A versatile toolbox for semi-automatic cell-by-cell object-based colocalization analysis

Abstract Differential fluorescence labeling and multi-fluorescence imaging followed by colocalization analysis is commonly used to investigate cellular heterogeneity in situ. This is particularly important when investigating the biology of tissues with diverse cell types. Object-based colocalization analysis (OBCA) tools can employ automatic approaches, which are sensitive to errors in cell segmentation, or manual approaches, which can be impractical and tedious. Here, we present a novel set of tools for OBCA using a semi-automatic approach, consisting of two ImageJ plugins, a Microsoft Excel macro, and a MATLAB script. One ImageJ plugin enables customizable processing of multichannel 3D images for enhanced visualization of features relevant to OBCA, and another enables semi-automatic colocalization quantification. The Excel macro and the MATLAB script enable data organization and 3D visualization of object data across image series. The tools are well suited for experiments involving complex and large image data sets, and can be used in combination or as individual components, allowing flexible, efficient and accurate OBCA. Here we demonstrate their utility in immunohistochemical analyses of the developing central nervous system, which is characterized by complexity in the number and distribution of cell types, and by high cell packing densities, which can both create challenging situations for OBCA.

Download Full-text

Biological and Medical Importance of Cellular Heterogeneity Deciphered by Single-Cell RNA Sequencing

Cells ◽

10.3390/cells9081751 ◽

2020 ◽

Vol 9 (8) ◽

pp. 1751 ◽

Cited By ~ 1

Author(s):

Rishikesh Kumar Gupta ◽

Jacek Kuznicki

Keyword(s):

Single Cell ◽

Rna Sequencing ◽

Cell Types ◽

Cellular Heterogeneity ◽

Future Directions ◽

Strong Basis ◽

Bodily Fluids ◽

Single Cell Rna Sequencing

The present review discusses recent progress in single-cell RNA sequencing (scRNA-seq), which can describe cellular heterogeneity in various organs, bodily fluids, and pathologies (e.g., cancer and Alzheimer’s disease). We outline scRNA-seq techniques that are suitable for investigating cellular heterogeneity that is present in cell populations with very high resolution of the transcriptomic landscape. We summarize scRNA-seq findings and applications of this technology to identify cell types, activity, and other features that are important for the function of different bodily organs. We discuss future directions for scRNA-seq techniques that can link gene expression, protein expression, cellular function, and their roles in pathology. We speculate on how the field could develop beyond its present limitations (e.g., performing scRNA-seq in situ and in vivo). Finally, we discuss the integration of machine learning and artificial intelligence with cutting-edge scRNA-seq technology, which could provide a strong basis for designing precision medicine and targeted therapy in the future.

Download Full-text

Cell segmentation-free inference of cell types from in situ transcriptomics data

10.1101/800748 ◽

2019 ◽

Cited By ~ 5

Author(s):

Jeongbin Park ◽

Wonyl Choi ◽

Sebastian Tiesmeyer ◽

Brian Long ◽

Lars E. Borm ◽

...

Keyword(s):

Tissue Characterization ◽

Cell Types ◽

Cell Segmentation ◽

Cell Type ◽

Computational Framework ◽

Transcriptomics Data ◽

Novel Method ◽

2D And 3D ◽

Spatial Cell

AbstractMultiplexed fluorescence in situ hybridization techniques have enabled cell-type identification, linking transcriptional heterogeneity with spatial heterogeneity of cells. However, inaccurate cell segmentation reduces the efficacy of cell-type identification and tissue characterization. Here, we present a novel method called Spot-based Spatial cell-type Analysis by Multidimensional mRNA density estimation (SSAM), a robust cell segmentation-free computational framework for identifying cell-types and tissue domains in 2D and 3D. SSAM is applicable to a variety of in situ transcriptomics techniques and capable of integrating prior knowledge of cell types. We apply SSAM to three mouse brain tissue images: the somatosensory cortex imaged by osmFISH, the hypothalamic preoptic region by MERFISH, and the visual cortex by multiplexed smFISH. We found that SSAM detects regions occupied by known cell types that were previously missed and discovers new cell types.

