Dead cells map guide 20218/22/2023 These automatic methods were able to make accurate pixel predictions of the location and intensity of the different structures represented by the fluorescence. In order to label each cell, Hoechst and DAPI have been used to identify nuclear areas, CellMask to highlight plasma membranes and Propidium Iodide to spot cells with compromised membranes. For example, deep convolutional neural networks have been trained 9 with labeled images from different cell types like motor neurons, stem cells, and Jurkat cells 10. More recent efforts are based on automatic classification of images using deep learning techniques 3, 4, a form of automatic learning 5, 6 enabling improved data analysis for high-throughput microscopy 7, 8. Some efforts are focused on developing image processing programs able to identify cells and separate them from the extracellular matrix, performing segmentation and tracking cells using contrast fluorescence 2. The emergence of automatic microscopes made it possible to develop large datasets of live fluorescence images and single cell analysis, and more recently, these data started to be massively studied by means of computational tools. Understanding the intricacy of the molecular cross-talk within the cell death pathway highlights the need for developing methods to characterize the morphological cell response to therapy with anticancer drugs. As a disease, it involves biologically diverse subtypes with high intratumor heterogeneity that determine different pathological characteristics and have different clinical implications. ![]() ![]() More importantly, we analyzed the way our classifiers clusterize bright-field images in the learned high-dimensional embedding and linked these groups to salient visual characteristics in live-dead cell biology observed by trained experts.īreast cancer is the most frequently diagnosed malignancy in women worldwide one out of eight women are expected to develop breast cancer at some point in their lifetime 1. Our results highlight the potential of machine learning and computational image analysis to build new diagnosis tools that benefit the biomedical field by reducing cost, time, and stimulating work reproducibility. Furthermore, it reached AUC = 0.978 when classifying breast cancer cells under drug treatment. The best model reached an AUC = 0.941 for classifying breast cancer cells without treatment. Model performances were evaluated and compared on a large number of bright-field images. Next, several classifiers were trained based on well-known convolutional neural networks (CNN) backbones to perform supervised classification using labels obtained from fluorescence microscopy images associated with each bright-field image. First, a vast image set composed by JIMT-1 human breast cancer cells that had been exposed to a chemotherapeutic drug treatment (doxorubicin and paclitaxel) or vehicle control was compiled. We tackled this problem using the JIMT-1 breast cancer cell line that grows as an adherent monolayer. Our hypothesis is that live-dead classification can be performed without any staining and using only bright-field images as input. In this work we were interested in classifying breast cancer cells as live or dead, based on a set of automatically retrieved morphological characteristics using image processing techniques. For instance, there have been several studies oriented towards building machine learning systems capable of automatically classifying images of different cell types (i.e. In recent years, automated microscopy technologies are allowing the study of live cells over extended periods of time, simplifying the task of compiling large image databases. Breast cancer is the most common malignancy in women that usually involves phenotypically diverse populations of breast cancer cells and an heterogeneous stroma. Automated cell classification in cancer biology is a challenging topic in computer vision and machine learning research.
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |