•  
  •  
 

Document Type

Original Study

Keywords

Computer Engineering

Abstract

In recent years, significant progress has been made in the field ofdiagnosis and classification of brain tumors, mainly attributed toadvancements in artificial intelligence and medical imaging. The mainobjective of this study is to improve the detection and classification of braintumors by applying and utilizing of artificial intelligence (AI) and recentadvancements in medical imaging techniques. Automation of the process oftumor identification and then classification, in addition to tumor grading, willdefinitely improve all procedures of brain tumor treatment and enhancepatient care. The proposed system combines conVolutional neural networks(CNNs), which act as extract features, and the You Only Look Once Algorithm(YOLOv7) for effective object identification and accurate classification. Themethodology described in this study inVolves employing a technique ofmultilayer classification, which integrates three distinct datasets. Thiscomprehensive approach shows an exceptional levels of accuracy andprecision. At the initial level, the model attains a 99.78% accuracy indistinguishing between tumor and nontumor cases. At the next level the systemaccurately sorts types of brain tumors (such, as glioma, meningioma andpituitary tumors) with an average accuracy of 99.35%. Moving on to the finalstage it successfully distinguishes between low grade and high grade gliomatumors with a precision of 93.07%. Moreover the model shows accuraciesranging from 99.41%, to 99.61% when classifying types of brain tumors andnontumor cases. The proposed system has the ability to determine theboundaries of the tumor, and thus this has helped in calculating the sizes oftumors with high accuracy.

Download

Share

COinS