Graph machine learning for integrated multi-omics analysis.

Multi-omics experiments at bulk or single-cell resolution facilitate the discovery of hypothesis-generating biomarkers for predicting response to therapy, as well as aid in uncovering mechanistic insights into cellular and microenvironmental processes. Many methods for data integration have been developed for the identification of key elements that explain or predict disease risk or other biological outcomes. The heterogeneous graph representation of multi-omics data provides an advantage for discerning patterns suitable for predictive/exploratory analysis, thus permitting the modeling of complex relationships. Graph-based approaches-including graph neural networks-potentially offer a reliable methodological toolset that can provide a tangible alternative to scientists and clinicians that seek ideas and implementation strategies in the integrated analysis of their omics sets for biomedical research. Graph-based workflows continue to push the limits of the technological envelope, and this perspective provides a focused literature review of research articles in which graph machine learning is utilized for integrated multi-omics data analyses, with several examples that demonstrate the effectiveness of graph-based approaches.

Intestinal BMP-9 locally upregulates FGF19 and is down-regulated in obese patients with diabetes.

Bone morphogenetic protein (BMP)-9, a member of the TGFß-family of cytokines, is believed to be mainly produced in the liver. The serum levels of BMP-9 were reported to be reduced in newly diagnosed diabetic patients and BMP-9 overexpression ameliorated steatosis in the high fat diet-induced obesity mouse model. Furthermore, injection of BMP-9 in mice enhanced expression of fibroblast growth factor (FGF)21. However, whether BMP-9 also regulates the expression of the related FGF19 is not clear. Because both FGF21 and 19 were described to protect the liver from steatosis, we have further investigated the role of BMP-9 in this context. We first analyzed BMP-9 levels in the serum of streptozotocin (STZ)-induced diabetic rats (a model of type I diabetes) and confirmed that BMP-9 serum levels decrease during diabetes. Microarray analyses of RNA samples from hepatic and intestinal tissue from BMP-9 KO- and wild-type mice (C57/Bl6 background) pointed to basal expression of BMP-9 in both organs and revealed a down-regulation of hepatic Fgf21 and intestinal Fgf19 in the KO mice. Next, we analyzed BMP-9 levels in a cohort of obese patients with or without diabetes. Serum BMP-9 levels did not correlate with diabetes, but hepatic BMP-9 mRNA expression negatively correlated with steatosis in those patients that did not yet develop diabetes. Likewise, hepatic BMP-9 expression also negatively correlated with serum LPS levels. In situ hybridization analyses confirmed intestinal BMP-9 expression. Intestinal (but not hepatic) BMP-9 mRNA levels were decreased with diabetes and positively correlated with intestinal E-Cadherin expression. In vitro studies using organoids demonstrated that BMP-9 directly induces FGF19 in gut but not hepatocyte organoids, whereas no evidence of a direct induction of hepatic FGF21 by BMP-9 was found. Consistent with the in vitro data, a correlation between intestinal BMP-9 and FGF19 mRNA expression was seen in the patients' samples. In summary, our data confirm that BMP-9 is involved in diabetes development in humans and in the control of the FGF-axis. More importantly, our data imply that not only hepatic but also intestinal BMP-9 associates with diabetes and steatosis development and controls FGF19 expression. The data support the conclusion that increased levels of BMP-9 would most likely be beneficial under pre-steatotic conditions, making supplementation of BMP-9 an interesting new approach for future therapies aiming at prevention of the development of a metabolic syndrome and liver steatosis.

Quantitative Assessment of Breast-Tumor Stiffness Using Shear-Wave Elastography Histograms.

