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

PrestoCell: A persistence-based clustering approach for rapid and robust segmentation of cellular morphology in three-dimensional data

Light microscopy methods have continued to advance allowing for unprecedented analysis of various cell types in tissues including the brain. Although the functional state of some cell types such as microglia can be determined by morphometric analysis, techniques to perform robust, quick, and accurate measurements have not kept pace with the amount of imaging data that can now be generated. Most of these image segmentation tools are further burdened by an inability to assess structures in three-dimensions. Despite the rise of machine learning techniques, the nature of some biological structures prevents the training of several current day implementations. Here we present PrestoCell, a novel use of persistence-based clustering to segment cells in light microscopy images, as a customized Python-based tool that leverages the free multidimensional image viewer Napari. In evaluating and comparing PrestoCell to several existing tools, including 3DMorph, Omipose, and Imaris, we demonstrate that PrestoCell produces image segmentations that rival these solutions. In particular, our use of cell nuclei information resulted in the ability to correctly segment individual cells that were interacting with one another to increase accuracy. These benefits are in addition to the simplified graphically based user refinement of cell masks that does not require expensive commercial software licenses. We further demonstrate that PrestoCell can complete image segmentation in large samples from light sheet microscopy, allowing quantitative analysis of these large datasets. As an open-source program that leverages freely available visualization software, with minimum computer requirements, we believe that PrestoCell can significantly increase the ability of users without data or computer science expertise to perform complex image analysis.

Three-dimensional topological radiogenomics of epidermal growth factor receptor Del19 and L858R mutation subtypes on computed tomography images of lung cancer patients

OBJECTIVES

To elucidate a novel radiogenomics approach using three-dimensional (3D) topologically invariant Betti numbers (BNs) for topological characterization of epidermal growth factor receptor (EGFR) Del19 and L858R mutation subtypes.

METHODS

In total, 154 patients (wild-type EGFR, 72 patients; Del19 mutation, 45 patients; and L858R mutation, 37 patients) were retrospectively enrolled and randomly divided into 92 training and 62 test cases. Two support vector machine (SVM) models to distinguish between wild-type and mutant EGFR (mutation [M] classification) as well as between the Del19 and L858R subtypes (subtype [S] classification) were trained using 3DBN features. These features were computed from 3DBN maps by using histogram and texture analyses. The 3DBN maps were generated using computed tomography (CT) images based on the Čech complex constructed on sets of points in the images. These points were defined by coordinates of voxels with CT values higher than several threshold values. The M classification model was built using image features and demographic parameters of sex and smoking status. The SVM models were evaluated by determining their classification accuracies. The feasibility of the 3DBN model was compared with those of conventional radiomic models based on pseudo-3D BN (p3DBN), two-dimensional BN (2DBN), and CT and wavelet-decomposition (WD) images. The validation of the model was repeated with 100 times random sampling.

RESULTS

The mean test accuracies for M classification with 3DBN, p3DBN, 2DBN, CT, and WD images were 0.810, 0.733, 0.838, 0.782, and 0.799, respectively. The mean test accuracies for S classification with 3DBN, p3DBN, 2DBN, CT, and WD images were 0.773, 0.694, 0.657, 0.581, and 0.696, respectively.

CONCLUSION

3DBN features, which showed a radiogenomic association with the characteristics of the EGFR Del19/L858R mutation subtypes, yielded higher accuracy for subtype classifications in comparison with conventional features.

Topology-based fluorescence image analysis for automated cell identification and segmentation

Cell segmentation refers to the body of techniques used to identify cells in images and extract biologically relevant information from them; however, manual segmentation is laborious and subjective. We present Topological Boundary Line Estimation using Recurrence Of Neighbouring Emissions (TOBLERONE), a topological image analysis tool which identifies persistent homological image features as opposed to the geometric analysis commonly employed. We demonstrate that topological data analysis can provide accurate segmentation of arbitrarily-shaped cells, offering a means for automatic and objective data extraction. One cellular feature of particular interest in biology is the plasma membrane, which has been shown to present varying degrees of lipid packing, or membrane order, depending on the function and morphology of the cell type. With the use of environmentally-sensitive dyes, images derived from confocal microscopy can be used to quantify the degree of membrane order. We demonstrate that TOBLERONE is capable of automating this task.

