Computerized Image Analysis Research Articles

Clinical Relevance of Computationally Derived Attributes of Peritubular Capillaries from Kidney Biopsies.

The association between peritubular capillary (PTC) density and disease progression has been studied in a variety of kidney diseases using immunohistochemistry. However, other PTC attributes such as PTC shape have not been explored yet. The recent development of computer vision techniques provides the opportunity for the quantification of PTC attributes using conventional stains and whole slide images. To explore the relationship between PTC characteristics and clinical outcome, n=280 periodic acid Schiff-stained kidney biopsies (88 minimal change disease, 109 focal segmental glomerulosclerosis, 46 membranous nephropathy, and 37 IgA nephropathy) from the NEPTUNE digital pathology repository were computationally analyzed. A previously validated deep learning model was applied to segment cortical PTCs. Average PTC aspect ratio (the PTC major to minor axis ratio), size (PTC pixels per PTC segmentation), and density (PTC pixels per unit cortical area) were computed for each biopsy. Cox proportional hazards models were used to assess associations between these PTC parameters and outcome (40% eGFR decline or kidney failure). Cortical PTC characteristics, and interstitial fractional space PTC density were compared between areas of interstitial fibrosis and tubular atrophy (IFTA) and areas without IFTA. When normalized PTC aspect ratio was below 0.6, a 0.1 increase in normalized PTC aspect ratio was significantly associated with disease progression, with a hazard ratio (95% confidence interval) of 1.28 (1.04-1.59) (p=0.019), while PTC density and size were not significantly associated with outcome. Interstitial fractional space PTC density was lower in areas of IFTA compared to non-IFTA areas. Computational image analysis enables quantification of the status of the kidney microvasculature and the discovery of a previously unrecognized PTC biomarker (aspect ratio) of clinical outcome.

Abstract 5783: Integration of AI-powered digital pathology and imaging mass cytometry to identify relevant features of the tumor microenvironment

Abstract Digital pathology coupled to artificial intelligence (AI)-powered approaches are receiving great attention in the oncoimmunology field, as their adoption holds promise to improve current diagnostic workflows and potentiate the analytic outputs. In this work, we aimed at combining different histopathological approaches and AI-aided analytic tools to analyze the ecosystem of tumor tissues. By deploying AI-powered standard H&E and high-dimensional imaging-mass cytometry (IMC) to FFPE tissue samples, we could extract quantitative and standardized features that couldn’t have been easily identified and integrated by eye. One tissue microarray (TMA) slide containing 108 spots of NSCLC specimens (both adenocarcinoma and squamous carcinoma) was stained with H&E and scanned through the Axio Scan.Z1 (ZEISS) to generate high-quality virtual images. A deep learning algorithm was trained and applied to H&E images to identify tumor cells. The consecutive tissue section was stained with metal-labeled antibodies and processed through the Hyperion workflow (StandardBiotools), allowing quantitative detection of a panel of 23 markers related to tumor cells (Pan-cytokeratin), tissue architecture (aSMA, Vimentin, CD31, Collagen I, nuclei), CD45+ immune cells, comprehensive of myeloid cells (CD68, CD14, CD16, CD163, CD63, CCR4), lymphoid cells (CD3, CD4, CD8, FOXP3, CD20) and immune activation (S100A8, HLA-DR, Granzyme-B, KI67, Arginase-1). Data were exported as MCD files, visualized using the MCD viewer and further analyzed with the Qupath software. Cell segmentation was performed by the CellProfiler and Ilastik softwares and main cell populations were identified by a supervised approach through Cytomap. On H&E images, we generated a classifier of tumor heterogeneity, by exploring the spatial localization of tumor cells with the K-function summary statistic, which analyzes the distribution of tumor cells as a function of their distance. The resulting K-score value was then used to classify each tumor spot as diffuse, poorly clustered or highly clustered. Multiparametric computational analysis of the IMC images allowed to grasp immune and stromal classifiers, including frequency of immune cell populations in the tumor nests versus fibrotic stroma and immune cell interactions. In conclusion, AI-powered analysis of H&E slides is a robust approach that can improve manual scoring and unlock tissue relevant features opening to new diagnostic possibilities. Meanwhile, the analysis of the immune ecosystem by multiparametric imaging mass cytometry allows investigating spatial patterns and cell interactions at single-cell level. Integration of these approaches is feasible and allows the identification of tumor patient profiles with clinical relevance. Citation Format: Alessandra Rigamonti, Marika Viatore, Rebecca Polidori, Marco Erreni, Maria Fumagalli, Daoud Rahal, Massimo Locati, Alberto Mantovani, Federica Marchesi. Integration of AI-powered digital pathology and imaging mass cytometry to identify relevant features of the tumor microenvironment. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5783.

Abstract 5466: Functional status of tumor-associated macrophages impacts clinical outcome of durvalumab in patients with advanced NSCLC as revealed by proteomics mass spectrometry

Abstract Introduction: Predictive biomarkers of anti‒PD-(L)1 therapies have largely focused on the tumor-T cell axis where tumor cell PD-L1 expression has demonstrated its clinical utility in predicting overall survival (OS) in patients with advanced NSCLC. In prior work using computational image analysis of multiplex immunofluorescence (mIF), we have shown the positive impact of CD68+ PD-L1+ macrophages in combination with CD8+ T cells in predicting long-term OS benefit in NSCLC patients treated with durvalumab (anti-PD-L1), highlighting the impact of the myeloid compartment on IO responses. In part, using proteomics mass spectrometry we sought to investigate further the functional impact of myeloid cells on the IO response and in particular, suppressive (M2) tumor associated macrophages (TAMs). Methods: Pre-treatment tumor samples from 66 patients with advanced NSCLC patients enrolled in durvalumab nonrandomized phase 1/2 trial (10 mg/kg Q2W, CP1108/NCT01693562) were processed for global and targeted proteomics. A pathologist determined the tumor area and a single FFPE tumor tissue section was used for laser-capture macrodissection and protein extraction followed by mass spectrometry analysis using label-free, data-independent and parallel reaction monitoring. Results: Among the immune associated proteins detected by proteomics mass spectrometry, we evaluated CD163 protein expression, a well-described marker of suppressive (M2) macrophages, and its impact on durvalumab clinical outcomes, alone and in relationship with PD-L1 and immune infiltration. While proteomics-based biomarker evaluable population (BEP) shows shorter median (m) OS compared to intended to treat population, we validated that high expression of PD-L1 as measured by IHC or proteomics associates with greater OS benefit as expected when treating with durvalumab. Building on this, the evaluation of protein associated with suppressive M2 macrophages, revealed that approximately 30% of NSCLC patients with high CD163 protein expression show poor OS benefit (5 months mOS) following durvalumab treatment. In contrast, patients with PD-L1 TC ≥50% and low CD163 expression derive greater OS benefit (13.4 months mOS) than those with high CD163 expression (5 months mOS) or with PD-L1 TC <50% regardless of level of CD163 expression (4.1-7.4 months mOS). Moreover, patients with poorer outcome have significantly higher baseline CD163 protein expression as a proportion of total CD45 protein expression. Conclusion: This analysis further confirms the importance of myeloid cell function within the tumor microenvironment (TME) in determining the outcome to T cell-directed IO therapy and highlights the utility of proteomics mass spectrometry in assessing more broadly and quantitatively the TME complementing findings based on RNAseq and IHC/mIF assays. Citation Format: Anna Margaret Hansen, Vivian Ying Wang, Andrew Chambers, David Chain, Jaime Rodriguez Canales, Jorge Blando, Steve Sweet, Zachary A. Cooper, Ashok Gupta, Carl Barrett, Yeoun Jin Kim, Ikbel Achour. Functional status of tumor-associated macrophages impacts clinical outcome of durvalumab in patients with advanced NSCLC as revealed by proteomics mass spectrometry. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5466.