Download Full-text

Cell segmentation and tracking using CNN-based distance predictions and a graph-based matching strategy

PLoS ONE ◽

10.1371/journal.pone.0243219 ◽

2020 ◽

Vol 15 (12) ◽

pp. e0243219

Author(s):

Tim Scherr ◽

Katharina Löffler ◽

Moritz Böhland ◽

Ralf Mikut

Keyword(s):

Cell Tracking ◽

Signal To Noise Ratio ◽

Cell Types ◽

Tracking Algorithm ◽

Training Data ◽

Cell Segmentation ◽

Data Sets ◽

Matching Strategy ◽

Microscopy Images ◽

Segmentation And Tracking

The accurate segmentation and tracking of cells in microscopy image sequences is an important task in biomedical research, e.g., for studying the development of tissues, organs or entire organisms. However, the segmentation of touching cells in images with a low signal-to-noise-ratio is still a challenging problem. In this paper, we present a method for the segmentation of touching cells in microscopy images. By using a novel representation of cell borders, inspired by distance maps, our method is capable to utilize not only touching cells but also close cells in the training process. Furthermore, this representation is notably robust to annotation errors and shows promising results for the segmentation of microscopy images containing in the training data underrepresented or not included cell types. For the prediction of the proposed neighbor distances, an adapted U-Net convolutional neural network (CNN) with two decoder paths is used. In addition, we adapt a graph-based cell tracking algorithm to evaluate our proposed method on the task of cell tracking. The adapted tracking algorithm includes a movement estimation in the cost function to re-link tracks with missing segmentation masks over a short sequence of frames. Our combined tracking by detection method has proven its potential in the IEEE ISBI 2020 Cell Tracking Challenge (http://celltrackingchallenge.net/) where we achieved as team KIT-Sch-GE multiple top three rankings including two top performances using a single segmentation model for the diverse data sets.

Download Full-text

Biological data annotation via a human-augmenting AI-based labeling system

npj Digital Medicine ◽

10.1038/s41746-021-00520-6 ◽

2021 ◽

Vol 4 (1) ◽

Author(s):

Douwe van der Wal ◽

Iny Jhun ◽

Israa Laklouk ◽

Jeff Nirschl ◽

Lara Richer ◽

...

Keyword(s):

Deep Learning ◽

Large Scale ◽

Microscopic Analysis ◽

Image Data ◽

Cell Types ◽

Biological Data ◽

Data Sets ◽

Data Set ◽

Data Annotation ◽

Labeling System

AbstractBiology has become a prime area for the deployment of deep learning and artificial intelligence (AI), enabled largely by the massive data sets that the field can generate. Key to most AI tasks is the availability of a sufficiently large, labeled data set with which to train AI models. In the context of microscopy, it is easy to generate image data sets containing millions of cells and structures. However, it is challenging to obtain large-scale high-quality annotations for AI models. Here, we present HALS (Human-Augmenting Labeling System), a human-in-the-loop data labeling AI, which begins uninitialized and learns annotations from a human, in real-time. Using a multi-part AI composed of three deep learning models, HALS learns from just a few examples and immediately decreases the workload of the annotator, while increasing the quality of their annotations. Using a highly repetitive use-case—annotating cell types—and running experiments with seven pathologists—experts at the microscopic analysis of biological specimens—we demonstrate a manual work reduction of 90.60%, and an average data-quality boost of 4.34%, measured across four use-cases and two tissue stain types.

Download Full-text

A multiresolution framework to characterize single-cell state landscapes

Nature Communications ◽

10.1038/s41467-020-18416-6 ◽

2020 ◽

Vol 11 (1) ◽

Cited By ~ 1

Author(s):

Shahin Mohammadi ◽

Jose Davila-Velderrain ◽

Manolis Kellis

Keyword(s):

Single Cell ◽

Single Cell Analysis ◽

Real Data ◽

Cell Types ◽

Cellular Heterogeneity ◽

Superior Performance ◽

Data Sets ◽

Structural Representation ◽

Archetypal Analysis ◽

Cell State

Abstract Dissecting the cellular heterogeneity embedded in single-cell transcriptomic data is challenging. Although many methods and approaches exist, identifying cell states and their underlying topology is still a major challenge. Here, we introduce the concept of multiresolution cell-state decomposition as a practical approach to simultaneously capture both fine- and coarse-grain patterns of variability. We implement this concept in ACTIONet, a comprehensive framework that combines archetypal analysis and manifold learning to provide a ready-to-use analytical approach for multiresolution single-cell state characterization. ACTIONet provides a robust, reproducible, and highly interpretable single-cell analysis platform that couples dominant pattern discovery with a corresponding structural representation of the cell state landscape. Using multiple synthetic and real data sets, we demonstrate ACTIONet’s superior performance relative to existing alternatives. We use ACTIONet to integrate and annotate cells across three human cortex data sets. Through integrative comparative analysis, we define a consensus vocabulary and a consistent set of gene signatures discriminating against the transcriptomic cell types and subtypes of the human prefrontal cortex.

