Oral Presentation

Volume Title: 2nd IEEE International Conference on Electronic Eng., Faculty of Electronic Eng., Menouf, Egypt, 3-4 July. 2021

¹Randa Aly ; ²waled Elshafai; ³Taha E. Taha; ⁴Fathi Abd El-SAmie

¹Communication and Electronic Engineering section, Munoyfia university

²Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University: Menouf, Egypt

³Faculty of Electronic Engineering

⁴Minufia- Egypt

this paper is concerned with the topic of medical image fusion. Bothe MRI and CT images are fused using convolutional neural network (CNN) approach. The CNN is composed of several layers that comprise convolutional layers, pooling layers and fully connected layer. The proposed approach comprises a hierarchy that contains focus detection, initial segmentation, consistency verification and fusion. The objective of utilization of the CNN is to generate a focus map from the two input images. The focus map is segmented into a binary map. Some image post processing is used to remove noise and undesired small objects. Simulation results of the fusion of MRI and CT images reveal images with high visual quality that are rich in details. This can help in the utilization of these images for further diagnosis application.

Image fusion; PCA; CNN; DWT; DT-CWT; Curvelet; Fuzzy; AWT