A novel pilot study of automatic identification of EMF radiation effect on brain using computer vision and machine learning. (March 2020)

• Record Type: Journal Article
• Authors: Singh, Anushikha; Singh, Neha; Jindal, Tanu; Rosado-Muñoz, Alfredo; Dutta, Malay Kishore
• Is Part Of: Biomedical signal processing and control. Volume 57(2020)
• Publication Date: 2020-03
• Subjects: Drosophila melanogaster -- Brain morphology -- Mobile radiation -- Image processing -- Segmentation -- Machine learning; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2019.101821
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: This work presents automated identification of the effect of EMF radiations on brain. Changes in brain morphology due to EMF exposure were analyzed considering drosophila melanogaster as a specimen. The geometrical features were extracted from the microscopic segmented brain image of drosophila. Machine learning techniques were used for identification of EMF exposure on drosophila brain. Abstract: Electromagnetic field (EMF) radiations from mobile phones and cell tower affect brain of humans and other organisms in many ways. Exposure to EMF could lead to neurological changes causing morphological or chemical changes in the brain and other internal organs. Cellular level analysis to measure and identify the effect of mobile radiations is an expensive and long process as it requires preparing the cell suspension for the analysis. This paper presents a novel pilot study to identify changes in brain morphology under EMF exposure considering drosophila melanogaster as a specimen. The brain is automatically segmented, obtaining microscopic images from which discriminatory geometrical features are extracted to identify the effect of EMF exposure. The geometrical features of the microscopic segmented brain image of drosophila are analyzed and found to have discriminatory properties suitable for machine learning. The most prominent discriminatory features were fed to four different classifiers: support vector machine, naïve bayes, artificial neural network and random forest for classification of exposed / non-exposed microscopic image of drosophila brain. Experimental results indicate that all four classifiers provide good classification results up to 94.66 % using discriminatory features selected by feature selection method. The proposed method is a novel approach to identify the effect of EMF exposure automatically and with low time complexity thus providing an efficient image processing framework based on machine learning.