Cell segmentation from telecentric bright-field transmitted light microscopy images using a Residual Attention U-Net: A case study on HeLa line

Living cell segmentation from bright-field light microscopy images is challenging due to the image complexity and temporal changes in the living cells. Recently developed deep learning (DL)-based methods became popular in medical and microscopy image segmentation tasks due to their success and promising outcomes. The main objective of this paper is to develop a deep learning, U-Net-based method to segment the living cells of the HeLa line in bright-field transmitted light microscopy. To find the most suitable architecture for our datasets, a residual attention U-Net was proposed and compared with an attention and a simple U-Net architecture. The attention mechanism highlights the remarkable features and suppresses activations in the irrelevant image regions. The residual mechanism overcomes with vanishing gradient problem. The Mean-IoU score for our datasets reaches 0.9505, 0.9524, and 0.9530 for the simple, attention, and residual attention U-Net, respectively. The most accurate semantic segmentation results was achieved in the Mean-IoU and Dice metrics by applying the residual and attention mechanisms together. The watershed method applied to this best - Residual Attention - semantic segmentation result gave the segmentation with the specific information for each cell.

Topological data analysis in biomedicine: A review

Significant technological advances made in recent years have shepherded a dramatic increase in utilization of digital technologies for biomedicine- everything from the widespread use of electronic health records to improved medical imaging capabilities and the rising ubiquity of genomic sequencing contribute to a "digitization" of biomedical research and clinical care. With this shift toward computerized tools comes a dramatic increase in the amount of available data, and current tools for data analysis capable of extracting meaningful knowledge from this wealth of information have yet to catch up. This article seeks to provide an overview of emerging mathematical methods with the potential to improve the abilities of clinicians and researchers to analyze biomedical data, but may be hindered from doing so by a lack of conceptual accessibility and awareness in the life sciences research community. In particular, we focus on topological data analysis (TDA), a set of methods grounded in the mathematical field of algebraic topology that seeks to describe and harness features related to the "shape" of data. We aim to make such techniques more approachable to non-mathematicians by providing a conceptual discussion of their theoretical foundations followed by a survey of their published applications to scientific research. Finally, we discuss the limitations of these methods and suggest potential avenues for future work integrating mathematical tools into clinical care and biomedical informatics.

Imaging-Based Machine Learning Analysis of Patient-Derived Tumor Organoid Drug Response

Three-quarters of compounds that enter clinical trials fail to make it to market due to safety or efficacy concerns. This statistic strongly suggests a need for better screening methods that result in improved translatability of compounds during the preclinical testing period. Patient-derived organoids have been touted as a promising 3D preclinical model system to impact the drug discovery pipeline, particularly in oncology. However, assessing drug efficacy in such models poses its own set of challenges, and traditional cell viability readouts fail to leverage some of the advantages that the organoid systems provide. Consequently, phenotypically evaluating complex 3D cell culture models remains difficult due to intra- and inter-patient organoid size differences, cellular heterogeneities, and temporal response dynamics. Here, we present an image-based high-content assay that provides object level information on 3D patient-derived tumor organoids without the need for vital dyes. Leveraging computer vision, we segment and define organoids as independent regions of interest and obtain morphometric and textural information per organoid. By acquiring brightfield images at different timepoints in a robust, non-destructive manner, we can track the dynamic response of individual organoids to various drugs. Furthermore, to simplify the analysis of the resulting large, complex data files, we developed a web-based data visualization tool, the Organoizer, that is available for public use. Our work demonstrates the feasibility and utility of using imaging, computer vision and machine learning to determine the vital status of individual patient-derived organoids without relying upon vital dyes, thus taking advantage of the characteristics offered by this preclinical model system.

Computational Image Analysis Identifies Histopathological Image Features Associated With Somatic Mutations and Patient Survival in Gastric Adenocarcinoma

Computational analysis of histopathological images can identify sub-visual objective image features that may not be visually distinguishable by human eyes, and hence provides better modeling of disease phenotypes. This study aims to investigate whether specific image features are associated with somatic mutations and patient survival in gastric adenocarcinoma (sample size = 310). An automated image analysis pipeline was developed to extract quantitative morphological features from H&E stained whole-slide images. We found that four frequently somatically mutated genes (TP53, ARID1A, OBSCN, and PIK3CA) were significantly associated with tumor morphological changes. A prognostic model built on the image features significantly stratified patients into low-risk and high-risk groups (log-rank test p-value = 2.6e-4). Multivariable Cox regression showed the model predicted risk index was an additional prognostic factor besides tumor grade and stage. Gene ontology enrichment analysis showed that the genes whose expressions mostly correlated with the contributing features in the prognostic model were enriched on biological processes such as cell cycle and muscle contraction. These results demonstrate that histopathological image features can reflect underlying somatic mutations and identify high-risk patients that may benefit from more precise treatment regimens. Both the image features and pipeline are highly interpretable to enable translational applications.

