Treffer: LASCA-Based Monitoring of Drug Impact and Classification using Machine Learning for Biospeckle Images of Melanoma Cells

Monitoring a drug's impact on any biological cell is essential for bioengineering and the pharmaceutical field. Preclinical models are available for drug monitoring and testing but are manual and time-consuming. The biospeckle laser technique (BSL) is one optical and nondestructive method that may be useful for measuring cell dynamics. With a deeper comprehension of drug actions and their influence on cellular processes, the BSL approach offers insights into the activity of cell-drug interaction. The technique provides the pattern that the laser beams produce on the screen to look into the activity therein. To Interpret the information using these biospeckle patterns, time and frequency domain algorithms were used in the past. We proposed machine learning and laser speckle contrast analysis LASCA-based analysis of melanoma cells using biospeckle signal/image. Using a machine learning model for computation adds useful inputs to automate the process. In this work, LSACA is used to track the effects of drugs on melanoma cell images. Additional machine learning algorithms are employed to categorize cells in two categories, with and without drug-induced melanoma cells. Various machine learning models are implemented and evaluated using Python language.