Image Analysis Tools Research Articles

From breast cancer cell homing to the onset of early bone metastasis: The role of bone (re)modeling in early lesion formation.

Breast cancer often metastasizes to bone, causing osteolytic lesions. Structural and biophysical changes are rarely studied yet are hypothesized to influence metastasis. We developed a mouse model of early bone metastasis and multimodal imaging to quantify cancer cell homing, bone (re)modeling, and onset of metastasis. Using tissue clearing and three-dimensional (3D) light sheet fluorescence microscopy, we located enhanced green fluorescent protein-positive cancer cells and small clusters in intact bones and quantified their size and spatial distribution. We detected early bone lesions using in vivo microcomputed tomography (microCT)-based time-lapse morphometry and revealed altered bone (re)modeling in the absence of detectable lesions. With a new microCT image analysis tool, we tracked the growth of early lesions over time. We showed that cancer cells home in all bone compartments, while osteolytic lesions are only detected in the metaphysis, a region of high (re)modeling. Our study suggests that higher rates of (re)modeling act as a driver of lesion formation during early metastasis.

Application of neuroimaging in diagnosis of focal cortical dysplasia: A survey of computational techniques

Focal Cortical Dysplasia (FCD) is a neurodevelopmental disorder characterized by abnormal neuronal migration, differentiation, and maturation, resulting in a range of clinical symptoms including drug-resistant epilepsy. Accurate and timely diagnosis of FCD is essential for effective treatment and management of patients with this condition. In recent years, there have been significant advances in neuroimaging and machine learning techniques, enabling automated detection of FCD lesions with increasing accuracy and efficiency.In this survey article, we provide an overview of the current state-of-the-art in computational techniques for the automated detection of FCD lesions using neuroimaging. We first introduce some common imaging findings that radiologists look for in FCD lesions, then review the automatic detection techniques studied in the last decade. These techniques have shown promising results in detecting and localizing FCD lesions, improving diagnostic accuracy and reducing misdiagnoses, diagnosis time, and cost of care.We suggest that the use of these types of quantitative image analysis tools and algorithms can play a key role in improving the overall management and outcome of patients with FCD. However, further studies are needed to validate and optimize the performance of these techniques in clinical practice. In summary, the combination of advanced neuroimaging and computational techniques has the potential to revolutionize the diagnosis and treatment of FCD, leading to better outcomes for patients with this condition.

STARdbi: A pipeline and database for insect monitoring based on automated image analysis

Insects are highly abundant and diverse, and play major roles in ecosystem functions. Monitoring of insect populations is key to their sustainable management. However, the labor and expertise needed to identify insects, and the challenges of archiving the wealth of data collected in monitoring programs, often limit these efforts. We describe a pipeline to reduce the barriers associated with curating and mining big data of insect biodiversity. The pipeline, STARdbi, includes capturing flying insects with sticky traps, scanning the traps, storing the trap-images in a public database with a web-based interface, and applying machine learning models to extract information from the images. To illustrate the insights that can be gained from STARdbi, we describe two case studies. One of them involves monitoring of circadian activity patterns of grain pests and of their natural enemies, and the other compares insect abundance, biomass and size distributions between agricultural and semi-natural habitats. We invite the community of insect ecologists to contribute to the STARdbi database, and to use its image analysis tools to address diverse ecological and evolutionary questions.

Adipose Tissue Analysis Toolkit (ATAT) for automated analysis of adipocyte size and extracellular matrix in white adipose tissue.

The pathological expansion of white adipose tissue (WAT) in obesity involves adipocyte hypertrophy accompanied by expansion of the collagen-rich pericellular extracellular matrix (ECM) and development of crown-like structures (CLS). Traditionally, WAT morphology is assessed through immunohistochemical analysis of WAT sections. However, manual analysis of large histological sections is time-consuming, and the available digital tools for analyzing adipocyte size and pericellular ECM are limited. To address this gap, the authors developed the Adipose Tissue Analysis Toolkit (ATAT), an ImageJ plugin facilitating analysis of adipocyte size, WAT ECM, and CLS. ATAT utilizes local and image-level differentials in pixel intensity to independently threshold image background, distinguishing adipocyte-free tissue without user input. It accurately captures adipocytes in histological sections stained with common dyes and automates the analysis of adipocyte cross-sectional area, total-field, and localized region-of-interest ECM. ATAT allows fully automated batch analysis of histological images using default or user-defined adipocyte detection parameters. ATAT provides several advantages over existing WAT image analysis tools, enabling high-throughput analyses of adipocyte-specific parameters and facilitating the assessment of ECM changes associated with WAT remodeling due to weight changes and other pathophysiological alterations that affect WAT function.

