International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169 Volume: 11 Issue: 10s DOI: https://doi.org/10.17762/ijritcc.v11i10s.7703 Article Received: 12 June 2023 Revised: 30 July 2023 Accepted: 10 August 2023 ___________________________________________________________________________________________________________________ 637 IJRITCC | September 2023, Available @ http://www.ijritcc.org Automated Identification and Localization of Brain Tumor in MRI Using U-Net Segmentation and CNN-LSTM Classification Chandrakantha T S 1 , Basavaraj N Jagadale 2 , Abhisheka T E 3 , Omar Abdullah Murshed Farhan Alnaggar 4 1 Research Scholar Department of PG Studies and Research in Electronics Kuvempu University, Shimoga,India chandrabeluved@gmail.com 2 Associate Professor Department of PG Studies and Research in Electronics Kuvempu University, Shimoga,India basujagadale@gmail.com 3 Research Scholar Department of PG Studies and Research in Electronics Kuvempu University, Shimoga,India te.abhishek@gmail.com 4 Research Scholar Department of PG Studies and Research in Electronics Kuvempu University, Shimoga,India alnaggar1994@gmail.com Abstract— Nowadays, the use of computers to evaluate medical images automatically is critical part of the life. Today's treatment method relies heavily on early diagnosis and accurate disease identification, which were formerly difficult for medical research to achieve. Brain Magnetic Resonance Imaging (MRI) is essential to the detection and treatment of brain tumor (BT). Tumor of the brain are the result of brain cell division that has gone awry or is otherwise out of control. The manual MRI segmentation of BT is a difficult and time-consuming process. The most critical factor in the effective treatment and identification of BT is the ability to accurately locate the tumor. The detection of BT is regarded as a difficult task in medical image processing. For analysing and interpreting MRI, there are semi-automatic and fully automated systems that require large-scale professional input and evaluation, with varying degrees of effectiveness. Automated identification and extraction of the tumor's localization from brain MRI will be proposed in this paper. To achieve this goal, the data collected from Kaggle and the collected data are processed. Then the U-Net is employed to segment the tumor region from the MRI. Next, the MRI is classified using DL models like Convolutional Neural Network (CNN), and the hybrid Convolutional Neural Network and Long Short-Term Memory (CNN- LSTM). Both process segmentation and classification are evaluated using the metrics. From the evaluation, it is identified that CNN-LSTM outperforms the CNN model. Keywords- Brain, Tumor, Augmentation, Resize, Segmentation, Accuracy, Loss. I. INTRODUCTION The detection and classification of organ abnormalities, including leukemia, colon cancer, brain tumor, breast cancer, bowel cancer, skin cancer, and optic image analysis, are crucial aspects of medical imaging classification. Organ defects and tumor growth are closely linked and can lead to fatalities [1]. Brain tumors (BT) are particularly serious as they affect the central nervous system and can occur in both children and adults. BTs can be benign or malignant, with malignant tumors being highly dangerous and requiring accurate diagnosis for effective treatment [2]. Medical imaging, especially MRI, heavily relies on computer technology, and image segmentation plays a fundamental role in medical image analysis [3]. Various segmentation methods are used to accurately categorize tumors from MRI images, improving classification success rates [4]. Ensembling features and using Convolutional Neural Networks (CNN) are effective techniques for tumor segmentation and classification [5][6][7]. Other approaches combine clustering methods with CNN for efficient segmentation [8][9]. Transfer learning is also employed to enhance classification performance [10].