Segmentation of biomedical images based on a computational topology framework

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

Interrogating the microenvironmental landscape of tumors with computational image analysis approaches

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

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

BACKGROUND

For virtually every patient with colorectal cancer (CRC), hematoxylin-eosin (HE)-stained tissue slides are available. These images contain quantitative information, which is not routinely used to objectively extract prognostic biomarkers. In the present study, we investigated whether deep convolutional neural networks (CNNs) can extract prognosticators directly from these widely available images.

METHODS AND FINDINGS

We hand-delineated single-tissue regions in 86 CRC tissue slides, yielding more than 100,000 HE image patches, and used these to train a CNN by transfer learning, reaching a nine-class accuracy of >94% in an independent data set of 7,180 images from 25 CRC patients. With this tool, we performed automated tissue decomposition of representative multitissue HE images from 862 HE slides in 500 stage I-IV CRC patients in the The Cancer Genome Atlas (TCGA) cohort, a large international multicenter collection of CRC tissue. Based on the output neuron activations in the CNN, we calculated a "deep stroma score," which was an independent prognostic factor for overall survival (OS) in a multivariable Cox proportional hazard model (hazard ratio [HR] with 95% confidence interval [CI]: 1.99 [1.27-3.12], p = 0.0028), while in the same cohort, manual quantification of stromal areas and a gene expression signature of cancer-associated fibroblasts (CAFs) were only prognostic in specific tumor stages. We validated these findings in an independent cohort of 409 stage I-IV CRC patients from the "Darmkrebs: Chancen der Verhütung durch Screening" (DACHS) study who were recruited between 2003 and 2007 in multiple institutions in Germany. Again, the score was an independent prognostic factor for OS (HR 1.63 [1.14-2.33], p = 0.008), CRC-specific OS (HR 2.29 [1.5-3.48], p = 0.0004), and relapse-free survival (RFS; HR 1.92 [1.34-2.76], p = 0.0004). A prospective validation is required before this biomarker can be implemented in clinical workflows.

CONCLUSIONS

In our retrospective study, we show that a CNN can assess the human tumor microenvironment and predict prognosis directly from histopathological images.

Multilacunarity as a spatial multiscale multi-mass morphometric of change in the meso-architecture of plant parenchyma tissue

The lacunarity index (monolacunarity) averages the behavior of variable size structures in a binary image. The generalized lacunarity concept (multilacunarity) on the basis of generalized distribution moments is an appealing model that can account for differences in the mass content at different scales. The model was tested previously on natural images [J. Vernon-Carter et al., Physica A 388, 4305 (2009)]. Here, the computational aspects of multilacunarity are validated using synthetic binary images that consist of random maps, spatial stochastic patterns, patterns with circular or polygonal elements, and a plane fractal. Furthermore, monolacunarity and detrended fluctuation analysis were employed to quantify the mesostructural changes in the intercellular air spaces of frozen-thawed parenchymatous tissue of pome fruit [N. A. Valous et al., J. Appl. Phys. 115, 064901 (2014)]. Here, the aim is to further examine the coherence of the multilacunarity model for quantifying the mesostructural changes in the intercellular air spaces of parenchymatous tissue of pome and stone fruit, acquired with X-ray microcomputed tomography, after storage and ripening, respectively. The multilacunarity morphometric is a multiscale multi-mass fingerprint of spatial pattern composition, assisting the exploration of the effects of metabolic and physiological activity on the pore space of plant parenchyma tissue.

Research on FAE Cloud Image Processing Method Based on Background Subtraction and Region Growing

After the first initiation, the Fuel Air Explosive (FAE) cloud formed through fuel explosion dispersal and it will generate tremendous damaging power after being detonated the second time. As the damaging power is closely related to the determination of reinitiation time, it is of great significance to study the growth principle of FAE cloud by means of analyzing FAE cloud images. Combining with background subtraction and region growing, an improved region growing image processing method was proposed, in which the seeds of region growing abstracted through background subtraction method and the growing criterion was modified. With this method, the integrate area of cloud can be obtained for extracting geometric parameters. Experiments were carried out on both cloudy and sunny days, and image overlap score was used to quantitatively evaluate the accuracy of images segmentation. The result indicated that this image processing method has advantages of high precision and robustness. In addition, the computation burden is reduced significantly compared with traditional region growing method.