Возможности прижизненной визуализации клеток крови при стрессе для оценки состояния организма

Biological specimens are the most difficult to study as almost exclusively light elements are considered, a little visibility yielded and structures are sparsely distinguishable. In addition cell structures are easily damaged on any stage of microscopic exploration. The optimal solution is to study their phase changes using laser interference microscopy. The method is based on the analysis of refractive index of intracellular medium of cells with subsequent computer analysis and processing of phase images followed by three-dimensional reconstruction of the object. The obtained images are digitally recorded, and any point of view can be introduced for viewing. This work uses laser interference microscopy followed by 3D reconstruction of cell images to study blood cells: neutrophils and erythrocytes by 3D reconstruction of neutrophils have demonstrated changes of their functional activity under technological stress, while 3D reconstruction of erythrocytes revealed a violation of the normal discoidal cell shape. Interpretation of the obtained data indicates a restructuring of the cellular component of nonspecific resistance and deterioration of the oxygen transport function of erythrocytes under technological stress. Visualization of interference patterns of blood cells through 3D image processing allows obtaining n a vital analysis of cells, the technique that is not available for other methods of microscopy, in particular light microscopy, which is traditionally used as a prognostic method of the state of the body. This direction represents the most important condition for further development of works in the field of cell diagnostics. The obtained results prove the applicability of 3D reconstruction of cell images for bioscanning of technological stress.

Brightfield vs Fluorescent Staining Dataset–A Test Bed Image Set for Machine Learning based Virtual Staining

Differential fluorescent staining is an effective tool widely adopted for the visualization, segmentation and quantification of cells and cellular substructures as a part of standard microscopic imaging protocols. Incompatibility of staining agents with viable cells represents major and often inevitable limitations to its applicability in live experiments, requiring extraction of samples at different stages of experiment increasing laboratory costs. Accordingly, development of computerized image analysis methodology capable of segmentation and quantification of cells and cellular substructures from plain monochromatic images obtained by light microscopy without help of any physical markup techniques is of considerable interest. The enclosed set contains human colon adenocarcinoma Caco-2 cells microscopic images obtained under various imaging conditions with different viable vs non-viable cells fractions. Each field of view is provided in a three-fold representation, including phase-contrast microscopy and two differential fluorescent microscopy images with specific markup of viable and non-viable cells, respectively, produced using two different staining schemes, representing a prominent test bed for the validation of image analysis methods.

Structure and function of the aortic and pulmonary outflows in a patient, 12 years after Nikaidoh operation, A cautionary Note

BackgroundNikaidoh translocation operation is increasingly being used for patients with TGA, VSD and LVOTO. The early results of this operation are excellent and possibly better than the Rastelli repair. However, the long-term results remain inadequately defined. Methods and resultsDetailed follow up data of a patient, 12 years after Nikaidoh operation, using computerized image analysis are reported. The patient complained of chest pain on exertion. Imaging showed severe dilatation of the non-coronary sinus of the aortic root, compressing the RVOT and pulmonary artery branches resulting in RV dilatation. The dilated aortic sinus showed marked pulsatility with expansion during systole and diastole. As the child was symptomatic, with a risk of aneurysm rupture, excision was performed. This complication is thought to be due to interruption of the innervation of the root as well as cutting vasa vasorum. ConclusionNikaidoh operation is a viable solution for the repair of TGA, VSD, PS. Dilatation of the neo-aortic root should be carefully followed and causes of the dilatation investigated.

Polarity and mixed-mode oscillations may underlie different patterns of cellular migration

