RE-InCep-BT-:Resource-Efficient InCeptor Model for Brain Tumor Diagnostic Healthcare Applications in Computer Vision

Abstract

The rising incidence of brain tumors in the medical field necessitates the development of precise and effective diagnostic tools to assist the medical experts especially neurosurgeons as well as radiologists in early diagnosis and treatment recommendations. This study introduces a unique resource-efficient inceptor model utilizing computer-vision techniques for diagnosing presence of abnormal tissues inside brain MRI scans. The proposed model utilizes strengths of the inception architecture and incorporate resource-efficient design principles for optimizing its performance for healthcare applications. The model has been trained on a distinct dataset with different sizes where it is further processed, trained and validated on InCeptor model. Features are extracted by transfer learning process namely InceptionV3 for leveraging prior knowledge learnt from imagenet which is further integrated with support vector machines for performing binary classification to have accurate and efficient outcomes for giving timely recommendation and treatment to patients suffering from such disorder. The architecture of the proposed model has been designed in such a way that model should be computationally efficient for making it suitable in healthcare especially for brain tumor diagnostic purpose with limited resources. Experimental results demonstrates accuracy of 98.31%, precision of 99.09%, recall of 98.91%, specificity of 95% and F1- Score of 99% over state of art techniques.