Download Full-text

Cell segmentation-free inference of cell types from in situ transcriptomics data

Nature Communications ◽

10.1038/s41467-021-23807-4 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Jeongbin Park ◽

Wonyl Choi ◽

Sebastian Tiesmeyer ◽

Brian Long ◽

Lars E. Borm ◽

...

Keyword(s):

Tissue Characterization ◽

Cell Types ◽

Cell Segmentation ◽

Cell Type ◽

Preoptic Region ◽

Computational Framework ◽

Transcriptomics Data ◽

2D And 3D ◽

Spatial Cell

AbstractMultiplexed fluorescence in situ hybridization techniques have enabled cell-type identification, linking transcriptional heterogeneity with spatial heterogeneity of cells. However, inaccurate cell segmentation reduces the efficacy of cell-type identification and tissue characterization. Here, we present a method called Spot-based Spatial cell-type Analysis by Multidimensional mRNA density estimation (SSAM), a robust cell segmentation-free computational framework for identifying cell-types and tissue domains in 2D and 3D. SSAM is applicable to a variety of in situ transcriptomics techniques and capable of integrating prior knowledge of cell types. We apply SSAM to three mouse brain tissue images: the somatosensory cortex imaged by osmFISH, the hypothalamic preoptic region by MERFISH, and the visual cortex by multiplexed smFISH. Here, we show that SSAM detects regions occupied by known cell types that were previously missed and discovers new cell types.

Download Full-text

Medical image segmentation using modified active contour method

Serbian Journal of Electrical Engineering ◽

10.2298/sjee1703401v ◽

2017 ◽

Vol 14 (3) ◽

pp. 401-413 ◽

Cited By ~ 1

Author(s):

Viacheslav Voronin ◽

Oxana Balabaeva ◽

Svetlana Tokareva ◽

Evgenii Semenishchev ◽

Vladimir Dub

Keyword(s):

Active Contour ◽

3D Visualization ◽

Practical Importance ◽

Image Data ◽

Medical Image Segmentation ◽

Contour Method ◽

Data Sets ◽

Significant Information ◽

Active Contour Method ◽

Segmentation Approach

Image data is of major practical importance in medical informatics. Accurate segmentation of medical images largely determines the final result of image analysis, which provides significant information for 3D visualization, surgical planning and early detection of diseases. In this paper, a modified segmentation approach based on the active contour method is proposed to extract parts of bones from MRI data sets. The efficiency of the method is verified on real MRI slices. Good results are shown in comparison with existing approaches of segmentation of medical data.

Download Full-text

Cell population characterization and discovery using single-cell technologies in endocrine systems

Journal of Molecular Endocrinology ◽

10.1530/jme-19-0276 ◽

2020 ◽

Vol 65 (2) ◽

pp. R35-R51

Author(s):

Leonard Y M Cheung ◽

Karine Rizzoti

Keyword(s):

Single Cell ◽

Cell Types ◽

Reproductive Organs ◽

Cellular Heterogeneity ◽

Disease Mechanisms ◽

Cell Technologies ◽

Endocrine Organs ◽

Source Materials

In the last 15 years, single-cell technologies have become robust and indispensable tools to investigate cell heterogeneity. Beyond transcriptomic, genomic and epigenome analyses, technologies are constantly evolving, in particular toward multi-omics, where analyses of different source materials from a single cell are combined, and spatial transcriptomics, where resolution of cellular heterogeneity can be detected in situ. While some of these techniques are still being optimized, single-cell RNAseq has commonly been used because the examination of transcriptomes allows characterization of cell identity and, therefore, unravel previously uncharacterized diversity within cell populations. Most endocrine organs have now been investigated using this technique, and this has given new insights into organ embryonic development, characterization of rare cell types, and disease mechanisms. Here, we highlight recent studies, particularly on the hypothalamus and pituitary, and examine recent findings on the pancreas and reproductive organs where many single-cell experiments have been performed.

Download Full-text