In mesenchymal cell motility, several migration patterns have been observed, including directional, exploratory and stationary. Two key members of the Rho-family of GTPases, Rac and Rho, along with an adaptor protein called paxillin, have been particularly implicated in the formation of such migration patterns and in regulating adhesion dynamics. Together, they form a key regulatory network that involves the mutual inhibition exerted by Rac and Rho on each other and the promotion of Rac activation by phosphorylated paxillin. Although this interaction is sufficient in generating wave-pinning that underscores cellular polarization comprised of cellular front (high active Rac) and back (high active Rho), it remains unclear how they interact collectively to induce other modes of migration detected in Chinese hamster Ovary (CHO-K1) cells. We previously developed a six-variable (6V) reaction–diffusion model describing the interactions of these three proteins (in their active/phosphorylated and inactive/unphosphorylated forms) along with other auxiliary proteins, to decipher their role in generating wave-pinning. In this study, we explored, through computational modeling and image analysis, how differences in timescales within this molecular network can potentially produce the migration patterns in CHO-K1 cells and how switching between migration modes could occur. To do so, the 6V model was reduced to an excitable 4V spatiotemporal model possessing three different timescales. The model produced not only wave-pinning in the presence of diffusion, but also mixed-mode oscillations (MMOs) and relaxation oscillations (ROs). Implementing the model using the Cellular Potts Model (CPM) produced outcomes in which protrusions in the cell membrane changed Rac–Rho localization, resulting in membrane oscillations and fast directionality variations similar to those observed experimentally in CHO-K1 cells. The latter was assessed by comparing the migration patterns of experimental with CPM cells using four metrics: instantaneous cell speed, exponent of mean-square displacement (alpha-value), directionality ratio and protrusion rate. Variations in migration patterns induced by mutating paxillin’s serine 273 residue were also captured by the model and detected by a machine classifier, revealing that this mutation alters the dynamics of the system from MMOs to ROs or nonoscillatory behaviour through variation in the scaled concentration of an active form of an adhesion protein called p21-Activated Kinase 1 (PAK). These results thus suggest that MMOs and adhesion dynamics are the key mechanisms regulating CHO-K1 cell motility.

Abstract P2-11-16: Computerized Measurements of Nuclear Morphology Features, Mitosis Rate, and Tubule Formation from H&E Images Predicts Disease-Free Survival in Patients with HR+ & LN+ Invasive Breast Cancer from SWOG S8814

Abstract Background: Lymph node (LN) involvement is a strong indicator of poor prognosis for breast cancer (BC), with adjuvant chemotherapy remaining fundamental to management of these patients. SWOG S8814 was a Phase III randomized trial of postmenopausal patients with pathologic LN-positive BC who were hormone receptor positive (HR+). The objectives of the clinical trial were to compare disease free survival (DFS) and overall survival (OS) of 1) these postoperative patients treated with a combination of cyclophosphamide, doxorubicin, fluorouracil (CAF) plus tamoxifen versus tamoxifen alone; and 2) patients treated with CAF followed by tamoxifen versus CAF plus concurrent tamoxifen. In this study we sought to evaluate the potential of applying computational image analysis on whole slide images (WSI) for predicting DFS and OS in SWOG S8814. Methods: A cohort of 135 patients (N=53 DFS event) diagnosed with HR+ & LN+ BC from clinical trial ECOG 2197 was utilized as training set D1. Validation set D2 comprised 630 patients (N=260 DFS event, N=195 death) with HR+& LN+ BC from SWOG S8814. Three deep learning models were employed to respectively detect nuclei, mitosis, and tubules in WSIs. Subsequently, a total of 1,810 features relating to nuclear morphology (e.g., spatial distribution, shape, texture, orientation), mitotic activity (e.g., mitosis hotspot, mitotic rates) and tubule formation (e.g., tubular nuclei distribution, ratio of tubule to non-tubule area) were extracted from each WSI. A lasso regularized Cox regression model (IbRiS) was trained on D1 to respectively identify four features from each of the feature categories (nuclei morphology, mitotic activity, and tubule formation) most strongly associated with DFS, a continuous risk score based on the selected features was then constructed. An optimal risk threshold was identified on D1 to dichotomize the risk scores into high vs. low risk of recurrence categories. Blinded validation of the machine learning model on SWOG S8814 using Cox regression was performed by SWOG to evaluate its performance in terms of DFS and OS. Results: In D2, patients identified as high risk of recurrence by IbRiS had a significantly worse prognosis in terms of DFS with hazard ratio=1.30 (p=0.039, 95% CI=1.01-1.66). IbRiS was also found to be significantly prognostic of OS with hazard ratio=1.38 (p=0.026, 95% CI=1.04-1.83). IbRiS was however, neither prognostic of DFS (HR = 1.20; 95% CI 0.93-1.54) nor OS (HR = 1.28; 95% CI 0.96-1.71) in multivariable analysis adjusting for treatment, tumor size, and number of positive nodes. IbRiS was also not a significant predictor of chemotherapy benefit (DFS p=0.45; OS p=0.25). Conclusion: We developed a prognostic model (IbRiS) based on the combined features of nuclear morphology, mitosis count, and tubule formation that can help further risk stratify HR+ & LN+ BC patients by only using H&E slides. Citation Format: Yuli Chen, William E. Barlow, Haojia Li, Cheng Lu, Andrew Janowczyk, German Corredor, Shridar Ganesan, Michael Feldman, Pingfu Fu, Hannah Gilmore, Kathy S. Albain, Lajos Pusztai, James Rae, Daniel Hayes, Andrew K. Godwin, Alastair M. Thompson, Anant Madabhushi. Computerized Measurements of Nuclear Morphology Features, Mitosis Rate, and Tubule Formation from H&E Images Predicts Disease-Free Survival in Patients with HR+ & LN+ Invasive Breast Cancer from SWOG S8814 [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P2-11-16.

