Classification of Human Protein in Multiple Cells Microscopy Images Using CNN

作     者：Lina Al-joudi Muhammad Arif 

作者机构：Department of Computer Science AI(CS-AI)Umm Al Qura University(UQU)Makkah24231Saudi Arabia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2023年第76卷第8期

页      面：1763-1780页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：Umm Al-Qura University  UQU 

主　　题：CNN protein PReLU SeLU microscopy images subcellular localization multi-cells 

摘      要：The subcellular localization of human proteins is vital for understanding the structure of human *** play a significant role within human cells,as many different groups of proteins are located in a specific location to perform a particular *** these functions will help in discoveringmany diseases and developing their *** importance of imaging analysis techniques,specifically in proteomics research,is becoming more *** recent advances in deep learning techniques for analyzing microscopy images,classification models have faced critical challenges in achieving high *** protein subcellular images have a significant class *** use oversampling and under sampling techniques in this research to overcome this *** have used a Convolutional Neural Network(CNN)model called GapNet-PL for the multi-label classification task on the Human Protein Atlas Classification(HPA)*** have found that the ParametricRectified LinearUnit(PreLU)activation function is better than the Scaled Exponential LinearUnit(SeLU)activation function in the GapNet-PL model in most classification *** results showed that the GapNet-PL model with the PReLU activation function achieved an area under the ROC curve(AUC)equal to 0.896,an F1 score of 0.541,and a recall of 0.473.