Comprehensive Image Analysis Research Articles

DWELLING EXTRACTION IN REFUGEE CAMPS USING CNN – FIRST EXPERIENCES AND LESSONS LEARNT

Abstract. There is a growing use of Earth observation (EO) data for support planning in humanitarian crisis response. Information about number and dynamics of displaced population in camps is essential to humanitarian organizations for decision-making and action planning. Dwelling extraction and categorisation is a challenging task, due to the problems in separating different dwellings under different conditions, with wide range of sizes, colour and complex spatial patterns. Nowadays, so-called deep learning techniques such as deep convolutional neural network (CNN) are used for understanding image content and object recognition. Although recent developments in the field of computer vision have introduced CNN networks as a practical tool also in the field of remote sensing, the training step of these techniques is rather time-consuming and samples for the training process are rarely transferable to other application fields. These techniques also have not been fully explored for mapping camps. Our study analyses the potential of a CNN network for dwelling extraction to be embedded as initial step in a comprehensive object-based image analysis (OBIA) workflow. The results were compared to a semi-automated, i.e. combined knowledge-/sample-based, OBIA classification. The Minawao refugee camp in Cameroon served as a case study due to its well-organised, clearly distinguishable dwelling structure. We use manually delineated objects as initial input for the training samples, while the CNN network is structured with two convolution layers and one max pooling.

Dimensionality Reduction and Classification of Hyperspectral Images Using Object-Based Image Analysis

Object-based image analysis (OBIA) has attained great importance for the delineation of landscape features, particularly with the accessibility to satellite images with high spatial resolution acquired by recent sensors. Statistical parametric classifiers have become ineffective mainly due to their assumption of normal distribution, vast increase in the dimensions of the data and availability of limited ground sample data. Despite pixel-based approaches, OBIA takes semantic information of extracted image objects into consideration, and thus provides more comprehensive image analysis. In this study, Indian Pines hyperspectral data set, which was recorded by the AVIRIS hyperspectral sensor, was used to analyse the effects of high dimensional data with limited ground reference data. To avoid the dimensionality curse, principal component analysis (PCA) and feature selection based on Jeffries–Matusita (JM) distance were utilized. First 19 principal components representing 98.5% of the image were selected using the PCA technique whilst 30 spectral bands of the image were determined using JM distance. Nearest neighbour (NN) and random forest (RF) classifiers were employed to test the performances of pixel- and object-based classification using conventional accuracy metrics. It was found that object-based approach outperformed the traditional pixel-based approach for all cases (up to 18% improvement). Also, the RF classifier produced significantly more accurate results (up to 10%) than the NN classifier.

Comprehensive high-throughput image analysis for therapeutic efficacy of architecturally complex heterotypic organoids

Bioengineered three-dimensional (3D) tumor models that incorporate heterotypic cellular communication are gaining interest as they can recapitulate key features regarding the intrinsic heterogeneity of cancer tissues. However, the architectural complexity and heterogeneous contents associated with these models pose a challenge for toxicological assays to accurately report treatment outcomes. To address this issue, we describe a comprehensive image analysis procedure for structurally complex organotypic cultures (CALYPSO) applied to fluorescence-based assays to extract multiparametric readouts of treatment effects for heterotypic tumor cultures that enables advanced analyses. The capacity of this approach is exemplified on various 3D models including adherent/suspension, mono-/heterocellular cultures and several disease types. The subsequent analysis revealed specific morphological effects of oxaliplatin chemotherapy, radiotherapy, and photodynamic therapy. The procedure can be readily implemented in most laboratories to facilitate high-throughput toxicological screening of pharmaceutical agents and treatment regimens on organotypic cultures of human disease to expedite drug and therapy development.

