BRAIN TUMOR CLASSIFICATION USING FINE TUNED-TRANSFER LEARNING MODELS

Abstract

The fast-paced nature of contemporary living has led to a notable increase in tumors, posing a significant hurdle in the field of oncology. Achieving accurate tumor diagnoses, primarily done through imaging methods like MRI and CT scans, remains a complex undertaking. To address this challenge, substantial research efforts have been devoted to employing artificial intelligence, specifically deep learning. Different transfer learning models are finetuned and compared these models with state-of-the-art pre-trained models in pneumonia class detection. Our experimental results demonstrate the comparative performance of transfer learning models and their tuned models regarding accuracy, sensitivity, and specificity. This research contributes to the evolving landscape of medical image analysis, offering insights into the optimal utilization of pre-trained models and the potential benefits of fine-tuning strategies in the specific context of brain tumor classification with sparse data. This paper gives a more accurate tumor diagnosis with fine-tuned pre-trained models and a comparative study is done with the pre-trained models.