A Systematic Approach in Detecting Brain Tumor using CCNN Algorithm

A brain tumor (BT) is characterized by the presence of abnormal cell growth, whether these cells are malignant or not. In BT conditions, the number of these cells increases and multiplies rapidly, causing uncontrolled growth. Detecting brain tumors at an early stage is crucial for timely prognosis and diagnosis. Recent advancements in artificial intelligence (AI) and machine learning (ML) have made it possible to forecast the growth of brain tumors more quickly. Deep learning and ML algorithms play a vital role in achieving higher accuracy, which greatly benefits patient treatment. This study aimed to develop a framework for a Competence Convolutional Neural Network (CCNN) model and establish parameters for training the model and predicting its accuracy, referred to as predictive diagnosis (PD). The research utilized a dataset of 150 brain tumor diagnoses, based on MRI images, to assess the proposed methodology using a ML-based CNN. The algorithm demonstrated an exceptional accuracy rate of 93% in the training phase, 87.34% in validation, and 89.5% during testing. These results surpass the accuracy of traditional methods for brain cancer detection in comparative studies.