ES 01.02 New Histological Classification

ES 01.02 New Histological Classification

Quantification of volume and lipid filling of intracellular vesicles carrying the ABCA3 transporter

The ABCA3 lipid transporter is located in the limiting membrane of lamellar bodies (LBs) in type-II-pneumocytes. Mutations within the ABCA3 gene may functionally impair the transporter, causing lung diseases in newborns, children and adults. Assays to quantify volume and lipid filling of the LBs on the level of the vesicular structures and thereby assess the function of ABCA3 are still lacking. In the present study human influenza haemagglutinin- (HA-) tagged wild type and mutant ABCA3 proteins were stably expressed in lung A549 cells. Fluorescently-labelled TopFluor phosphatidylcholine (TopF-PC) incorporated in surfactant-like liposomes was delivered to the cells and visualized by confocal microscopy. Subsequently, a comprehensive image analysis method was applied to quantify volume and fluorescence intensity of TopF-PC in ABCA3-HA-positive vesicles. TopF-PC accumulated within the vesicles in a time and concentration-dependent manner, whereas the volume remained unchanged, suggesting active transport into preformed ABCA3 containing vesicles. Furthermore, this finding was supported by a decrease of the fluorescence intensity within the vesicles when either the ATPase of the transporter was inhibited by vanadate, or when a disease-causing mutation (K1388N) close to the ABCA3-nucleotide binding domain 2 was introduced. Conversely, a mutation (E292V) located in the first cytoplasmic loop of ABCA3 did not significantly affect lipid transport, but rather resulted in smaller vesicles. In addition to these findings, the assay used in this work for analysing the PC-lipid transport into ABCA3 positive vesicles will be useful to screen for compounds susceptible to restore function in mutated ABCA3 protein.

TRACMIT: An effective pipeline for tracking and analyzing cells on micropatterns through mitosis

The use of micropatterns has transformed investigations of dynamic biological processes by enabling the reproducible analysis of live cells using time-lapse fluorescence microscopy. With micropatterns, thousands of individual cells can be efficiently imaged in parallel, rendering the approach well suited for screening projects. Despite being powerful, such screens remain challenging in terms of data handling and analysis. Typically, only a fraction of micropatterns is occupied in a manner suitable to monitor a given phenotypic output. Moreover, the presence of dying or otherwise compromised cells complicates the analysis. Therefore, focusing strictly on relevant cells in such large time-lapse microscopy dataset poses interesting analysis challenges that are not readily met by existing software packages. This motivated us to develop an image analysis pipeline that handles all necessary image processing steps within one open-source platform to detect and analyze individual cells seeded on micropatterns through mitosis. We introduce a comprehensive image analysis pipeline running on Fiji termed TRACMIT (pipeline for TRACking and analyzing cells on micropatterns through MITosis). TRACMIT was developed to rapidly and accurately assess the orientation of the mitotic spindle during metaphase in time-lapse fluorescence microscopy of human cells expressing mCherry::histone 2B and plated on L-shaped micropatterns. This solution enables one to perform the entire analysis from the raw data, avoiding the need to save intermediate images, thereby decreasing data volume and thus reducing the data that needs to be processed. We first select micropatterns containing a single cell and then identify anaphase figures in the time-lapse recording. Next, TRACMIT tracks back in time until metaphase, when the angle of the mitotic spindle with respect to the micropattern is assessed. We designed the pipeline to allow for manual validation of selected cells with a simple user interface, and to enable analysis of cells plated on micropatterns of different shapes. For ease of use, the entire pipeline is provided as a series of Fiji/ImageJ macros, grouped into an ActionBar. In conclusion, the open source TRACMIT pipeline enables high-throughput analysis of single mitotic cells on micropatterns, thus accurately and efficiently allowing automatic determination of spindle positioning from time-lapse recordings.

Separating Bulk and Surface Contributions to Electronic Excited-State Processes in Hybrid Mixed Perovskite Thin Films via Multimodal All-Optical Imaging.

A comprehensive understanding of electronic excited-state phenomena underlying the impressive performance of solution-processed hybrid halide perovskite solar cells requires access to both spatially resolved electronic processes and corresponding sample morphological characteristics. Here, we demonstrate an all-optical multimodal imaging approach that enables us to obtain both electronic excited-state and morphological information on a single optical microscope platform with simultaneous high temporal and spatial resolution. Specifically, images were acquired for the same region of interest in thin films of chloride containing mixed lead halide perovskites (CH3NH3PbI3-xClx) using femtosecond transient absorption, time-integrated photoluminescence, confocal reflectance, and transmission microscopies. Comprehensive image analysis revealed the presence of surface- and bulk-dominated contributions to the various images, which describe either spatially dependent electronic excited-state properties or morphological variations across the probed region of the thin films. These results show that PL probes effectively the species near or at the film surface.