Purpose: Shear-wave elastography (SWE) measures tissue elasticity using ultrasound waves. This study proposes a histogram-based SWE analysis to improve breast malignancy detection. Methods: N = 22/32 (patients/tumors) benign and n = 51/64 malignant breast tumors with histological ground truth. Colored SWE heatmaps were adjusted to a 0−180 kPa scale. Normalized, 250-binned RGB histograms were used as image descriptors based on skewness and area under curve (AUC). The histogram method was compared to conventional SWE metrics, such as (1) the qualitative 5-point scale classification and (2) average stiffness (SWEavg)/maximal tumor stiffness (SWEmax) within the tumor B-mode boundaries. Results: The SWEavg and SWEmax did not discriminate malignant lesions in this database, p > 0.05, rank sum test. RGB histograms, however, differed between malignant and benign tumors, p < 0.001, Kolmogorov−Smirnoff test. The AUC analysis of histograms revealed the reduction of soft-tissue components as a significant SWE biomarker (p = 0.03, rank sum). The diagnostic accuracy of the suggested method is still low (Se = 0.30 for Se = 0.90) and a subject for improvement in future studies. Conclusions: Histogram-based SWE quantitation improved the diagnostic accuracy for malignancy compared to conventional average SWE metrics. The sensitivity is a subject for improvement in future studies.

Microglia Activation in the Midbrain of the Human Neonate: The Effect of Perinatal Hypoxic-Ischemic Injury.

Perinatal hypoxia-ischemia (PHI) is a major risk factor for the development of neuropsychiatric deficits later in life. We previously reported that after prolonged PHI, the dopaminergic neurons of the human neonate showed a dramatic reduction of tyrosine hydroxylase (TH) in the substantia nigra, without important signs of neuronal degeneration despite the significant reduction in their cell size. Since microglia activation could precede neuronal death, we now investigated 2 microglia activation markers, ionized calcium-binding adapter molecule 1 (Iba1), and the phagocytosis marker Cd68. The highest Iba1 immunoreactivity was found in neonates with neuropathological lesions of severe/abrupt PHI, while the lowest in subjects with moderate/prolonged or older PHI. Subjects with very severe/prolonged or chronic PHI showed an increased Iba1 expression and very activated microglial morphology. Heavy attachment of microglia on TH neurons and remarkable expression of Cd68 were also observed indicating phagocytosis in this group. Females appear to express more Iba1 than males, suggesting a gender difference in microglia maturation and immune reactivity after PHI insult. PHI-induced microglial "priming" during the sensitive for brain development perinatal/neonatal period, in combination with genetic or other epigenetic factors, could predispose the survivors to neuropsychiatric disorders later in life, possibly through a sexually dimorphic way.

Segmentation of biomedical images based on a computational topology framework.

The homology groups of a topological space provide us with information about its connectivity and the number and type of holes in it. This type of information can find practical applications in describing the intrinsic structure of an image, as well as in identifying equivalence classes in collections of images. When computing homological characteristics, the existence and strength of the relationships between each pair of points in the topological space are studied. The practical use of this approach begins by building a topological space from the image, in which the computation of the homology groups can be carried out in a feasible time. Once the homological properties are obtained, what follows is the task of translating such information into operations such as image segmentation. This work presents a technique for denoising persistent diagrams and reconstructing the shape of segmented objects using the remaining classes on the diagram. A case study for the segmentation of cell nuclei in histological images is used for demonstration purposes. With this approach: a) topological denoising is achieved by aggregating trivial classes on the persistence diagram, and b) a growing seed algorithm uses the information obtained during the construction of the persistence diagram for the reconstruction of the segmented cell structures.

Interrogating the microenvironmental landscape of tumors with computational image analysis approaches.

The tumor microenvironment is an interacting heterogeneous collection of cancer cells, resident as well as infiltrating host cells, secreted factors, and extracellular matrix proteins. With the growing importance of immunotherapies, it has become crucial to be able to characterize the composition and the functional orientation of the microenvironment. The development of novel computational image analysis methodologies may enable the robust quantification and localization of immune and related biomarker-expressing cells within the microenvironment. The aim of the review is to concisely highlight a selection of current and significant contributions pertinent to methodological advances coupled with biomedical or translational applications. A further aim is to concisely present computational advances that, to our knowledge, have currently very limited use for the assessment of the microenvironment but have the potential to enhance image analysis pipelines; on this basis, an example is shown for the detection and segmentation of cells of the microenvironment using a published pipeline and a public dataset. Finally, a general proposal is presented on the conceptual design of automation-optimized computational image analysis workflows in the biomedical and clinical domain.