Orientation-invariant autoencoders learn robust representations for shape profiling of cells and organelles

Cell and organelle shape are driven by diverse genetic and environmental factors and thus accurate quantification of cellular morphology is essential to experimental cell biology. Autoencoders are a popular tool for unsupervised biological image analysis because they learn a low-dimensional representation that maps images to feature vectors to generate a semantically meaningful embedding space of morphological variation. The learned feature vectors can also be used for clustering, dimensionality reduction, outlier detection, and supervised learning problems. Shape properties do not change with orientation, and thus we argue that representation learning methods should encode this orientation invariance. We show that conventional autoencoders are sensitive to orientation, which can lead to suboptimal performance on downstream tasks. To address this, we develop O2-variational autoencoder (O2-VAE), an unsupervised method that learns robust, orientation-invariant representations. We use O2-VAE to discover morphology subgroups in segmented cells and mitochondria, detect outlier cells, and rapidly characterise cellular shape and texture in large datasets, including in a newly generated synthetic benchmark.

Findaureus: An open-source application for locating Staphylococcus aureus in fluorescence-labelled infected bone tissue slices.

Staphylococcus aureus (S. aureus) is a facultative pathogenic bacterium that can cause infections in various tissue types in humans. Fluorescence imaging techniques have been employed to visualize the bacteria in ex-vivo samples mostly in research, aiding in the understanding of the etiology of the pathogen. However, the multispectral images generated from fluorescence microscopes are complex, making it difficult to locate bacteria across image files, especially in consecutive planes with different imaging depths. To address this issue, we present Findaureus, an open-source application specifically designed to locate and extract critical information about bacteria, especially S. aureus. Due to the limited availability of datasets, we tested the application on a dataset comprising fluorescence-labelled infected mouse bone tissue images, achieving an accuracy of 95%. We compared Findaureus with other state-of-the-art image analysis tools and found that it performed better, given its specificity toward bacteria localization. The proposed approach has the potential to aid in medical research of bone infections and can be extended to other tissue and bacteria types in the future.

A Lightweight Browser-Based Tool for Collaborative and Blinded Image Analysis.

Collaborative manual image analysis by multiple experts in different locations is an essential workflow in biomedical science. However, sharing the images and writing down results by hand or merging results from separate spreadsheets can be error-prone. Moreover, blinding and anonymization are essential to address subjectivity and bias. Here, we propose a new workflow for collaborative image analysis using a lightweight online tool named Tyche. The new workflow allows experts to access images via temporarily valid URLs and analyze them blind in a random order inside a web browser with the means to store the results in the same window. The results are then immediately computed and visible to the project master. The new workflow could be used for multi-center studies, inter- and intraobserver studies, and score validations.

Comparison of quantification of intraretinal hard exudates between optical coherence tomography en face image versus fundus photography.

To compare the quantification of intraretinal hard exudate (HE) using en face optical coherence tomography (OCT) and fundus photography. Consecutive en face images and corresponding fundus photographs from 13 eyes of 10 patients with macular edema associated with diabetic retinopathy or Coats' disease were analyzed using the machine-learning-based image analysis tool, "ilastik." The overall measured HE area was greater with en face images than with fundus photos (en face: 0.49 ± 0.35 mm2 vs. fundus photo: 0.34 ± 0.34 mm2, P < 0.001). However, there was an excellent correlation between the two measurements (intraclass correlation coefficient [ICC] = 0.844). There was a negative correlation between HE area and central macular thickness (CMT) (r = -0.292, P = 0.001). However, HE area showed a positive correlation with CMT in the previous several months, especially in eyes treated with anti-vascular endothelial growth factor (VEGF) therapy (CMT 3 months before: r = 0.349, P = 0.001; CMT 4 months before: r = 0.287, P = 0.012). Intraretinal HE can be reliably quantified from either en face OCT images or fundus photography with the aid of an interactive machine learning-based image analysis tool. HE area changes lagged several months behind CMT changes, especially in eyes treated with anti-VEGF injections.

