• Uttam
• Sowmya
• Sarvesh Mohan Gaonkar
• Harsharaj S Shetty
• Rahul K

Brain tumor detection is a critical task in medical imaging, where timely and precise diagnosis can greatly enhance patient outcomes. This paper presents an AI-based framework for enhanced identification of brain cancers using multimodal MRI scans. The proposed system integrates advanced architectures for deep learning using traditional images processing techniques to take use of both data-driven and traditional segmentation approaches. Using T1, T1-Gd, T2, and FLAIR sequences, the framework applies pre-processing, optimized multi-level thresholding via Harmony Search Optimization, and morphological operations to extract tumor regions effectively. Furthermore, deep neural networks such as InceptionResNetV2 and DenseNet121 are evaluated for classification tasks, aided by transfer learning and data augmentation. Comparative analysis with standard convolutional networks demonstrates the superiority of the hybrid model in terms of accuracy, Dice coefficient, and execution efficiency. The results validate the potential of combining AI and hybrid segmentation techniques for reliable and scalable brain tumor detection.

Brain Tumor Detection, MRI, Deep Learning, Hybrid Segmentation, Transfer Learning

"ENHANCED BRAIN TUMOR DETECTION USING AI-BASED MULTIMODAL MRI ANALYSIS AND HYBRID SEGMENTATION TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.137-141, July-2025, Available :http://www.jetir.org/papers/JETIRGX06026.pdf

"ENHANCED BRAIN TUMOR DETECTION USING AI-BASED MULTIMODAL MRI ANALYSIS AND HYBRID SEGMENTATION TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp137-141, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06026.pdf