CCR5 status and metastatic progression in colorectal cancer.

Multiple reports have highlighted the importance of the local immunological cellular composition (i.e. the density of effector T cells and macrophage polarization state) in predicting clinical outcome in advanced metastatic stage of colorectal cancer. However, in spite of the general association between a high effector T cell density and improved outcome, our recent work has revealed a specific lymphocyte-driven cancer cell-supporting signal. Indeed, lymphocyte-derived CCL5 supports CCR5-positive tumor cell proliferation and thereby fosters tumor growth in metastatic liver lesions. Upon systematic analysis of CCR5 expression by tumor cells using immunohistochemistry, we observed that the intensity of CCR5 increases with primary tumor size and peaks in T4 tumors. In liver metastases however, though CCR5 expression intensity is globally heightened compared to primary tumors, alterations in the expression patterns appear, leading to "patchiness" of the stain. CCR5 patchiness is, therefore, a signature of liver metastases in our cohort (n = 97 specimens) and relates to globally decreased expression intensity, but does not influence the extent of the response to CCR5 inhibitor Maraviroc in patients. Moreover, CCR5 patchiness relates to a poor immune landscape characterized by a low cytotoxic-to-regulatory T cell ratio at the invasive margin and enriched cellular and molecular markers of macrophage M2 polarization. Finally, because higher numbers of PD-1- and CTLA-4-positive cells surround tumors with patchy CCR5 expression, one can speculate that these tumors potentially respond to immune checkpoint blockade. This hypothesis is corroborated by the prolonged disease-free survival and disease-specific survival observed in patients with low gene expression of CCR5 in metastases from two publically available cohorts. These observations highlight the complex role of the CCL5-CCR5 axis in CRC metastatic progression and warrant further investigations.

Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study.

BACKGROUND: For virtually every patient with colorectal cancer (CRC), hematoxylin-eosin (HE)-stained tissue slides are available. These images contain quantitative information, which is not routinely used to objectively extract prognostic biomarkers. In the present study, we investigated whether deep convolutional neural networks (CNNs) can extract prognosticators directly from these widely available images. METHODS AND FINDINGS: We hand-delineated single-tissue regions in 86 CRC tissue slides, yielding more than 100,000 HE image patches, and used these to train a CNN by transfer learning, reaching a nine-class accuracy of >94% in an independent data set of 7,180 images from 25 CRC patients. With this tool, we performed automated tissue decomposition of representative multitissue HE images from 862 HE slides in 500 stage I-IV CRC patients in the The Cancer Genome Atlas (TCGA) cohort, a large international multicenter collection of CRC tissue. Based on the output neuron activations in the CNN, we calculated a "deep stroma score," which was an independent prognostic factor for overall survival (OS) in a multivariable Cox proportional hazard model (hazard ratio [HR] with 95% confidence interval [CI]: 1.99 [1.27-3.12], p = 0.0028), while in the same cohort, manual quantification of stromal areas and a gene expression signature of cancer-associated fibroblasts (CAFs) were only prognostic in specific tumor stages. We validated these findings in an independent cohort of 409 stage I-IV CRC patients from the "Darmkrebs: Chancen der Verhütung durch Screening" (DACHS) study who were recruited between 2003 and 2007 in multiple institutions in Germany. Again, the score was an independent prognostic factor for OS (HR 1.63 [1.14-2.33], p = 0.008), CRC-specific OS (HR 2.29 [1.5-3.48], p = 0.0004), and relapse-free survival (RFS; HR 1.92 [1.34-2.76], p = 0.0004). A prospective validation is required before this biomarker can be implemented in clinical workflows. CONCLUSIONS: In our retrospective study, we show that a CNN can assess the human tumor microenvironment and predict prognosis directly from histopathological images.

Downregulation of SPARC Is Associated with Epithelial-Mesenchymal Transition and Low Differentiation State of Biliary Tract Cancer Cells.