Geographical Influence on Morphometric Variability of Genetically "Pure" Schistosoma haematobium Eggs from Sub-Saharan Migrants in Spain.

Schistosome eggs play a key role in schistosomiasis diagnosis and research. The aim of this work is to morphogenetically study the eggs of Schistosoma haematobium found in sub-Saharan migrants present in Spain, analyzing their morphometric variation in relation to the geographical origin of the parasite (Mali, Mauritania and Senegal). Only eggs considered "pure" S. haematobium by genetic characterization (rDNA ITS-2 and mtDNA cox1) have been used. A total of 162 eggs obtained from 20 migrants from Mali, Mauritania and Senegal were included in the study. Analyses were made by the Computer Image Analysis System (CIAS). Following a previously standardized methodology, seventeen measurements were carried out on each egg. The morphometric analysis of the three morphotypes detected (round, elongated and spindle) and the biometric variations in relation to the country of origin of the parasite on the egg phenotype were carried out by canonical variate analysis. Mahalanobis distances, when all egg measurements were analyzed, showed differences between: (i) Mali-Mauritania, Mali-Senegal and Mauritania-Senegal in the round morphotype; (ii) Mali-Mauritania and Mauritania-Senegal in the elongated morphotype; and (iii) Mauritania-Senegal in the spindle morphotype. Mahalanobis distances, when spine variables were analyzed, showed differences between Mali-Senegal in the round morphotype. In conclusion, this is the first phenotypic study performed on individually genotyped "pure" S. haematobium eggs, allowing the assessment of the intraspecific morphological variations associated with the geographical origin of the schistosome eggs.

Colorimetric and fluorimetric pH sensing using polydiacetylene embedded within PVC‐PCL nanofibers

AbstractThe applicability of model polydiacetylenes (PDAs) in hydrogen ions sensitive optodes was tested. Nanofibers mats were electrospun using a mixture of polyvinyl chloride (PVC) and polycaprolactone (PCL) together with 10, 12‐tricosadiynoic acid (TCDA) or 10,12‐pentacosadiynoic acid (PCDA). After the polymerization the mats were applied in colorimetric and fluorimetric pH sensors. The PDAs were formed by photopolymerization with a UV lamp (254 nm), resulting in a change of mats color from white to dark blue. The morphology of both fiber mats is similar (SEM images), and the average diameters of fibers were estimated as equal to 228±73 and 248±61 nm for TCDA and PCDA, respectively. As the pH increases, the color of the fiber mat changes from blue to red and the process can be followed visually. The result obtained by computer image analysis showed a sigmoidal increase in the intensity of red and a decrease in the intensity of blue color with increasing pH. A similar sigmoidal response is observed for the dependence of the emission intensity on the pH. Changes in the recorded signal occur in the pH range from 7 to 8.5 or from 8 to 9.5 for mats with TCDA and PCDA, respectively. Both readout modes can be successfully used for pH sensing with proposed nanofibrous mats in the range of pH close to the physiological pH range.

Machine learning analysis of complex late gadolinium enhancement patterns to improve risk prediction of major arrhythmic events.