P013 Magnetic Resonance Imaging-Based Average T2 Signal as A Non-Invasive Measure of Fibrosis In Enteric Crohn’s Disease

Abstract Background In Crohn’s Disease (CD), 10% of patients present with fibrostenosis with a further 10% progressing from inflammatory to a fibrostenotic disease behaviour over 7 years. 40% of fibrostenotic CD patients need surgery at 5 years compared to ~10% with inflammatory disease. Present non-invasive fibrosis biomarkers lack the required accuracy needed to be used routinely for clinical decision making. T1, T2, diffusion weighted imaging, motility and bowel volumes have shown promise in the non-invasive measure of fibrosis. Methods The primary objective of this study is to undertake biological validation of MRI measures as independent imaging biomarkers of histological fibrosis with the primary outcome being the correlation between MRI measures and histological fibrosis measures. GI-Seg (Motilent, London, UK) is an image analysis tool used to segment the gastrointestinal tract on T2W MRI scans. Patients with CD histological diagnosis and in need of surgical resection for stenosis attended a one-hour 3T MRI scanning session within 12 weeks prior to their intestinal resection surgery. Histological samples were scored by a specialized gastrointestinal pathologist for inflammation, fibrosis, and muscular hypertrophy. An expert radiologist with the help of the histopathologist located the strictures on DWI, quantitative T2&amp;T2 scans, and T2 weighted clinical MRI scans. GI-Seg was used to generate a 3D model of the stricture on T2W scans measuring bowel wall volume and average signal intensity of each stricture. Pearson correlation coefficient was used to quantify the correlation between the variables. Results A total of 10 CD patients, encompassing 20 strictures, were included in the study. The analysis revealed that the average T2 signal has a significant correlation with global fibrosis scores (r(20) = .563, p = .010) (Figure) and total inflammation scores (r(20) = .451, p = .046). Additionally, stricture volume showed a fair correlation with chronic inflammation component scores (r(20) = .453, p = .045). Notably, quantitative T1 values correlated with total inflammation scores (r(17) = .493, p = .045). Conclusion The study reveals fair correlations between the T2 signal average and both global fibrosis and global inflammation scores, as well as between stricture volume and chronic inflammation in CD strictures. While these findings indicate that the GI-seg tool's measurements of bowel wall volume and signal intensity have potential utility as imaging biomarkers for fibrosis and inflammation, the results also underscore the necessity for additional markers that are specifically correlated with fibrosis. Such markers are essential to distinctly identify fibrotic changes, independent of inflammatory processes.

Study of defects in PV generators using image analysis techniques with Matlab

It is evidence that the useful life of the photovoltaic generator, as its correct operation, define the production and the profitability of a photovoltaic installation. There are several aspects that cause descents in the level of production of the generator and therefore losses in the installation. Based on it, it has developed numerous of both corrective and preventive maintenance that avoid these circumstances. Along the document there are revised the possible defects that the photovoltaic generator can have and the techniques of detection of the same ones. Inside the techniques of analysis and examination [1] we will center on the very concrete one: the visual inspection and its development by image analysis tools with Matlab. The techniques used are part of the tool “Image processing toolbox” that provides a finished set of algorithms of standard reference and graphic hardware to the prosecution, the analysis and the visualization of images and the development of complementary algorithms. Across the employment and the adaptation of some of the included algorithms it will be claimed to approach a step more specializing in the conventional visual analysis used in the maintenance of the plants of photovoltaic solar energy.

An integrative biology approach to understanding keratinocyte collective migration as stimulated by bioglass.