BACKGROUND: Biliary tract cancers (BTCs) have a poor prognosis. BTCs are characterized by a prominent desmoplastic reaction which possibly contributes to the aggressive phenotype of this tumor. The desmoplastic reaction includes excessive production and deposition of extracellular matrix proteins such as periostin, secreted protein acidic and rich in cysteine (SPARC), thrombospondin-1, as well as accumulation of α-smooth muscle actin-positive cancer-associated fibroblasts and immune cells, secreting growth factors and cytokines including transforming growth factor (TGF)-ß. In the present study, we investigated the expression of SPARC in BTC as well as its possible regulation by TGF-ß. METHODS: Expression levels of Sparc, TGF-ß1 and its receptor ALK5 were evaluated by quantitative real-time PCR in 6 biliary tract cell lines as well as 1 immortalized cholangiocyte cell line (MMNK-1). RNAs from tumor samples of 7 biliary tract cancer patients were analyzed for expression of Sparc, TGF-ß type II receptor (TbRII) as well as Twist and ZO-1. MMNK-1 cells were stimulated with TGF-ß for 24 h, and Sparc, ZO-1 and E-Cadherin expressions were determined. The presence of SPARC protein was analyzed by immunohistochemistry in tumor specimens from 10 patients. RESULTS: When comparing basal Sparc transcript levels in diverse BTC cell lines to MMNK-1 cells, we found that it was strongly downregulated in all cancer cell lines. The remaining expression levels were higher in highly differentiated cell lines (CCSW1, MZChA1, MZChA2 and TFK-1) than in less differentiated and undifferentiated ones (BDC, SKChA1). Expression of Sparc in BTC patient samples showed a significant positive correlation with expression of the epithelial marker ZO-1. In contrast, the mesenchymal marker Twist and the TbRII showed a trend of negative correlation with expression of Sparc in these samples. TGF-ß exposure significantly downregulated Sparc expression in MMNK-1 cholangiocytes in vitro in parallel to downregulation of epithelial markers (E-Cadherin and ZO-1). Finally, SPARC immunostaining was performed in 10 patient samples, and the correlation between absence of SPARC and survival times was analyzed. CONCLUSIONS: These data imply that a decrease in SPARC expression is correlated with dedifferentiation of BTC cells resulting in enhanced EMT being possibly mediated by TGF-ß. Thereby SPARC levels might be a marker for individual prognosis of a patient, and strategies aiming at inhibition of SPARC downregulation might have potential for new future therapies.

Large-scale database mining reveals hidden trends and future directions for cancer immunotherapy.

Cancer immunotherapy has fundamentally changed the landscape of oncology in recent years and significant resources are invested into immunotherapy research. It is in the interests of researchers and clinicians to identify promising and less promising trends in this field in order to rationally allocate resources. This requires a quantitative large-scale analysis of cancer immunotherapy related databases. We developed a novel tool for text mining, statistical analysis and data visualization of scientific literature data. We used this tool to analyze 72002 cancer immunotherapy publications and 1469 clinical trials from public databases. All source codes are available under an open access license. The contribution of specific topics within the cancer immunotherapy field has markedly shifted over the years. We show that the focus is moving from cell-based therapy and vaccination towards checkpoint inhibitors, with these trends reaching statistical significance. Rapidly growing subfields include the combination of chemotherapy with checkpoint blockade. Translational studies have shifted from hematological and skin neoplasms to gastrointestinal and lung cancer and from tumor antigens and angiogenesis to tumor stroma and apoptosis. This work highlights the importance of unbiased large-scale database mining to assess trends in cancer research and cancer immunotherapy in particular. Researchers, clinicians and funding agencies should be aware of quantitative trends in the immunotherapy field, allocate resources to the most promising areas and find new approaches for currently immature topics.

Astrocytic glutamine synthetase is expressed in the neuronal somatic layers and down-regulated proportionally to neuronal loss in the human epileptic hippocampus.

