Spatial-temporal detection of apoptotic cell death in live-cell imaging

Apoptotic cell death is a crucial mechanism that contributes to tissue homeostasis and prevents the onset of several diseases. However, this phenomenon is challenging to identify within microscopy movies that can encompass thousands of cells. Led by Santiago Gonzalez, the recent study carried at the Institute for Research in Biomedicine (IRB) in Bellinzona, affiliated with USI, introduces ADeS, an innovative approach based on artificial intelligence for the automatic detection of apoptotic cells in microscopy movies. ADeS not only ensures an accurate quantification of this dynamic process, but also reduces processing time, delivering results comparable to those of imaging experts. Developed by Dr. Alain Pulfer and Dr. Diego Pizzagalli, ADeS was recentlly published in the eLife Journal, creating new avenues in cell death research.

Intravital microscopy has revolutionised 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 time-lapses. ADeS was developed to overcome this limitation, a deep learning-based apoptosis detection system that employs the principle of activity recognition. ADeS has been trained 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 time-lapses, surpassing human performance in the same task. The effectiveness and robustness of ADeS has been demonstrated across various imaging modalities, cell types, and staining techniques. Finally, ADeS has been employed to quantify cell survival in vitro and tissue damage in vivo, demonstrating its potential application in toxicity assays, treatment evaluation, and inflammatory dynamics. 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.