A critical phase of wound healing is the coordinated movement of keratinocytes. To this end, bioglasses show promise in speeding healing in hard tissues and skin wounds. Studies suggest that bioglass materials may promote wound healing by inducing positive cell responses in proliferation, growth factor production, expression of angiogenic factors, and migration. Precise details of how bioglass may stimulate migration are unclear, however, because the common assays for studying migration in wound healing focus on simplified outputs like rate of migration or total change in wound area. These outputs are limited in that they represent the average behavior of the collective, with no connection between the motion of the individual cells and the collective wound healing response. There is a need to apply more refined tools that identify how the motion of the individual cells changes in response to perturbations, such as by bioglass, and in turn affects motion of the cell collective. Here, we apply an integrative biology strategy that combines an in vitro wound healing assay using primary neonatal human keratinocytes with time lapse microscopy and quantitative image analysis. The resulting data set provides the cell velocity field, from which we define key metrics that describe cooperative migration phenotypes. Treatment with growth factors led to faster single-cell speeds compared to control, but the migration was not cooperative, with cells breaking away from their neighbors and migrating as individuals. Treatment with calcium or bioglass led to migration phenotypes that were highly collective, with greater coordination in space compared to control. We discuss the link between bioglass treatment and observed increases in free calcium ions that are hypothesized to promote these distinct coordinated behaviors in primary keratinocytes. These findings have been enabled by the unique descriptors developed through applying image analysis to interpret biological response in migration models. Insight Box/Paragraph Statement: Bioglasses are important materials for tissue engineering and have more recently shown promise in skin and wound healing by mechanisms tied to their unique ionic properties. The precise details, however, of how cell migration may be affected by bioglass are left unclear by traditional cell assay methods. The following describes the integration of migration assays of keratinocytes, cells critical for skin and wound healing, with the tools of time lapse microscopy and image analysis to generate a quantitative description of coordinated, tissue-like migration behavior, stimulated by bioglass, that would not have been accessible without the combination of these analytical tools.

Deep Machine Learning for Medical Diagnosis, Application to Lung Cancer Detection: A Review

Deep learning has emerged as a powerful tool for medical image analysis and diagnosis, demonstrating high performance on tasks such as cancer detection. This literature review synthesizes current research on deep learning techniques applied to lung cancer screening and diagnosis. This review summarizes the state-of-the-art in deep learning for lung cancer detection, highlighting key advances, limitations, and future directions. We prioritized studies utilizing major public datasets, such as LIDC, LUNA16, and JSRT, to provide a comprehensive overview of the field. We focus on deep learning architectures, including 2D and 3D convolutional neural networks (CNNs), dual-path networks, Natural Language Processing (NLP) and vision transformers (ViT). Across studies, deep learning models consistently outperformed traditional machine learning techniques in terms of accuracy, sensitivity, and specificity for lung cancer detection in CT scans. This is attributed to the ability of deep learning models to automatically learn discriminative features from medical images and model complex spatial relationships. However, several challenges remain to be addressed before deep learning models can be widely deployed in clinical practice. These include model dependence on training data, generalization across datasets, integration of clinical metadata, and model interpretability. Overall, deep learning demonstrates great potential for lung cancer detection and precision medicine. However, more research is required to rigorously validate models and address risks. This review provides key insights for both computer scientists and clinicians, summarizing progress and future directions for deep learning in medical image analysis.

Analysis of Signature Patterns: Consistency and Distinctiveness in Handwritten Signatures for Forensic Authentication

Handwritten signatures are unique behavioural attributes that serve as a distinct form of identification forindividuals. This study focuses on the analysis of signature patterns using various parameters, including aspect ratio, angle of the first letter with respect to the baseline, and the ratio of the area of a circle to its radius within the signature. A dataset consisting of 1200 genuine and 1200 simulated (English) signature samples from 12 individuals were examined using an image analysis tool to record measurements for these parameters. The primary objectives were to investigate the consistency of signatures within the same person and to compare genuine signatures with simulated ones. This study contributes to the field of forensic investigations by offering insights into the authentication of signatures and the measurement of dissimilarities between signatures of the same and different individuals based on their patterns. The findings aid in identifying most influential parameter in distinguishing genuine signatures from counterfeits and enhance the evidential value of handwritten signature samples. Additionally, the simplified approach employed in this study allows for universal applicability across languages. Future research endeavours could expand the dataset and explore additional parameters to further improve the accuracy and reliability of signature verification methods in forensic analysis.

On the Assessment of Strawberries' Shelf-Life and Quality, Based on Image Analysis, Physicochemical Methods, and Chemometrics.