Human mesial temporal lobe epilepsy (MTLE) features subregion-specific hippocampal neurodegeneration and reactive astrogliosis, including up-regulation of the glial fibrillary acidic protein (GFAP) and down-regulation of glutamine synthetase (GS). However, the regional astrocytic expression pattern of GFAP and GS upon MTLE-associated neurodegeneration still remains elusive. We assessed GFAP and GS expression in strict correlation with the local neuronal number in cortical and hippocampal surgical specimens from 16 MTLE patients using immunohistochemistry, stereology and high-resolution image analysis for digital pathology and whole-slide imaging. In the cortex, GS-positive (GS+) astrocytes are dominant in all neuronal layers, with a neuron to GS+ cell ratio of 2:1. GFAP-positive (GFAP+) cells are widely spaced, with a GS+ to GFAP+ cell ratio of 3:1-5:1. White matter astrocytes, on the contrary, express mainly GFAP and, to a lesser extent, GS. In the hippocampus, the neuron to GS+ cell ratio is approximately 1:1. Hippocampal degeneration is associated with a reduction of GS+ astrocytes, which is proportional to the degree of neuronal loss and primarily present in the hilus. Up-regulation of GFAP as a classical hallmark of reactive astrogliosis does not follow the GS-pattern and is prominent in the CA1. Reactive alterations were proportional to the neuronal loss in the neuronal somatic layers (stratum pyramidale and hilus), while observed to a lesser extent in the axonal/dendritic layers (stratum radiatum, molecular layer). We conclude that astrocytic GS is expressed in the neuronal somatic layers and, upon neurodegeneration, is down-regulated proportionally to the degree of neuronal loss.

In Silico Modeling of Immunotherapy and Stroma-Targeting Therapies in Human Colorectal Cancer.

Despite the fact that the local immunological microenvironment shapes the prognosis of colorectal cancer, immunotherapy has shown no benefit for the vast majority of colorectal cancer patients. A better understanding of the complex immunological interplay within the microenvironment is required. In this study, we utilized wet lab migration experiments and quantitative histological data of human colorectal cancer tissue samples (n = 20) including tumor cells, lymphocytes, stroma, and necrosis to generate a multiagent spatial model. The resulting data accurately reflected a wide range of situations of successful and failed immune surveillance. Validation of simulated tissue outcomes on an independent set of human colorectal cancer specimens (n = 37) revealed the model recapitulated the spatial layout typically found in human tumors. Stroma slowed down tumor growth in a lymphocyte-deprived environment but promoted immune escape in a lymphocyte-enriched environment. A subgroup of tumors with less stroma and high numbers of immune cells showed high rates of tumor control. These findings were validated using data from colorectal cancer patients (n = 261). Low-density stroma and high lymphocyte levels showed increased overall survival (hazard ratio 0.322, P = 0.0219) as compared with high stroma and high lymphocyte levels. To guide immunotherapy in colorectal cancer, simulation of immunotherapy in preestablished tumors showed that a complex landscape with optimal stroma permeabilization and immune cell activation is able to markedly increase therapy response in silico These results can help guide the rational design of complex therapeutic interventions, which target the colorectal cancer microenvironment. Cancer Res; 77(22); 6442-52. ©2017 AACR.

Detailed resolution analysis reveals spatial T cell heterogeneity in the invasive margin of colorectal cancer liver metastases associated with improved survival.

On a broader scale, T cell density and localization in colorectal cancer liver metastases have prognostic and predictive implications. As T cell distribution at higher resolutions has not been fully investigated, a detailed resolution analysis of T cell distribution was performed. Patient tissues were divided into 10 µm distance classes between the tumor border and adjacent normal liver. Thereby, distinct density patterns of T cell localization in relation to the malignant tissue could be detected. At a distance of 20 to 30 µm to the tumor, a decrease of CD3 T cells is common. Within this area, cytotoxic Granzyme B and CD8+ T cells were found to be significantly reduced as well as CD163 macrophages were increased and identified to be in close contact with T cells. Our data suggests a physical or functional border within this region. Survival analysis revealed improved overall survival in patients with high T cells numbers at the direct tumor border. Interestingly, the decreased T cells in the 20 to 30 µm region were also found to be significantly associated with improved survival. Consequently, the detailed localization of T cells, despite blockade, could be associated with improved clinical outcome. The high-resolution analysis represents new insights into relevant heterogenous T cell distributions especially related to clinical responses. As the paradoxical observation of localization-dependent prognostic relevance of T cell densities is only detectable by detailed spatial analyses, this investigation of spatial profiles at higher resolutions is suggested as a new biomarker for survival and response to therapies.

