Automated segmentation of brain cells for clonal analyses in fluorescence microscopy images

Quantitative analysis of prion disease using an AI-powered digital pathology framework

Prion disease is a fatal neurodegenerative disorder characterized by accumulation of an abnormal prion protein (PrPSc) in the central nervous system. To identify PrPSc aggregates for diagnostic purposes, pathologists use immunohistochemical staining of prion protein antibodies on tissue samples. With digital pathology, artificial intelligence can now analyze stained slides. In this study, we developed an automated pipeline for the identification of PrPSc aggregates in tissue samples from the cerebellar and occipital cortex. To the best of our knowledge, this is the first framework to evaluate PrPSc deposition in digital images. We used two strategies: a deep learning segmentation approach using a vision transformer, and a machine learning classification approach with traditional classifiers. Our method was developed and tested on 64 whole slide images from 41 patients definitively diagnosed with prion disease. The results of our study demonstrated that our proposed framework can accurately classify WSIs from a blind test set. Moreover, it can quantify PrPSc distribution and localization throughout the brain. This could potentially be extended to evaluate protein expression in other neurodegenerative diseases like Alzheimer's and Parkinson's. Overall, our pipeline highlights the potential of AI-assisted pathology to provide valuable insights, leading to improved diagnostic accuracy and efficiency.

Segmentation of Tissues and Proliferating Cells in Light-Sheet Microscopy Images of Mouse Embryos Using Convolutional Neural Networks

A variety of genetic mutations affect cell proliferation during organism development, leading to structural birth defects. However, the mechanisms by which these alterations influence the development of the face remain unclear. Cell proliferation and its relation to shape variation can be studied using Light-Sheet Microscopy (LSM) imaging across a range of developmental time points using mouse models. The aim of this work was to develop and evaluate accurate automatic methods based on convolutional neural networks (CNNs) for: (i) tissue segmentation (neural ectoderm and mesenchyme), (ii) cell segmentation in nuclear-stained images, and (iii) segmentation of proliferating cells in phospho-Histone H3 (pHH3)-stained LSM images of mouse embryos. For training and evaluation of the CNN models, 155 to 176 slices from 10 mouse embryo LSM images with corresponding manual segmentations were available depending on the segmentation task. Three U-net CNN models were trained optimizing their loss functions, among other hyper-parameters, depending on the segmentation task. The tissue segmentation achieved a macro-average F-score of 0.84, whereas the inter-observer value was 0.89. The cell segmentation achieved a Dice score of 0.57 and 0.56 for nuclear-stained and pHH3-stained images, respectively, whereas the corresponding inter-observer Dice scores were 0.39 and 0.45, respectively. The proposed pipeline using the U-net CNN architecture can accelerate LSM image analysis and together with the annotated datasets can serve as a reference for comparison of more advanced LSM image segmentation methods in future.

Multicolor strategies for investigating clonal expansion and tissue plasticity

Understanding the generation of complexity in living organisms requires the use of lineage tracing tools at a multicellular scale. In this review, we describe the different multicolor strategies focusing on mouse models expressing several fluorescent reporter proteins, generated by classical (MADM, Brainbow and its multiple derivatives) or acute (StarTrack, CLoNe, MAGIC Markers, iOn, viral vectors) transgenesis. After detailing the multi-reporter genetic strategies that serve as a basis for the establishment of these multicolor mouse models, we briefly mention other animal and cellular models (zebrafish, chicken, drosophila, iPSC) that also rely on these constructs. Then, we highlight practical applications of multicolor mouse models to better understand organogenesis at single progenitor scale (clonal analyses) in the brain and briefly in several other tissues (intestine, skin, vascular, hematopoietic and immune systems). In addition, we detail the critical contribution of multicolor fate mapping strategies in apprehending the fine cellular choreography underlying tissue morphogenesis in several models with a particular focus on brain cytoarchitecture in health and diseases. Finally, we present the latest technological advances in multichannel and in-depth imaging, and automated analyses that enable to better exploit the large amount of data generated from multicolored tissues.

Computational Methods for Single-Cell Imaging and Omics Data Integration

Integrating single cell omics and single cell imaging allows for a more effective characterisation of the underlying mechanisms that drive a phenotype at the tissue level, creating a comprehensive profile at the cellular level. Although the use of imaging data is well established in biomedical research, its primary application has been to observe phenotypes at the tissue or organ level, often using medical imaging techniques such as MRI, CT, and PET. These imaging technologies complement omics-based data in biomedical research because they are helpful for identifying associations between genotype and phenotype, along with functional changes occurring at the tissue level. Single cell imaging can act as an intermediary between these levels. Meanwhile new technologies continue to arrive that can be used to interrogate the genome of single cells and its related omics datasets. As these two areas, single cell imaging and single cell omics, each advance independently with the development of novel techniques, the opportunity to integrate these data types becomes more and more attractive. This review outlines some of the technologies and methods currently available for generating, processing, and analysing single-cell omics- and imaging data, and how they could be integrated to further our understanding of complex biological phenomena like ageing. We include an emphasis on machine learning algorithms because of their ability to identify complex patterns in large multidimensional data.

