An image processing approach to analyze morphological features of microscopic images of muscle fibers

Integrated Cells and Collagen Fibers Spatial Image Analysis

Modern technologies designed for tissue structure visualization like brightfield microscopy, fluorescent microscopy, mass cytometry imaging (MCI) and mass spectrometry imaging (MSI) provide large amounts of quantitative and spatial information about cells and tissue structures like vessels, bronchioles etc. Many published reports have demonstrated that the structural features of cells and extracellular matrix (ECM) and their interactions strongly predict disease development and progression. Computational image analysis methods in combination with spatial analysis and machine learning can reveal novel structural patterns in normal and diseased tissue. Here, we have developed a Python package designed for integrated analysis of cells and ECM in a spatially dependent manner. The package performs segmentation, labeling and feature analysis of ECM fibers, combines this information with pre-generated single-cell based datasets and realizes cell-cell and cell-fiber spatial analysis. To demonstrate performance and compatibility of our computational tool, we integrated it with a pipeline designed for cell segmentation, classification, and feature analysis in the KNIME analytical platform. For validation, we used a set of mouse mammary gland tumors and human lung adenocarcinoma tissue samples stained for multiple cellular markers and collagen as the main ECM protein. The developed package provides sufficient performance and precision to be used as a novel method to investigate cell-ECM relationships in the tissue, as well as detect structural patterns correlated with specific disease outcomes.

Characterization of heterogeneous primary human cartilage-derived cell population using non-invasive live-cell phase-contrast time-lapse imaging

Reliable and reproducible cell therapy strategies to treat osteoarthritis demand an improved characterization of the cell and heterogeneous cell population resident in native cartilage tissue. Using live-cell phase-contrast time-lapse imaging (PC-TLI), this study investigates the morphological attributes and biological performance of the three primary biological objects enzymatically isolated from primary human cartilage: connective tissue progenitors (CTPs), non-progenitors (NPs) and multi-cellular structures (MCSs). The authors' results demonstrated that CTPs were smaller in size in comparison to NPs (P < 0.001). NPs remained part of the adhered cell population throughout the cell culture period. Both NPs and CTP progeny on day 8 increased in size and decreased in circularity in comparison to their counterparts on day 1, although the percent change was considerably less in CTP progeny (P < 0.001). PC-TLI analyses indicated three colony types: single-CTP-derived (29%), multiple-CTP-derived (26%) and MCS-derived (45%), with large heterogeneity with respect to cell morphology, proliferation rate and cell density. On average, clonal (CL) (P = 0.009) and MCS (P = 0.001) colonies exhibited higher cell density (cells per colony area) than multi-clonal (MC) colonies; however, it is interesting to note that the behavior of CL (less cells per colony and less colony area) and MCS (high cells per colony and high colony area) colonies was quite different. Overall effective proliferation rate (EPR) of the CTPs that formed CL colonies was higher than the EPR of CTPs that formed MC colonies (P = 0.02), most likely due to CTPs with varying EPR that formed the MC colonies. Finally, the authors demonstrated that lag time before first cell division of a CTP (early attribute) could potentially help predict its proliferation rate long-term. Quantitative morphological characterization using non-invasive PC-TLI serves as a reliable and reproducible technique to understand cell heterogeneity. Size and circularity parameters can be used to distinguish CTP from NP populations. Morphological cell and colony features can also be used to reliably and reproducibly identify CTP subpopulations with preferred proliferation and differentiation potentials in an effort to improve cell manufacturing and therapeutic outcomes.

A neural network approach to analyze cross-sections of muscle fibers in pathological images

Morphological characteristics of muscle fibers, such as their cross-sections, are important indicators of the health and function of the musculoskeletal system. However, manual analysis of muscle fiber morphology is a labor-intensive and time-consuming process that is prone to errors. Overall, the procedure involves high inter- and intra-observer variability. Therefore, it is desirable for biologists to have a tool that can produce objective and reproducible analysis for muscle fiber images. In this work, we propose a deep convolutional neural network (DCNN) followed by post-processing for detecting and measuring the cross-sections of muscle fibers. We evaluate three segmentation networks for muscle boundary segmentation: (1) U-net, (2) FusionNet, and (3) a customized FusionNet. The customized FusionNet, which had the highest Dice coefficient on the test set, was used for subsequent morphological analysis of the muscle fibers. The proposed method was tested on microscopic images of the tibialis anterior muscles of a pre-clinical model of muscular dystrophy. The dataset contained four mosaic images, totalling more than 3400 fibers. Because of the severity of muscle injury in this pre-clinical model, its muscle fiber images present a challenge for quantitative analysis for several reasons. First, the muscle fibers had inhomogeneous spatial distribution and very different sizes. Second, the membranes of the muscle fibers had uneven signal intensity due to the loss of a membrane protein. Third, the shapes of intact muscle fibers were very different. All these factors contributed to the difficulty of acquiring good training data in the first place. Despite these difficulties, we achieved an average muscle fiber overlay precision of 0.65 and an average recall of 0.49. In this context, overlaid fibers are defined as fibers that have one or more pixels overlaying in the manual and DCNN cross-section segmentation. For the overlaid fibers, the proposed method achieved excellent segmentation accuracy of 94% ± 10.26%, as measured by the Dice-Sorensen coefficient.

A computational approach to detect and segment cytoplasm in muscle fiber images

We developed a computational approach to detect and segment cytoplasm in microscopic images of skeletal muscle fibers. The computational approach provides computer-aided analysis of cytoplasm objects in muscle fiber images to facilitate biomedical research. Cytoplasm in muscle fibers plays an important role in maintaining the functioning and health of muscular tissues. Therefore, cytoplasm is often used as a marker in broad applications of musculoskeletal research, including our search on treatment of muscular disorders such as Duchenne muscular dystrophy, a disease that has no available treatment. However, it is often challenging to analyze cytoplasm and quantify it given the large number of images typically generated in experiments and the large number of muscle fibers contained in each image. Manual analysis is not only time consuming but also prone to human errors. In this work we developed a computational approach to detect and segment the longitudinal sections of cytoplasm based on a modified graph cuts technique and iterative splitting method to extract cytoplasm objects from the background. First, cytoplasm objects are extracted from the background using the modified graph cuts technique which is designed to optimize an energy function. Second, an iterative splitting method is designed to separate the touching or adjacent cytoplasm objects from the results of graph cuts. We tested the computational approach on real data from in vitro experiments and found that it can achieve satisfactory performance in terms of precision and recall rates.