BMP-9 interferes with liver regeneration and promotes liver fibrosis.

OBJECTIVE: Bone morphogenetic protein (BMP)-9, a member of the transforming growth factor-ß family of cytokines, is constitutively produced in the liver. Systemic levels act on many organs and tissues including bone and endothelium, but little is known about its hepatic functions in health and disease. DESIGN: Levels of BMP-9 and its receptors were analysed in primary liver cells. Direct effects of BMP-9 on hepatic stellate cells (HSCs) and hepatocytes were studied in vitro, and the role of BMP-9 was examined in acute and chronic liver injury models in mice. RESULTS: Quiescent and activated HSCs were identified as major BMP-9 producing liver cell type. BMP-9 stimulation of cultured hepatocytes inhibited proliferation, epithelial to mesenchymal transition and preserved expression of important metabolic enzymes such as cytochrome P450. Acute liver injury caused by partial hepatectomy or single injections of carbon tetrachloride (CCl4) or lipopolysaccharide (LPS) into mice resulted in transient downregulation of hepatic BMP-9 mRNA expression. Correspondingly, LPS stimulation led to downregulation of BMP-9 expression in cultured HSCs. Application of BMP-9 after partial hepatectomy significantly enhanced liver damage and disturbed the proliferative response. Chronic liver damage in BMP-9-deficient mice or in mice adenovirally overexpressing the selective BMP-9 antagonist activin-like kinase 1-Fc resulted in reduced deposition of collagen and subsequent fibrosis. CONCLUSIONS: Constitutive expression of low levels of BMP-9 stabilises hepatocyte function in the healthy liver. Upon HSC activation, endogenous BMP-9 levels increase in vitro and in vivo and high levels of BMP-9 cause enhanced damage upon acute or chronic injury.

Robust detection and segmentation of cell nuclei in biomedical images based on a computational topology framework.

The segmentation of cell nuclei is an important step towards the automated analysis of histological images. The presence of a large number of nuclei in whole-slide images necessitates methods that are computationally tractable in addition to being effective. In this work, a method is developed for the robust segmentation of cell nuclei in histological images based on the principles of persistent homology. More specifically, an abstract simplicial homology approach for image segmentation is established. Essentially, the approach deals with the persistence of disconnected sets in the image, thus identifying salient regions that express patterns of persistence. By introducing an image representation based on topological features, the task of segmentation is less dependent on variations of color or texture. This results in a novel approach that generalizes well and provides stable performance. The method conceptualizes regions of interest (cell nuclei) pertinent to their topological features in a successful manner. The time cost of the proposed approach is lower-bounded by an almost linear behavior and upper-bounded by O(n2) in a worst-case scenario. Time complexity matches a quasilinear behavior which is O(n1+ɛ) for ε < 1. Images acquired from histological sections of liver tissue are used as a case study to demonstrate the effectiveness of the approach. The histological landscape consists of hepatocytes and non-parenchymal cells. The accuracy of the proposed methodology is verified against an automated workflow created by the output of a conventional filter bank (validated by experts) and the supervised training of a random forest classifier. The results are obtained on a per-object basis. The proposed workflow successfully detected both hepatocyte and non-parenchymal cell nuclei with an accuracy of 84.6%, and hepatocyte cell nuclei only with an accuracy of 86.2%. A public histological dataset with supplied ground-truth data is also used for evaluating the performance of the proposed approach (accuracy: 94.5%). Further validations are carried out with a publicly available dataset and ground-truth data from the Gland Segmentation in Colon Histology Images Challenge (GlaS) contest. The proposed method is useful for obtaining unsupervised robust initial segmentations that can be further integrated in image/data processing and management pipelines. The development of a fully automated system supporting a human expert provides tangible benefits in the context of clinical decision-making.

Spatial intratumoral heterogeneity of proliferation in immunohistochemical images of solid tumors.

