A mass correlation based deep learning approach using deep Convolutional neural network to classify the brain tumor. (March 2023)

• Record Type: Journal Article
• Authors: Satyanarayana, Gandi; Appala Naidu, P.; Subbaiah Desanamukula, Venkata; Satish kumar, Kadupukotla; Chinna Rao, B.
• Is Part Of: Biomedical signal processing and control. Volume 81(2023)
• Publication Date: 2023-03
• Subjects: Deep Learning -- CNN -- Brain Tumor Classification -- Image Processing -- AMEA -- MCA -- DCNN_AMEA; 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.2022.104395
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: The 3D MRI images are mainly considered for detecting the brain tumor. The input dataset are initially taken to pre-processing where Average Mass Elimination Algorithm (AMEA) is applied. AMEA is to remove the noisy pixel form the images. The obtained weight helps to improve the performance of the CNN model to fetch most effective results. Abstract: The 3D MRI images are mainly considered for detecting the brain tumor. The deep learning approaches are highly effective for detecting the disease in its early stage. However, the detection and classification is achieved though the highly enhanced deep learning approaches that provides various classes. However, the considerable limitation in this field is detecting the significant features. In order to handle these issues, A highly enhanced deep learning approach is considered that is based on Convolutional Neural Network (CNN) with mass correlation analysis. Here, the input dataset is initially taken to pre-processing where Average Mass Elimination Algorithm (AMEA) is applied. AMEA is to remove the noisy pixel form the images. The significant features are fetched using Median values of white mass. Then the extracted features are trained using the CNN model based on Mass Correlation Analysis (MCA) that helps to assign the weight measure. The obtained weight helps to improve the performance of the CNN model to fetch most effective results.