Article Preview
Top1. Introduction
The current World Health Organization (WHO) guidelines for brain tumor classification are strictly histopathological, which limits clinical application (Geethu Mohan et al.,2018). This has a constraint in the field of medical imaging for diagnosis and classification planning including automated approaches. Approaches have been abandoned in favor of non-invasive, high-resolution techniques, especially magnetic resonance imaging (MRI) and computed tomography (CT) scans (Thomas et al., 2018), though MRI is typically the reference standard used (Michael et al.,2018). Analyses of large-scale medical imaging data involving deep learning are rapidly evolving to include classification, detection, and diagnosis. Diffusion tensor imaging (DTI) is a non-invasive method that includes the use of MRI, allowing the study of white matter and therefore of the corticospinal tracts (Domenico Chirchiglia et a.,2020). Currently, considerable attention has been paid to magnetic particle imaging (MPI)because of its better sensitivity compared to MR. Imaging technologies have played a role in the analysis of brain anatomy and functions with the development of technology (LakshmanaprabuS.K.,2019). Early imaging brain tumor treatment approaches, such as pneumonia cephalography and cerebral angiography are invasive and potentially dangerous.
Recently, an important diagnostic technique in medical imaging is a non-invasive method uses by clinicians to diagnose and identify the development of brain tumors. Brain tumors can be examined using computed tomography (CT) or magnetic resonance imaging (MRI), the results are often confirmed with a biopsy an invasive procedure). Computer tomography (CT) is an imaging procedure that creates detailed images of scans of areas inside the body. It is often termed computerized tomography or computerized axial tomography (CAT). MRI is an imaging technology producing three-dimensional detailed anatomical images, it is used in both diagnosis and treatment monitoring. MRI is based on sophisticated technology that excites and detects the change in the direction of the rotational axis of protons found in the water that makes up living tissues. The theory of image segmentation and extraction in brain tumors plays a vital lot in the diagnosis of tumors and the application has created a big gap in the monitoring of tumor grades between computers and clinicians. Furthermore, radiologists improve diagnostic accuracy from a different perspective in interpreting medical images with these hybrid techniques (Mohan G et al,2018). The use of a convolutional neural network (CNN) technique in the analysis of automatic medical images has gained significant adhesion as an effective approach in medical diagnostics. The processing of medical images currently plays a central role in the diagnosis and monitoring of a broad range of medical conditions and has the benefit of identifying such conditions at an early stage to enable appropriate treatment (P.Mohamed Shakeel et al, 2019). Image classification, extraction, and segmentation are in all areas of medical examination to solve complicated problems in medical images in hospitals (Tuan, et al, 2017). The literature has a large body of published research addressing the classification of medical images including significant reported results relating to the classification of brain tumors. However, the classification methods have not achieved 100% accuracy in the areas of medical imaging classification.