The aim of the present study was to evaluate Marisol strawberries' (Fragaria × ananassa) physicochemical quality and shelf-life during storage, using an integrated analytical approach. More specifically, the research aimed to assess the strawberries' color, texture, and nutritional quality, over an 11-day storage period, employing physicochemical analyses, spectrophotometric assays, Attenuated Total Reflection-Fourier Transform Infrared (ATR-FTIR) spectroscopy, image analysis, and statistical tools. The results revealed significant changes in the outer surface texture and color characteristics, indicating spoilage progression. Physicochemical parameters such as water activity, moisture content, soluble solids, titratable acidity, and ascorbic acid content exhibited significant alterations, influencing the taste profile and freshness perception. Antioxidant and antiradical activities showed fluctuations, suggesting a potential decrease in phenolic content during storage. Moreover, the ATR-FTIR spectra findings confirmed the results regarding the moisture content, soluble solids, and total phenolic content. The integration of physicochemical and image analysis-derived features through a principal component analysis (PCA) enabled the accurate classification of samples based on storage days. Regression analysis, using these features, successfully predicted the storage day with high accuracy. Overall, this integrated analytical approach provided valuable information on the estimation of Marisol strawberries' shelf-life and the prediction of their quality deterioration, contributing to better fruit management and the minimization of discards.

Morphology-based deep learning enables accurate detection of senescence in mesenchymal stem cell cultures.

Cell senescence is a sign of aging and plays a significant role in the pathogenesis of age-related disorders. For cell therapy, senescence may compromise the quality and efficacy of cells, posing potential safety risks. Mesenchymal stem cells (MSCs) are currently undergoing extensive research for cell therapy, thus necessitating the development of effective methods to evaluate senescence. Senescent MSCs exhibit distinctive morphology that can be used for detection. However, morphological assessment during MSC production is often subjective and uncertain. New tools are required for the reliable evaluation of senescent single cells on a large scale in live imaging of MSCs. We have developed a successful morphology-based Cascade region-based convolution neural network (Cascade R-CNN) system for detecting senescent MSCs, which can automatically locate single cells of different sizes and shapes in multicellular images and assess their senescence state. Additionally, we tested the applicability of the Cascade R-CNN system for MSC senescence and examined the correlation between morphological changes with other senescence indicators. This deep learning has been applied for the first time to detect senescent MSCs, showing promising performance in both chronic and acute MSC senescence. The system can be a labor-saving and cost-effective option for screening MSC culture conditions and anti-aging drugs, as well as providing a powerful tool for non-invasive and real-time morphological image analysis integrated into cell production.

CAT: a computational anatomy toolbox for the analysis of structural MRI data.

A large range of sophisticated brain image analysis tools have been developed by the neuroscience community, greatly advancing the field of human brain mapping. Here we introduce the Computational Anatomy Toolbox (CAT)-a powerful suite of tools for brain morphometric analyses with an intuitive graphical user interface but also usable as a shell script. CAT is suitable for beginners, casual users, experts, and developers alike, providing a comprehensive set of analysis options, workflows, and integrated pipelines. The available analysis streams-illustrated on an example dataset-allow for voxel-based, surface-based, and region-based morphometric analyses. Notably, CAT incorporates multiple quality control options and covers the entire analysis workflow, including the preprocessing of cross-sectional and longitudinal data, statistical analysis, and the visualization of results. The overarching aim of this article is to provide a complete description and evaluation of CAT while offering a citable standard for the neuroscience community.

Computed tomography cross-sections for an objective evaluation of the textile fabric’s inner structure and its thickness