PURPOSE: The interactions of neoplastic cells with each other and the microenvironment are complex. To understand intratumoral heterogeneity, subtle differences should be quantified. Main factors contributing to heterogeneity include the gradient ischemic level within neoplasms, action of microenvironment, mechanisms of intercellular transfer of genetic information, and differential mechanisms of modifications of genetic material/proteins. This may reflect on the expression of biomarkers in the context of prognosis/stratification. Hence, a rigorous approach for assessing the spatial intratumoral heterogeneity of histological biomarker expression with accuracy and reproducibility is required, since patterns in immunohistochemical images can be challenging to identify and describe. METHODS: A quantitative method that is useful for characterizing complex irregular structures is lacunarity; it is a multiscale technique that exhaustively samples the image, while the decay of its index as a function of window size follows characteristic patterns for different spatial arrangements. In histological images, lacunarity provides a useful measure for the spatial organization of a biomarker when a sampling scheme is employed and relevant features are computed. The proposed approach quantifies the segmented proliferative cells and not the textural content of the histological slide, thus providing a more realistic measure of heterogeneity within the sample space of the tumor region. The aim is to investigate in whole sections of primary pancreatic neuroendocrine neoplasms (pNENs), using whole-slide imaging and image analysis, the spatial intratumoral heterogeneity of Ki-67 immunostains. Unsupervised learning is employed to verify that the approach can partition the tissue sections according to distributional heterogeneity. RESULTS: The architectural complexity of histological images has shown that single measurements are often insufficient. Inhomogeneity of distribution depends not only on percentage content of proliferation phase but also on how the phase fills the space. Lacunarity curves demonstrate variations in the sampled image sections. Since the spatial distribution of proliferation in each case is different, the width of the curves changes too. Image sections that have smaller numerical variations in the computed features correspond to neoplasms with spatially homogeneous proliferation, while larger variations correspond to cases where proliferation shows various degrees of clumping. Grade 1 (uniform/nonuniform: 74%/26%) and grade 3 (uniform: 100%) pNENs demonstrate a more homogeneous proliferation with grade 1 neoplasms being more variant, while grade 2 tumor regions render a more diverse landscape (50%/50%). Hence, some cases show an increased degree of spatial heterogeneity comparing to others with similar grade. Whether this is a sign of different tumor biology and an association with a more benign/malignant clinical course needs to be investigated further. The extent and range of spatial heterogeneity has the potential to be evaluated as a prognostic marker. CONCLUSIONS: The association with tumor grade as well as the rationale that the methodology reflects true tumor architecture supports the technical soundness of the method. This reflects a general approach which is relevant to other solid tumors and biomarkers. Drawing upon the merits of computational biomedicine, the approach uncovers salient features for use in future studies of clinical relevance.

VIS-NIR spectroscopy as a process analytical technology for compositional characterization of film biopolymers and correlation with their mechanical properties.

There is an increasing interest in the use of polysaccharides and proteins for the production of biodegradable films. Visible and near-infrared (VIS-NIR) spectroscopy is a reliable analytical tool for objective analyses of biological sample attributes. The objective is to investigate the potential of VIS-NIR spectroscopy as a process analytical technology for compositional characterization of biodegradable materials and correlation to their mechanical properties. Biofilms were produced by single-screw extrusion with different combinations of polybutylene adipate-co-terephthalate, whole oat flour, glycerol, magnesium stearate, and citric acid. Spectral data were recorded in the range of 400-2498nm at 2nm intervals. Partial least square regression was used to investigate the correlation between spectral information and mechanical properties. Results show that spectral information is influenced by the major constituent components, as they are clustered according to polybutylene adipate-co-terephthalate content. Results for regression models using the spectral information as predictor of tensile properties achieved satisfactory results, with coefficients of prediction (R(2)C) of 0.83, 0.88 and 0.92 (calibration models) for elongation, tensile strength, and Young's modulus, respectively. Results corroborate the correlation of NIR spectra with tensile properties, showing that NIR spectroscopy has potential as a rapid analytical technology for non-destructive assessment of the mechanical properties of the films.

Semantic focusing allows fully automated single-layer slide scanning of cervical cytology slides.