Abstract 4815: Humanized single mouse trial: A preclinical platform feasible for immune-oncology drug screening and translational biomarker development

Abstract The field of cancer immunology is rapidly moving towards innovative therapeutic strategies. As a consequence the need for robust and predictive preclinical platforms arises just as well. The current project aims to establish a drug screening workflow bridging between innovative mouse models and clinical biomarker development. A total of 69 NOG (NOD/Shi-scid/IL-2Rγnull) mice were engrafted with CD34+ hematopoietic stem cells. Thereafter, tumor material from 11 different lung cancer patient derived xenograft models (NSCLC PDX) was implanted subcutaneously. Individual mice were treated with α-CTLA-4, α-PD-1 or the combination thereof. With n=1 per treatment arm and model the study design followed the screening approach of the single mouse trial (SMT). Infiltration of human immune cells was detected by flow cytometry (FC) and immunohistochemistry (IHC) in hematopoietic organs and tumor tissue. A computerized analysis for digitized whole-slide images of the samples was used to quantify the lymphocyte infiltration using color classification and morphological image processing techniques. All 3 treatment arms displayed a discrete activity pattern throughout the PDX panel. Tumor models with high tumor infiltrating lymphocyte (TIL) rates in the donor patient material tended to be more sensitive towards checkpoint inhibitor treatment as models with low rates. Numbers of TILs in the PDX detected by FC and IHC were significantly increased in the treatment groups as compared to control vehicle. In parallel, hematopoietic organs showed high (>25%) amounts of huCD45 cells in all groups and models. PDX models being sensitive towards checkpoint inhibitor treatment (responders) displayed a higher percentage of DAB+ nuclei in huCD45 IHC stains than non-responder models as determined by image analysis. Irrespective thereof, in responders as well as non-responders the treatment with checkpoint inhibitors enhanced the percentage of DAB+ nuclei. Whole-slide image analysis of the H&E stains revealed an increase of the stromal compartment proportion in the tumor tissue under treatment with checkpoint inhibitors in responder models. In non-responder models the ratio between tumor and stroma was not influenced by drug treatment. The use of PDX based humanized mouse models in a SMT format allows screening approaches in complex mouse models. The combination with a comprehensive image analysis tool enables additional read-outs to quantify antitumoral activity of immune modulatory compounds. The latter can be used to identify possible biomarkers in the preclinical setting. Moreover, the translation and validation of these biomarker candidates in a clinical setting is self-evident as primary material needed for these types of analyses is easily accessible. Citation Format: Daniel Bug, Eva Oswald, Anne Grote, Anne-Lise Peille, Gabriele Niedermann, Dorit Merhof, Friedrich Feuerhake, Julia B. Schüler. Humanized single mouse trial: A preclinical platform feasible for immune-oncology drug screening and translational biomarker development [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2017; 2017 Apr 1-5; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2017;77(13 Suppl):Abstract nr 4815. doi:10.1158/1538-7445.AM2017-4815

Multiscale image analysis reveals structural heterogeneity of the cell microenvironment in homotypic spheroids

Three-dimensional multicellular aggregates such as spheroids provide reliable in vitro substitutes for tissues. Quantitative characterization of spheroids at the cellular level is fundamental. We present the first pipeline that provides three-dimensional, high-quality images of intact spheroids at cellular resolution and a comprehensive image analysis that completes traditional image segmentation by algorithms from other fields. The pipeline combines light sheet-based fluorescence microscopy of optically cleared spheroids with automated nuclei segmentation (F score: 0.88) and concepts from graph analysis and computational topology. Incorporating cell graphs and alpha shapes provided more than 30 features of individual nuclei, the cellular neighborhood and the spheroid morphology. The application of our pipeline to a set of breast carcinoma spheroids revealed two concentric layers of different cell density for more than 30,000 cells. The thickness of the outer cell layer depends on a spheroid’s size and varies between 50% and 75% of its radius. In differently-sized spheroids, we detected patches of different cell densities ranging from 5 × 105 to 1 × 106cells/mm3. Since cell density affects cell behavior in tissues, structural heterogeneities need to be incorporated into existing models. Our image analysis pipeline provides a multiscale approach to obtain the relevant data for a system-level understanding of tissue architecture.

Comprehensive Retinal Image Analysis for Aggressive Posterior Retinopathy of Prematurity.

Computer aided analysis plays a nontrivial role in assisting the diagnosis of various eye pathologies. In this paper, we propose a framework to help diagnose the presence of Aggressive Posterior Retinopathy Of Prematurity (APROP), a pathology that is characterised by rapid onset and increased tortuosity of blood vessels close to the optic disc (OD). We quantify vessel characteristics that are of clinical relevance to APROP such as tortuosity and the extent of branching i.e., vessel segment count in the defined diagnostic region. We have adapted three vessel segmentation techniques: matched filter response, scale space theory and morphology with local entropy based thresholding. The proposed feature set equips us to build a linear discriminant classifier to discriminate APROP images from clinically healthy images. We have studied 36 images from 21 APROP subjects against a control group of 15 clinically healthy age matched infants. All subjects are age matched ranging from 33−40 weeks of post menstrual age. Experimental results show that we attain 100% recall and 95.45% precision, when the vessel network obtained from morphology is used for feature extraction.

Automated Analysis of Orientational Order in Images of Fibrillar Materials

Nanofibers are a ubiquitous structural motif in a variety of functional materials. In the field of organic electronics, π–π-stacking of conjugated polymers leads to fibrillar morphologies with a wide array of fiber packing behavior. Fiber orientation and alignment are known to influence the charge transport properties of devices such as organic field effect transistors. The solution processing methods used to create these devices give rise to large variations in these structural parameters—however, they are only observable with imaging techniques such as atomic force microscopy (AFM). To bring more rigorous quantification of orientation and alignment to these materials, a comprehensive image analysis tool is introduced to quantify the two-dimensional orientation and alignment of nanofibers from AFM images. It has been developed in MATLAB and packaged as a stand-alone application, so that researchers with no computational expertise can produce publication-ready figures directly from their images. AFM frequ...

Understanding the Formation of Anisometric Supraparticles: A Mechanistic Look Inside Droplets Drying on a Superhydrophobic Surface.

Evaporating drops of nanoparticle suspensions on superhydrophobic surfaces can give anisotropic superaparticles. Previous studies implied the formation of a stiff shell that collapses, but the exact mechanism leading to anisotropy was unclear so far. Here we report on a new experiment using confocal laser scanning microscopy for a detailed characterization of particle formation from droplets of aqueous colloidal dispersions on superhydrophobic surfaces. In a customized setup, we investigated droplets of fumed silica suspensions using two different fluorescent dyes for independently marking silica and the water phase. Taking advantage of interfacial reflection, we locate the drop-air interface and extract normalized time-resolved intensity profiles for dyed silica throughout the drying process. Using comprehensive image analysis we observe and quantify shell-like interfacial particle accumulation arising from droplet evaporation. This leads to a buildup of a stiff fumed silica mantle of ∼20 μm thickness that causes deformation of the droplet throughout further shrinkage, consequently leading to the formation of solid anisometric fumed silica particles.

Multimodal nonlinear microscopy of head and neck carcinoma - toward surgery assisting frozen section analysis.

Treatment of early cancer stages is deeply connected to a good prognosis, a moderate reduction of the quality of life, and comparably low treatment costs. Head and neck squamous cell carcinomas were investigated using the multimodal combination of coherent anti-Stokes Raman scattering (CARS), two-photon excited fluorescence (TPEF), and second-harmonic generation (SHG) microscopy. An increased median TPEF to CARS contrast was found comparing cancerous and healthy squamous epithelium with a p value of 1.8·10(-10) . A following comprehensive image analysis was able to predict the diagnosis of imaged tissue sections with an overall accuracy of 90% for a 4-class model. Nonlinear multimodal imaging is verified objectively as a valuable diagnostic tool that complements conventional staining protocols and can serve as filter in future clinical routine reducing the pathologist's workload. © 2016 Wiley Periodicals, Inc. Head Neck 38: First-1552, 2016.

Computer-aided pulmonary image analysis in small animal models.

To develop an automated pulmonary image analysis framework for infectious lung diseases in small animal models. The authors describe a novel pathological lung and airway segmentation method for small animals. The proposed framework includes identification of abnormal imaging patterns pertaining to infectious lung diseases. First, the authors' system estimates an expected lung volume by utilizing a regression function between total lung capacity and approximated rib cage volume. A significant difference between the expected lung volume and the initial lung segmentation indicates the presence of severe pathology, and invokes a machine learning based abnormal imaging pattern detection system next. The final stage of the proposed framework is the automatic extraction of airway tree for which new affinity relationships within the fuzzy connectedness image segmentation framework are proposed by combining Hessian and gray-scale morphological reconstruction filters. 133 CT scans were collected from four different studies encompassing a wide spectrum of pulmonary abnormalities pertaining to two commonly used small animal models (ferret and rabbit). Sensitivity and specificity were greater than 90% for pathological lung segmentation (average dice similarity coefficient > 0.9). While qualitative visual assessments of airway tree extraction were performed by the participating expert radiologists, for quantitative evaluation the authors validated the proposed airway extraction method by using publicly available EXACT'09 data set. The authors developed a comprehensive computer-aided pulmonary image analysis framework for preclinical research applications. The proposed framework consists of automatic pathological lung segmentation and accurate airway tree extraction. The framework has high sensitivity and specificity; therefore, it can contribute advances in preclinical research in pulmonary diseases.

Experimental Investigation of CO2 Utilization as an Injection Solvent in Vapour Extraction (VAPEX) Process

Abstract In this research, an extensive experimental investigation is carried out to evaluate the utilization of CO 2 as an injection solvent for VAPEX process. To accomplish this goal, two large, visual rectangular, sand-packed VAPEX models with 24.5 cm and 47.5 cm heights were employed to run the experiments using Plover Lake heavy oil (5650 cP) with a low permeability (6∼9 D) sand pack. Propane, CO 2 and propane/CO 2 mixture were considered as respective solvents for the experiments, and a total of 6 tests were carried out. The heavy oil production rate and the produced gas-oil ratio were measured periodically. Moreover, separate experiments were carried out at the end of each VAPEX experiment to measure the asphaltene precipitation at various locations of the VAPEX models. To observe the drainage height effect in more details, a comprehensive image analysis was performed during the solvent chamber evolution. As a result, it was determined that drainage height has a significant impact on production rate and heavy oil recovery. The results prove the complexity of the effect of drainage height and the up- scaling issues with the VAPEX process. Furthermore, in terms of solvents, propane showed the highest recovery factor of 75% of original oil in place due to its favourable low vapour pressure and high solubility. Ultimately, the promising recovery performance after introducing CO 2 as a carrier gas was observed, the recovery factor of 55% of original oil in place was achieved when the mixture of propane/CO 2 was used as the solvent. After conducting asphaltene measurement tests, it was observed that more asphaltene precipitation occurred close to the injection points and at the oil/solvent interface. Furthermore, the image analysis revealed that the highest sweep efficiency was observed to be 0.86 after injecting propane, followed by propane/CO 2 mixture, and pure CO 2 .

Polarized light imaging of birefringence and diattenuation at high resolution and high sensitivity

Polarized light microscopy provides unique opportunities for analyzing the molecular order in man-made and natural materials, including biological structures inside living cells, tissues, and whole organisms. 20 years ago, the LC-PolScope was introduced as a modern version of the traditional polarizing microscope enhanced by liquid crystal devices for the control of polarization, and by electronic imaging and digital image processing for fast and comprehensive image acquisition and analysis. The LC-PolScope is commonly used for birefringence imaging, analyzing the spatial and temporal variations of the differential phase delay in ordered and transparent materials. Here we describe an alternative use of the LC-PolScope for imaging the polarization dependent transmittance of dichroic materials. We explain the minor changes needed to convert the instrument between the two imaging modes, discuss the relationship between the quantities measured with each instrument, and touch on the physical connection between refractive index, birefringence, transmittance, diattenuation, and dichroism.

