Types of Optical Microscopic Analysis for Cell Death Using Artificial Intelligence

Cell death is a biological process that occurs when a cell stops carrying out all its functions. Cell death leads to macroscopic changes in the cell morphology. Coherent anti-Stokes Raman scattering (CARS), Stimulated Raman scattering (SRS) are used as a tool to observe structural and chemical changes at cellular resolution. There are many methods used to detect cell death generally takes time and materials. Spectroscopic and microscopic analyses are commonly used techniques for non-invasive analysis of samples, for cell death. Raman spectroscopy and microscopy techniques detects the inelastic scattering of light due to excitation or de-excitation of the samples. Spectroscopic technique has the advantage of being able to take rapid measurements in real time of in vivo, and in vitro samples, without any undesirable effects on the surrounding living cells and perform analysis regardless of the sample size. Despite the advantages that spectroscopy techniques offer, the complexity of the spectroscopic peaks is a major drawback. This gives rise to the need to develop automated algorithms for analysing high throughput spectroscopic and microscopic value with great efficiency and accuracy. Machine learning, which is a subset of artificial intelligence (AI) may be used to assess and draw conclusions from scientific investigations that give rise to large amounts of data in an automated manner, thereby reducing the scope for manual errors during analysis. Machine learning algorithms is categorized into supervised learning, unsupervised learning, as well as reinforcement learning algorithms. The development of new algorithms like deep learning (DL) has proven to be highly beneficial in classifying large and complex data. When used with fluorescence microscopy, DL has proven to show high specificity and can help in achieving inexpensive and rapid analysis.