The thickness and inner structure of porous fibrous structures - textiles is an important parameter, especially regarding comfort, noise, heat insulation, and permeability. The standard and probably the fastest thickness measuring method is with a thickness gauge, which uses a certain slight pressure, as well as other known methodologies. The paper presents an original methodology for evaluating the thickness of non-pressure-controlled porosity structures using their transversal packing density distribution. It also determines the maximum packing density value of the evaluated structure and the packing density level at which the thickness gauge approximately measures the thickness. The ratio of pressure-controlled and non-pressure-controlled thicknesses is used to define the proportion of the “incompressible” core of the fabric to its “compressible” surface. The packing density is evaluated in transverse virtual cross-sections of the structures using an image analysis tool. The standard soft cross-sections that are used could again cause some deformation of the studied structures, so the cross-sections were performed using Rigaku’s nano3DX computed tomography equipment. The methodology was tested on a set of seven diverse textile structures in terms of material and manufacturing technology. Each test specimen was evaluated for its internal structure through the transverse packing density process, the corresponding mentioned packing density levels were found, the non-pressure controlled thickness was determined, and the core and outlying fibers ratio was defined. The maximum packing density in the fabric core decreased as expected from the woven fabric through the weft and warp knitted fabric to the non-woven fabric. The maximum transverse packing density is independent of the thickness and the material used and, therefore, depends only on the structure. So is the packing density level at which the thickness gauge measures the thickness. This level has been set at 0.028 for knitted fabrics.

"MeiQuant": An Integrated Tool for Analyzing Meiotic Prophase I Spread Images.

Immunocytochemical analysis of meiotic proteins on mouse chromosome spreads is one method of choice to study prophase I chromosome organization and homologous recombination. In recent decades, the development of microscopic approaches led to the production of a large number of images that monitor fluorescent proteins, defined as fluorescent objects, and a major challenge facing the community is the deep analysis of these fluorescent objects (measurement of object length, intensity, distance between objects, as well as foci identification, counting, and colocalization). We propose a set of tools designed from the macro language of the widely used image analysis software ImageJ (Schindelin et al., Nat Methods 9: 676-682, 2012), embedded in the "MeiQuant" macro, which are specifically designed for analyzing objects in the field of meiosis. Our aim is to propose a unified evolutive common tool for image analysis, with a specific focus on mouse prophase I meiotic events.

Quantitative Analysis of Whole-Mount Fluorescence-Stained Tumor Spheroids in Phenotypic Drug Screens.

Three-dimensional cell cultures, such as spheroids or organoids, serve as important models for drug screening purposes. Optical tissue clearing (OTC) enhances the visualization of fluorescence stainings and enables in toto microscopy of 3D cell culture models. Furthermore, subsequent automated image analysis tools convert qualitative confocal image sets into quantitative data. In this chapter, we describe a detailed protocol for preparation of HT29 cancer spheroids, 3D in toto immunostaining, glycerol-based OTC, whole-mount imaging, and semi-automated downstream image processing and segmentation for nuclear image analysis using open-source software.

Automated Layer Analysis (ALAn): An Image Analysis Tool for the Unbiased Characterization of Mammalian Epithelial Architecture in Culture.

Cultured mammalian cells are a common model system for the study of epithelial biology and mechanics. Epithelia are often considered as pseudo-two dimensional and thus imaged and analyzed with respect to the apical tissue surface. We found that the three-dimensional architecture of epithelial monolayers can vary widely even within small culture wells, and that layers that appear organized in the plane of the tissue can show gross disorganization in the apical-basal plane. Epithelial cell shapes should be analyzed in 3D to understand the architecture and maturity of the cultured tissue to accurately compare between experiments. Here, we present a detailed protocol for the use of our image analysis pipeline, Automated Layer Analysis (ALAn), developed to quantitatively characterize the architecture of cultured epithelial layers. ALAn is based on a set of rules that are applied to the spatial distributions of DNA and actin signals in the apical-basal (depth) dimension of cultured layers obtained from imaging cultured cell layers using a confocal microscope. ALAn facilitates reproducibility across experiments, investigations, and labs, providing users with quantitative, unbiased characterization of epithelial architecture and maturity. Key features • This protocol was developed to spatially analyze epithelial monolayers in an automated and unbiased fashion. • ALAn requires two inputs: the spatial distributions of nuclei and actin in cultured cells obtained using confocal fluorescence microscopy. • ALAn code is written in Python3 using the Jupyter Notebook interactive format. • Optimized for use in Marbin-Darby Canine Kidney (MDCK) cells and successfully applied to characterize human MCF-7 mammary gland-derived and Caco-2 colon carcinoma cells. • This protocol utilizes Imaris software to segment nuclei but may be adapted for an alternative method. ALAn requires the centroid coordinates and volume of nuclei.