Deep Learning with DCMU_NET Networks for Brain Tumor Segmentation Based on MRI Images

Abstract

Abnormal development of cells in human body leads to the formation of cancer or tumor. The uncontrolled augmentation of cells in human brain leads to the configuration of tumors in brain. These brain tumors are classified into benign and malignant. Similarly, the cells in tumor region are categorized into active or inactive cells. Hence, surgery is required for removing these tumors in brain image. This Research work presents a tumor are formed in brain due to the uncontrolled development of cells. These tumors can be cured if it is timely detected and by proper medication. This wok proposes a computer aided automatic detection and diagnosis of Meningioma brain tumors in brain images using Deep Learning Cross Modality U_NET (DCMU_NET) algorithm segmentation. The proposed system consists of pre-processing and segmentation and diagnosis sections.  Based on the location of these abnormal regions in brain tissues, the segmented tumor regions are diagnosed.