Higher‐order statistical analysis of short wind wave fields

Observations of along‐wind surface wave profiles were made in the large Marseille‐Luminy wind wave tank for a broad range of wind and fetch conditions. The processing of high resolution camera snapshots enables us to carry on a thorough statistical analysis of wind wave geometrical properties. We consider distinctively the four different wind wave fields characterized by a comprehensive image analysis in the range of capillary‐gravity to gravity scales. This set of data makes it possible to describe and discuss the behavior of the distribution of wave heights, longitudinal wave slopes and curvatures in terms of their second‐ and higher‐order moments as well as a function of the dominant wave scale. We calculate the autocorrelation and related functions and evidence the self‐similar nature of wind wave fields. We also derive a simple and universal expression for the structure functions of third (skewness) and fourth (kurtosis) order which are needed for the simulation of sea radar return in the microwave regime.

The importance of destination image analysis to UK rural tourism

PurposeThe Forest of Dean attracts relatively low numbers of staying visitors and low visitor spend. The paper aims to explore the image of this destination and identify the potential to visit along with any underlying factors that may deter visitors.Design/methodology/approachA mix of qualitative and quantitative methods were used to gather and analyse responses to an online survey. Respondents offered a range of words and pictures from which they were asked to select those they felt best represented the destination, and also then asked to explain their selection. Quantitative data were also analysed for frequency of occurrence. A content analysis of qualitative data was conducted to generate destination image clusters of the Forest of Dean.FindingsThe findings show there is a very positive and unique image associated with the Forest of Dean among previous visitors, with many expressing an intention to visiting the area again.Research limitations/implicationsAlthough response rates are relatively low, and results are heavily concentrated on actual visitors, the research provides very broad ranging and meaningful data that have offered a deeper and richer insight into the image of the Forest of Dean.Practical implicationsThe paper has provided important data from which new competitive brand image strategies can be developed for the destination. The paper also provides a first step towards a comprehensive image analysis for the Forest of Dean, from which future promotional strategies can be developed.Originality/valueMany visitor guides promote UK rural destinations on their superb scenery, relaxation, outdoor leisure activities, quality accommodation, locally‐sourced food, a range of attractions and a full calendar of events and festivals. To date there has been very little research carried out on UK rural destination brands and no academic research carried out on the image or branding of the Forest of Dean as a unique rural destination.

Systematic image‐driven analysis of the spatial Drosophila embryonic expression landscape

Discovery of temporal and spatial patterns of gene expression is essential for understanding the regulatory networks and development in multicellular organisms. We analyzed the images from our large-scale spatial expression data set of early Drosophila embryonic development and present a comprehensive computational image analysis of the expression landscape. For this study, we created an innovative virtual representation of embryonic expression patterns using an elliptically shaped mesh grid that allows us to make quantitative comparisons of gene expression using a common frame of reference. Demonstrating the power of our approach, we used gene co-expression to identify distinct expression domains in the early embryo; the result is surprisingly similar to the fate map determined using laser ablation. We also used a clustering strategy to find genes with similar patterns and developed new analysis tools to detect variation within consensus patterns, adjacent non-overlapping patterns, and anti-correlated patterns. Of the 1800 genes investigated, only half had previously assigned functions. The known genes suggest developmental roles for the clusters, and identification of related patterns predicts requirements for co-occurring biological functions.

Proposed Method for Determining the Residual Mortar Content of Recycled Concrete Aggregates

Abstract Recycling concrete from demolition of existing structures and using it as recycled concrete aggregates (RCAs) in structural-grade concrete have significant economic and environmental benefits. Currently, only a small portion of the concrete waste is reused in building construction, while most of it is used as either pavement base course or sent to landfills for disposal. The lack of confidence in the material properties of the concrete produced with RCAs is generally the main reason for its under-utilization in structural concrete. It has been demonstrated in the literature that the amount of residual mortar attached to the original (or “virgin”) aggregate particles is one of the factors affecting the material properties of RCAs. Therefore, before using RCAs in new concrete, it is crucial that the residual mortar content (RMC) is determined accurately; however, currently there is no standard procedure to determine this quantity. In this paper, an experimental method is proposed to determine the RMC of RCAs. The method comprises a combination of mechanical and chemical stresses that disintegrate the residual mortar and destroy the bond between the mortar and the natural aggregates. The mechanical stresses are created through subjecting RCA to freeze-and-thaw action, while the chemical degradation is achieved through exposure of the RCA to a sodium sulphate solution. The results of the proposed test procedure are validated by means of comprehensive image analysis. With the proposed approach, the attached residual mortar can be adequately removed, and the residual mortar content can be determined.