Liquid-based cytology (LBC) in conjunction with Whole-Slide Imaging (WSI) enables the objective and sensitive and quantitative evaluation of biomarkers in cytology. However, the complex three-dimensional distribution of cells on LBC slides requires manual focusing, long scanning-times, and multi-layer scanning. Here, we present a solution that overcomes these limitations in two steps: first, we make sure that focus points are only set on cells. Secondly, we check the total slide focus quality. From a first analysis we detected that superficial dust can be separated from the cell layer (thin layer of cells on the glass slide) itself. Then we analyzed 2,295 individual focus points from 51 LBC slides stained for p16 and Ki67. Using the number of edges in a focus point image, specific color values and size-inclusion filters, focus points detecting cells could be distinguished from focus points on artifacts (accuracy 98.6%). Sharpness as total focus quality of a virtual LBC slide is computed from 5 sharpness features. We trained a multi-parameter SVM classifier on 1,600 images. On an independent validation set of 3,232 cell images we achieved an accuracy of 94.8% for classifying images as focused. Our results show that single-layer scanning of LBC slides is possible and how it can be achieved. We assembled focus point analysis and sharpness classification into a fully automatic, iterative workflow, free of user intervention, which performs repetitive slide scanning as necessary. On 400 LBC slides we achieved a scanning-time of 13.9±10.1 min with 29.1±15.5 focus points. In summary, the integration of semantic focus information into whole-slide imaging allows automatic high-quality imaging of LBC slides and subsequent biomarker analysis.

Multistage histopathological image segmentation of Iba1-stained murine microglias in a focal ischemia model: methodological workflow and expert validation.

A multistage workflow was developed for segmenting and counting murine microglias from histopathological brightfield images, in a permanent focal cerebral ischemia model. Automated counts are useful, since for the assessment of inflammatory mechanisms in ischemic stroke there is a need to quantify the brain's responses to post-ischemia, which primarily is the rapid activation of microglial cells. Permanent middle cerebral artery occlusion was induced in murine brain tissue samples. Positive cells were quantified by immunohistochemistry for the ionized calcium-binding adaptor molecule-1 (Iba1) as the microglia marker. Microglia cells were segmented in seven sequential steps: (i) contrast boosting using quaternion operations, (ii) intensity outlier normalization, (iii) nonlocal total variation denoising, (iv) histogram specification and contrast stretching, (v) homomorphic filtering, (vi) global thresholding, and (vii) morphological filtering. Workflow counts were validated on an image subset, with ground-truth data acquired from manual counts conducted by a neuropathologist. Automated workflow matched ground-truth counts pretty well; 80-90% accuracy was achieved, as regards to time after pMCAO and correspondence to ischemic/non-ischemic tissue.

Parsimonious classification of binary lacunarity data computed from food surface images using kernel principal component analysis and artificial neural networks.

Lacunarity is about quantifying the degree of spatial heterogeneity in the visual texture of imagery through the identification of the relationships between patterns and their spatial configurations in a two-dimensional setting. The computed lacunarity data can designate a mathematical index of spatial heterogeneity, therefore the corresponding feature vectors should possess the necessary inter-class statistical properties that would enable them to be used for pattern recognition purposes. The objectives of this study is to construct a supervised parsimonious classification model of binary lacunarity data-computed by Valous et al. (2009)-from pork ham slice surface images, with the aid of kernel principal component analysis (KPCA) and artificial neural networks (ANNs), using a portion of informative salient features. At first, the dimension of the initial space (510 features) was reduced by 90% in order to avoid any noise effects in the subsequent classification. Then, using KPCA, the first nineteen kernel principal components (99.04% of total variance) were extracted from the reduced feature space, and were used as input in the ANN. An adaptive feedforward multilayer perceptron (MLP) classifier was employed to obtain a suitable mapping from the input dataset. The correct classification percentages for the training, test and validation sets were 86.7%, 86.7%, and 85.0%, respectively. The results confirm that the classification performance was satisfactory. The binary lacunarity spatial metric captured relevant information that provided a good level of differentiation among pork ham slice images.