![]() Available automated systems for detecting cellular events such as cell division and cell death mostly rely on the use of fluorescently labeled cells 12, 13 limiting the flexibility of applications due to phototoxicity effects, cell lines availability, and fluorescent probe stability. The application of such analyses to extended datasets, such as those obtained in high-throughput experiments, requires automated approaches based on machine learning/artificial intelligence with the aim of defining complex phenotypic profiles 10, 11. In addition, abnormal mitotic progression detected by time-lapse microscopy may help identify mitotic regulators and/or pathways impinging on mitosis, which can widen our understanding of the genetic regulation of cell proliferation and death and can represent novel targets for anti-cancer drugs. Indeed, monitoring by time-lapse microscopy the single-cell response to anti-mitotic drugs in terms of cell division and cell death has allowed revealing the heterogeneity of induced events within a cell population, thus providing key information for the characterization of novel compounds of therapeutic interest 9. Among anti-cancer compounds, an important class is represented by anti-mitotic drugs, which arrest cell division (mitosis) and induce cell death 8. The drug discovery and cancer research fields have largely benefited from these innovative approaches 6, 7. The analysis of image sequences enables the quantification of relevant parameters, such as the number of cells and their geometric features (e.g., perimeter, area, nuclear position and shape roundness), as well as the assessment of their movement and fate, gaining unique spatio-temporal information on dynamic biological processes 5. In cell biology studies, time-lapse microscopy advanced methodologies are used to observe the dynamic behavior of single cells over time 4. Many algorithms have been developed to tackle events arising in different video domains, such as abnormality detection for surveillance 1, human action detection 2, and cell population monitoring 3 in several biological and biomedical studies. The dataset is useful for testing and comparing methods for identifying interphase and mitotic events and reconstructing their lineage, and for discriminating different cellular phenotypes.Īdvances in computer in vision, imaging technologies, and computational tools have led to significant results in video event detection and recognition. It contains various annotations (pixel-wise segmentation masks, object-wise bounding boxes, tracking information). It consists of 29 time-lapse image sequences from HeLa, U2OS, and hTERT RPE-1 cells under different experimental conditions, acquired by differential interference contrast microscopy, for a total of 237.9 hours. ![]() ![]() ![]() In this study, we present ALFI, a dataset of images and annotations for label-free microscopy, made publicly available to the scientific community, that notably extends the current panorama of expertly labeled data for detection and tracking of cultured living nontransformed and cancer human cells. ![]() Differently from fluorescence microscopy, label-free techniques can be easily applied to almost all cell lines, reducing sample preparation complexity and phototoxicity. For living cells, the task becomes even more arduous as cells change their morphology over time, can partially overlap, and mitosis leads to new cells. Detecting and tracking multiple moving objects in a video is a challenging task. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |