Hyperspectral Imaging in Brain Tumor Detection using Machine Learning

Hyperspectral imaging is a powerful tool in spectral analysis, used to obtain the spectrum for each pixel in an image by capturing a broad range of wavelengths in the electromagnetic spectrum. This research aims to utilize Machine Learning techniques in identification of brain tumors through hyperspectral imaging (HSI). Early detection of brain tumor is crucial because it enables the implementation of more precise and less invasive treatment strategies. To enable early detection in brain cancer, the integration of hyperspectral imaging (HSI) with Machine Learning methodologies becomes imperative. The Machine Learning models are trained to interpret complex spectral signatures, using which the images are classified as tumor or normal brain tissue. The spectral information provided by HSI offers enhanced identification of tumor, contributing to more effective surgical outcomes. Out of all experimented models, Random Forest Classifier stands out as the best-performing model with accuracy of 96.78, showcasing its effectiveness in brain tumor detection.