Drug investigation tool: Identifying the effect of drug on cell image by using improved correlation

Abstract

In the treatment of human cancer, the existing drug response identification and assessment methods have some issues, such as high cost, slow processing, and low accuracy. Responsive methods that easily and indirectly assess patient tissue response to drugs or small molecules offer promising options for improving drug safety, and they are able to identify the right treatment for specific patients. Digital image correlation is a good technique that detects a part of the image between two images. In this article, a new method of correlation called significant improvement of correlation (SIC) was proposed. Data were taken from the confocal microscopy of two‐photon excited fluorescence (TPEF) probe images taken every 5 min for short‐term monitoring (STM) and long‐term monitoring (LTM; 12, 24, and 48 hours). Cells were cultured, and a new compound TPEF was tested and injected the drug. The effect of drug on the TPEF compound was assessed through correlation. Experimental and simulation results showed that the proposed SIC was better than the conventional correlation method. Results also revealed that the first three images had 0.8% correlation in STM and LTM Image15 and Image10 had 0.49% correlation. The other images demonstrated minimum correlation. Thus, the effect of the newly made drug on the cell and image had a minimum correlation.

Segmentation of Drug-Treated Cell Image and Mitochondrial-Oxidative Stress Using Deep Convolutional Neural Network

“…Additionally, it also represented the specifics of each type of image. We evaluate our method on microscopy image, resolution of 0.2456 μ m per pixel, and image area is 512 × 512 μ m and size of image 2084 × 2084 pixels [ 55 – 57 ].…”