Machine learning analysis of complex myocardial scar patterns affords the potential to enhance risk prediction of life-threatening arrhythmia in stable coronary artery disease (CAD). To assess the utility of computational image analysis, alongside a machine learning (ML) approach, to identify scar microstructure features on late gadolinium enhancement cardiovascular magnetic resonance (LGE-CMR) that predict major arrhythmic events in patients with CAD. Patients with stable CAD were prospectively recruited into a CMR registry. Shape-based scar microstructure features characterizing heterogeneous ('peri-infarct') and homogeneous ('core') fibrosis were extracted. An ensemble of machine learning approaches were used for risk stratification, in addition to conventional analysis using Cox modeling. Of 397 patients (mean LVEF 45.4 ± 16.0) followed for a median of 6 years, 55 patients (14%) experienced a major arrhythmic event. When applied within an ML model for binary classification, peri-infarct zone (PIZ) entropy, peri-infarct components and core interface area outperformed a model representative of the current standard of care (LVEF<35% and NYHA>Class I): AUROC (95%CI) 0.81 (0.81-0.82) vs. 0.64 (0.63-0.65), p = 0.002. In multivariate cox regression analysis, these features again remained significant after adjusting for LVEF<35% and NYHA>Class I: PIZ entropy hazard ratio (HR) 1.88, 95% confidence interval (CI) 1.38-2.56, p < 0.001; number of PIZ components HR 1.34, 95% CI 1.08-1.67, p = 0.009; core interface area HR 1.6, 95% CI 1.29-1.99, p = <0.001. Machine learning models using LGE-CMR scar microstructure improved arrhythmic risk stratification as compared to guideline-based clinical parameters; highlighting a potential novel approach to identifying candidates for implantable cardioverter defibrillators in stable CAD.

A Survey on Evolutionary Computation for Computer Vision and Image Analysis: Past, Present, and Future Trends

Computer vision (CV) is a big and important field in artificial intelligence covering a wide range of applications. Image analysis is a major task in CV aiming to extract, analyse and understand the visual content of images. However, image-related tasks are very challenging due to many factors, e.g., high variations across images, high dimensionality, domain expertise requirement, and image distortions. Evolutionary computation (EC) approaches have been widely used for image analysis with significant achievement. However, there is no comprehensive survey of existing EC approaches to image analysis. To fill this gap, this paper provides a comprehensive survey covering all essential EC approaches to important image analysis tasks including edge detection, image segmentation, image feature analysis, image classification, object detection, and others. This survey aims to provide a better understanding of evolutionary computer vision (ECV) by discussing the contributions of different approaches and exploring how and why EC is used for CV and image analysis. The applications, challenges, issues, and trends associated to this research field are also discussed and summarised to provide further guidelines and opportunities for future research.

Quantifying Podocyte Number in a Small Sample Size of Glomeruli with CUBIC to Evaluate Podocyte Depletion of db/db Mice.

The loss of podocyte is crucial for diagnosis and prognosis of diabetic kidney disease, whereas commonly two-dimensional methods for quantifying podocyte number existed with issues of low fidelity and accuracy. In this study, clear, unobstructed brain imaging cocktails and computational analysis (CUBIC), one of three-dimensional optical clearing approaches, was used which combines tissue clearing, immunolabeling, and a light-sheet microscope to image and evaluate podocytes in C57BL/6 (C57) and db/db mice. We discovered that 77 podocytes per glomerulus were in C57 mice. On the subject of db/db mice, there were 74 podocytes by the age of 8 w, 72 podocytes by the age of 12 w, and 66 podocytes by the age of 16 w, compared with 76 podocytes in the control group, suggesting that there was a significant decrease in podocyte number in db/db mice with the age of 16 w, showing a trend which positively correlated to the deterioration of kidney function. Sample size estimation using the PASS software revealed that taking 5%, 7.5%, and 10% of the mean podocyte number per glomerulus as the statistical allowable error and 95% as total confidence interval, 33, 15, and 9 glomeruli were independently needed to be sampled in C57 mice to represent the overall glomeruli to calculate podocyte number. Furthermore, in the control group of db/db mice, 36, 18, and 11 glomeruli were needed, compared with 46, 24, and 14 glomeruli in db/db mice by the age of 8 w, 43, 21, and 12 glomeruli by the age of 12 w, and 52, 27, and 16 by the age of 16 w. These findings indicated that precise quantification of podocyte number could judge the progression of diabetic kidney disease. In addition, a small number of glomeruli could be actually representative of the whole sample size, which indicated apparent practicability of CUBIC for clinical use.

Single patch super-resolution of histopathology whole slide images: a comparative study.

The latest generation of scanners can digitize histopathology glass slides for computerized image analysis. These images contain valuable information for diagnostic and prognostic purposes. Consequently, the availability of high digital magnifications like and is commonly expected in scanning the slides. Thus, the image acquisition typically generates gigapixel high-resolution images, times as large as . Naturally, the storage and processing of such huge files may be subject to severe computational bottlenecks. As a result, the need for techniques that can operate on lower magnification levels but produce results on par with outcomes for high magnification levels is becoming urgent. Over the past decade, the digital solution of enhancing images resolution has been addressed by the concept of super resolution (SR). In addition, deep learning has offered state-of-the-art results for increasing the image resolution after acquisition. In this study, multiple deep learning networks designed for image SR are trained and assessed for the histopathology domain. We report quantitative and qualitative comparisons of the results using publicly available cancer images to shed light on the benefits and challenges of deep learning for extrapolating image resolution in histopathology. Three pathologists evaluated the results to assess the quality and diagnostic value of generated SR images. Pixel-level information, including structures and textures in histopathology images, are learnable by deep networks; hence improving the resolution quantity of scanned slides is possible by training appropriate networks. Different SR networks may perform best for various cancer sites and subtypes.

Computer Vision and Image Analysis of Art 2023 Conference Overview and Papers Program

Computer Vision and Image Analysis of Art 2023 Conference Overview and Papers Program

Traditional vs. Automated Computer Image Analysis-A Comparative Assessment of Use for Analysis of Digital SEM Images of High-Temperature Ceramic Material.

Image analysis is a powerful tool that can be applied in scientific research, industry, and everyday life, but still, there is more room to use it in materials science. The interdisciplinary cooperation between materials scientists and computer scientists can unlock the potential of digital image analysis. Traditional image analysis used in materials science, manual or computer-aided, permits for the quantitative assessment of the coexisting components at the cross-sections, based on stereological law. However, currently used cutting-edge tools for computer image analysis can greatly speed up the process of microstructure analysis, e.g., via simultaneous extraction of quantitative data of all phases in an SEM image. The dedicated digital image processing software Aphelion was applied to develop an algorithm for the automated image analysis of multi-phase high-temperature ceramic material. The algorithm recognizes each phase and simultaneously calculates its quantity. In this work, we compare the traditional stereology-based methods of image analysis (linear and planimetry) to the automated method using a developed algorithm. The analysis was performed on a digital SEM microstructural image of high-temperature ceramic material from the Cu-Al-Fe-O system, containing four different phase components. The results show the good agreement of data obtained by classical stereology-based methods and the developed automated method. This presents an opportunity for the fast extraction of both qualitative and quantitative from the SEM images.

Comprehensive Phenotypic Characterization of Late Gadolinium Enhancement Predicts Sudden Cardiac Death in Coronary Artery Disease

