Transformer-based spatial-temporal detection of apoptotic cell death in live-cell imaging.

Intravital microscopy has revolutionized live-cell imaging by allowing the study of spatial-temporal cell dynamics in living animals. However, the complexity of the data generated by this technology has limited the development of effective computational tools to identify and quantify cell processes. Amongst them, apoptosis is a crucial form of regulated cell death involved in tissue homeostasis and host defense. Live-cell imaging enabled the study of apoptosis at the cellular level, enhancing our understanding of its spatial-temporal regulation. However, at present, no computational method can deliver robust detection of apoptosis in microscopy timelapses. To overcome this limitation, we developed ADeS, a deep learning-based apoptosis detection system that employs the principle of activity recognition. We trained ADeS on extensive datasets containing more than 10,000 apoptotic instances collected both in vitro and in vivo, achieving a classification accuracy above 98% and outperforming state-of-the-art solutions. ADeS is the first method capable of detecting the location and duration of multiple apoptotic events in full microscopy timelapses, surpassing human performance in the same task. We demonstrated the effectiveness and robustness of ADeS across various imaging modalities, cell types, and staining techniques. Finally, we employed ADeS to quantify cell survival in vitro and tissue damage in mice, demonstrating its potential application in toxicity assays, treatment evaluation, and inflammatory dynamics. Our findings suggest that ADeS is a valuable tool for the accurate detection and quantification of apoptosis in live-cell imaging and, in particular, intravital microscopy data, providing insights into the complex spatial-temporal regulation of this process.

CANCOL, a Computer-Assisted Annotation Tool to Facilitate Colocalization and Tracking of Immune Cells in Intravital Microscopy.

Two-photon intravital microscopy (2P-IVM) has become a widely used technique to study cell-to-cell interactions in living organisms. Four-dimensional imaging data obtained via 2P-IVM are classically analyzed by performing automated cell tracking, a procedure that computes the trajectories followed by each cell. However, technical artifacts, such as brightness shifts, the presence of autofluorescent objects, and channel crosstalking, affect the specificity of imaging channels for the cells of interest, thus hampering cell detection. Recently, machine learning has been applied to overcome a variety of obstacles in biomedical imaging. However, existing methods are not tailored for the specific problems of intravital imaging of immune cells. Moreover, results are highly dependent on the quality of the annotations provided by the user. In this study, we developed CANCOL, a tool that facilitates the application of machine learning for automated tracking of immune cells in 2P-IVM. CANCOL guides the user during the annotation of specific objects that are problematic for cell tracking when not properly annotated. Then, it computes a virtual colocalization channel that is specific for the cells of interest. We validated the use of CANCOL on challenging 2P-IVM videos from murine organs, obtaining a significant improvement in the accuracy of automated tracking while reducing the time required for manual track curation.

A trainable clustering algorithm based on shortest paths from density peaks.

Clustering is a technique to analyze empirical data, with a major application for biomedical research. Essentially, clustering finds groups of related points in a dataset. However, results depend on both metrics for point-to-point similarity and rules for point-to-group association. Non-appropriate metrics and rules can lead to artifacts, especially in case of multiple groups with heterogeneous structure. In this work, we propose a clustering algorithm that evaluates the properties of paths between points (rather than point-to-point similarity) and solves a global optimization problem, finding solutions not obtainable by methods relying on local choices. Moreover, our algorithm is trainable. Hence, it can be adapted and adopted for specific datasets and applications by providing examples of valid and invalid paths to train a path classifier. We demonstrate its applicability to identify heterogeneous groups in challenging synthetic datasets, segment highly nonconvex immune cells in confocal microscopy images, and classify arrhythmic heartbeats in electrocardiographic signals.

Leukocyte Tracking Database, a collection of immune cell tracks from intravital 2-photon microscopy videos.

Recent advances in intravital video microscopy have allowed the visualization of leukocyte behavior in vivo, revealing unprecedented spatiotemporal dynamics of immune cell interaction. However, state-of-the-art software and methods for automatically measuring cell migration exhibit limitations in tracking the position of leukocytes over time. Challenges arise both from the complex migration patterns of these cells and from the experimental artifacts introduced during image acquisition. Additionally, the development of novel tracking tools is hampered by the lack of a sound ground truth for algorithm validation and benchmarking. Therefore, the objective of this work was to create a database, namely LTDB, with a significant number of manually tracked leukocytes. Broad experimental conditions, sites of imaging, types of immune cells and challenging case studies were included to foster the development of robust computer vision techniques for imaging-based immunological research. Lastly, LTDB represents a step towards the unravelling of biological mechanisms by video data mining in systems biology.

Cutaneous immune responses in the common carp detected using transcript analysis.

In order to detect new immune-related genes in common carp (Cyprinus carpio L.) challenged by an ectoparasitic infection, two cDNA libraries were constructed from carp skin sampled at 3 and 72h after infection with Ichthyophthirius multifiliis. In a total of 3500 expressed sequence tags (ESTs) we identified 82 orthologues of genes of immune relevance previously described in other organisms. Of these, 61 have never been described before in C. carpio, thus shedding light on some key components of the defence mechanisms of this species. Among the newly described genes, full-length molecules of prostaglandin D2 synthase (PGDS), the CC chemokine molecule SCYA103, and a second gene for the carp beta(2)-microglobulin (beta(2)m), beta(2)m-2, were described. Transcript amounts of the genes PGDS, interferon (IFN), SCYA103, complement factor 7 (C7), complement factor P (FP), complement factor D (FD) and beta(2)m-2 were evaluated by real-time quantitative PCR (RQ-PCR). Samples from skin, blood and liver from fish challenged with I. multifiliis were taken at 3, 12, 24, 36 and 48h post infection. Higher expression levels of most of these transcripts were observed in skin from uninfected fish, compared to the transcript levels detected in blood and liver from the same animals. Also, there was significant down-regulation of the genes PGDS and beta(2)m-2 in skin, whilst significant up-regulation was observed for the C7 and SCYA103 genes in liver of fish infected with the parasite. These results confirm the active role of fish skin in the immune response against infections, acting as an important site of expression of immune-related molecules.