ACSA-2 and GLAST classify subpopulations of multipotent and glial-restricted cerebellar precursors

The formation of the cerebellum is highly coordinated to obtain its characteristic morphology and all cerebellar cell types. During mouse postnatal development, cerebellar progenitors with astroglial‐like characteristics generate mainly astrocytes and oligodendrocytes. However, a subset of astroglial‐like progenitors found in the prospective white matter (PWM) produces astroglia and interneurons. Characterizing these cerebellar astroglia‐like progenitors and distinguishing their developmental fates is still elusive. Here, we reveal that astrocyte cell surface antigen‐2 (ACSA‐2), lately identified as ATPase, Na+/K+ transporting, beta 2 polypeptide, is expressed by glial precursors throughout postnatal cerebellar development. In contrast to common astrocyte markers, ACSA‐2 appears on PWM cells but is absent on Bergmann glia (BG) precursors. In the adult cerebellum, ACSA‐2 is broadly expressed extending to velate astrocytes in the granular layer, white matter astrocytes, and to a lesser extent to BG. Cell transplantation and transcriptomic analysis revealed that marker staining discriminates two postnatal progenitor pools. One subset is defined by the co‐expression of ACSA‐2 and GLAST and the expression of markers typical of parenchymal astrocytes. These are PWM precursors that are exclusively gliogenic. They produce predominantly white matter and granular layer astrocytes. Another subset is constituted by GLAST positive/ACSA‐2 negative precursors that express neurogenic and BG‐like progenitor genes. This population displays multipotency and gives rise to interneurons besides all glial types, including BG. In conclusion, this work reports about ACSA‐2, a marker that in combination with GLAST enables for the discrimination and isolation of multipotent and glia‐committed progenitors, which generate different types of cerebellar astrocytes.

Myelin detection in fluorescence microscopy images using machine learning

BACKGROUND

The myelin sheath produced by glial cells insulates the axons, and supports the function of the nervous system. Myelin sheath degeneration causes neurodegenerative disorders, such as multiple sclerosis (MS). There are no therapies for MS that promote remyelination. Drug discovery frequently involves screening thousands of compounds. However, this is not feasible for remyelination drugs, since myelin quantification is a manual labor-intensive endeavor. Therefore, the development of assistive software for expedited myelin detection is instrumental for MS drug discovery by enabling high-content image-based drug screens.

NEW METHOD

In this study, we developed a machine learning based expedited myelin detection approach in fluorescence microscopy images. Multi-channel three-dimensional microscopy images of a mouse stem cell-based myelination assay were labeled by experts. A spectro-spatial feature extraction method was introduced to represent local dependencies of voxels both in spatial and spectral domains. Feature extraction yielded two data set of over forty-seven thousand annotated images in total.

RESULTS

Myelin detection performances of 23 different supervised machine learning techniques including a customized-convolutional neural network (CNN), were assessed using various train/test split ratios of the data sets. The highest accuracy values of 98.84±0.09% and 98.46±0.11% were achieved by Boosted Trees and customized-CNN, respectively.

COMPARISON WITH EXISTING METHODS

Our approach can detect myelin in a common experimental setup. Myelin extending in any orientation in 3 dimensions is segmented from 3 channel z-stack fluorescence images.

CONCLUSIONS

Our results suggest that the proposed expedited myelin detection approach is a feasible and robust method for remyelination drug screening.

ACDC: Automated Cell Detection and Counting for Time-Lapse Fluorescence Microscopy

Advances in microscopy imaging technologies have enabled the visualization of live-cell dynamic processes using time-lapse microscopy imaging. However, modern methods exhibit several limitations related to the training phases and to time constraints, hindering their application in the laboratory practice. In this work, we present a novel method, named Automated Cell Detection and Counting (ACDC), designed for activity detection of fluorescent labeled cell nuclei in time-lapse microscopy. ACDC overcomes the limitations of the literature methods, by first applying bilateral filtering on the original image to smooth the input cell images while preserving edge sharpness, and then by exploiting the watershed transform and morphological filtering. Moreover, ACDC represents a feasible solution for the laboratory practice, as it can leverage multi-core architectures in computer clusters to efficiently handle large-scale imaging datasets. Indeed, our Parent-Workers implementation of ACDC allows to obtain up to a 3.7× speed-up compared to the sequential counterpart. ACDC was tested on two distinct cell imaging datasets to assess its accuracy and effectiveness on images with different characteristics. We achieved an accurate cell-count and nuclei segmentation without relying on large-scale annotated datasets, a result confirmed by the average Dice Similarity Coefficients of 76.84 and 88.64 and the Pearson coefficients of 0.99 and 0.96, calculated against the manual cell counting, on the two tested datasets.