Enhanced Brain Tumor Detection using Support Vector Classifier and Logistic Regression with Principal Component Analysis

The health of people is seriously threatened by brain tumours, which can have serious repercussions if misdiagnosed or mistreated. Improving results and patient survival rates depend heavily on early identification. In this work, we present a sophisticated method for detecting brain tumours using logistic regression techniques with Principal Component Analysis (PCA) and Support Vector Classifier (SVC). The Kaggle website provided the dataset for this study, which was preprocessed using a number of techniques, including image scaling. By identifying important traits, PCA was used for feature extraction, which allowed for the accurate diagnosis of brain tumours. The accuracy of two classification methods, SVC and logistic regression, in identifying brain tumours was assessed and contrasted. Our findings show that SVC performs better than logistic regression, with a 98.61% accuracy rate. Additionally, PCA analysis was conducted to reduce the dataset's dimensionality while preserving critical information. The study underscores the importance of employing SVC techniques for precise brain tumor diagnosis and classification, offering researchers and clinicians a reliable tool for formulating effective treatment plans and improving patient care outcomes.