BackgroundLate gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) offers the potential to noninvasively characterize the phenotypic substrate for sudden cardiac death (SCD). ObjectivesThe authors assessed the utility of infarct characterization by CMR, including scar microstructure analysis, to predict SCD in patients with coronary artery disease (CAD). MethodsPatients with stable CAD were prospectively recruited into a CMR registry. LGE quantification of core infarction and the peri-infarct zone (PIZ) was performed alongside computational image analysis to extract morphologic and texture scar microstructure features. The primary outcome was SCD or aborted SCD. ResultsOf 437 patients (mean age: 64 years; mean left ventricular ejection fraction [LVEF]: 47%) followed for a median of 6.3 years, 49 patients (11.2%) experienced the primary outcome. On multivariable analysis, PIZ mass and core infarct mass were independently associated with the primary outcome (per gram: HR: 1.07 [95% CI: 1.02-1.12]; P = 0.002 and HR: 1.03 [95% CI: 1.01-1.05]; P = 0.01, respectively), and the addition of both parameters improved discrimination of the model (Harrell’s C-statistic: 0.64-0.79). PIZ mass, however, did not provide incremental prognostic value over core infarct mass based on Harrell’s C-statistic or risk reclassification analysis. Severely reduced LVEF did not predict the primary endpoint after adjustment for scar mass. On scar microstructure analysis, the number of LGE islands in addition to scar transmurality, radiality, interface area, and entropy were all associated with the primary outcome after adjustment for severely reduced LVEF and New York Heart Association functional class of >1. No scar microstructure feature remained associated with the primary endpoint when PIZ mass and core infarct mass were added to the regression models. ConclusionsComprehensive LGE characterization independently predicted SCD risk beyond conventional predictors used in implantable cardioverter-defibrillator (ICD) insertion guidelines. These results signify the potential for a more personalized approach to determining ICD candidacy in CAD.

A review of computational modeling, machine learning and image analysis in cancer metastasis dynamics

AbstractCancer is a life‐threatening process that stems from genetic mutations in cells, which leads to the formation of tumors, and is a major cause of deaths in the United States, with secondary metastasis being a major driver of fatality. The development of an optimal metastatic environment is an essential process prior to tumor metastasis. This process, called pre‐metastatic niche formation, involves the activation of resident fibroblast‐like cells and macrophages. Tumor‐mediated factors introduced to this environment transform resident cells that secrete additional growth factors and remodel the extracellular matrix, which is thought to promote tumor colonization and metastasis in the secondary environment. Furthermore, an important component of metastasis is the biological process of epithelial–mesenchymal transition, which can be exploited by cancer cells to change their phenotype, to migrate and proliferate as necessary. In this review, we discuss recent advances in the investigation of cancer growth and migration. Computational models that focus on biochemical signaling and multicellular dynamics are examined. Machine learning models and image analysis that classify cancer‐related data are also explored. Through this review, we highlight advances in the study of important aspects of cancer and metastasis signaling and computational tools to study these dynamics.

Ten quick tips for computational analysis of medical images.

Medical imaging is a great asset for modern medicine, since it allows physicians to spatially interrogate a disease site, resulting in precise intervention for diagnosis and treatment, and to observe particular aspect of patients' conditions that otherwise would not be noticeable. Computational analysis of medical images, moreover, can allow the discovery of disease patterns and correlations among cohorts of patients with the same disease, thus suggesting common causes or providing useful information for better therapies and cures. Machine learning and deep learning applied to medical images, in particular, have produced new, unprecedented results that can pave the way to advanced frontiers of medical discoveries. While computational analysis of medical images has become easier, however, the possibility to make mistakes or generate inflated or misleading results has become easier, too, hindering reproducibility and deployment. In this article, we provide ten quick tips to perform computational analysis of medical images avoiding common mistakes and pitfalls that we noticed in multiple studies in the past. We believe our ten guidelines, if taken into practice, can help the computational-medical imaging community to perform better scientific research that eventually can have a positive impact on the lives of patients worldwide.

Cell Division and Meristem Dynamics in Fern Gametophytes.

One of the most important questions in all multicellular organisms is how to define and maintain different cell fates during continuous cell division and proliferation. Plant meristems provide a unique research system to address this fundamental question because meristems dynamically maintain themselves and sustain organogenesis through balancing cell division and cell differentiation. Different from the gametophytes of seed plants that depend on their sporophytes and lack meristems, the gametophytes of seed-free ferns develop different types of meristems (including apical cell-based meristems and multicellular apical and marginal meristems) to promote independent growth and proliferation during the sexual gametophyte phase. Recent studies combining confocal time-lapse imaging and computational image analysis reveal the cellular basis of the initiation and proliferation of different types of meristems in fern gametophytes, providing new insights into the evolution of meristems in land plants. In this review, we summarize the recent progress in understanding the cell growth dynamics in fern gametophytes and discuss both conserved and diversified mechanisms underlying meristem cell proliferation in seed-free vascular plants.