsDDX3 expression was investigated by immunohistochemistry in breast cancer in comparison with hypoxia related proteins HIF-1α, GLUT1, CAIX, EGFR, HER2, Akt1, FOXO4, p53, ERα, COMMD1, FER kinase, PIN1, E-cadherin, p21, p27, Transferrin receptor, FOXO3A, c-Met and Notch1. DDX3 was overexpressed in 127 of 366 breast cancer patients, and was correlated with overexpression of HIF-1α and its downstream genes CAIX and GLUT1. Moreover, DDX3 expression correlated with hypoxia-related proteins EGFR, HER2, FOXO4, ERα and c-Met in a HIF-1α dependent fashion, and with COMMD1, FER kinase, Akt1, E-cadherin, TfR and FOXO3A independent of HIF-1α.ConclusionsIn invasive breast cancer, expression of DDX3 was correlated with overexpression of HIF-1α and many other hypoxia related proteins, pointing to a distinct role for DDX3 under hypoxic conditions and supporting the oncogenic role of DDX3 which could have clinical implication for current development of DDX3 inhibitors.

Background There has been much interest in differentiating diseased and normal samples using biomarkers derived from mass spectrometry (MS) studies. However, biomarker identification for specific diseases has been hindered by irreproducibility. Specifically, a peak profile extracted from a dataset for biomarker identification depends on a data pre-processing algorithm. Until now, no widely accepted agreement has been reached. Results In this paper, we investigated the consistency of biomarker identification using differentially expressed (DE) peaks from peak profiles produced by three widely used average spectrum-dependent pre-processing algorithms based on SELDI-TOF MS data for prostate and breast cancers. Our results revealed two important factors that affect the consistency of DE peak identification using different algorithms. One factor is that some DE peaks selected from one peak profile were not detected as peaks in other profiles, and the second factor is that the statistical power of identifying DE peaks in large peak profiles with many peaks may be low due to the large scale of the tests and small number of samples. Furthermore, we demonstrated that the DE peak detection power in large profiles could be improved by the stratified false discovery rate (FDR) control approach and that the reproducibility of DE peak detection could thereby be increased. Conclusions Comparing and evaluating pre-processing algorithms in terms of reproducibility can elucidate the relationship among different algorithms and also help in selecting a pre-processing algorithm. The DE peaks selected from small peak profiles with few peaks for a dataset tend to be reproducibly detected in large peak profiles, which suggests that a suitable pre-processing algorithm should be able to produce peaks sufficient for identifying useful and reproducible biomarkers.