International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Deep Learning-Based Brain Tumor Detection and Classification |
|---|---|
| ABSTRACT | Brain Tumor represents one of the severe and life threatening oncological conditions globally. Earlier and perfect detection and diagnosis is significant patient outcomes. This present the detection of the brain tumor and diagnosis. Manual clinical Evaluation of complex 3 dimensional magnetic resonance image scans highly subjective and prone to human error creating an urgent humanitarian need for rapid automated secondary diagnostic tools. This paper proposes an advanced computer aided diagnosis framework using deep learning to automate brain tumour detection and segmentation directly aiming to mitigate human casualties and reduce the diagnostic burden on healthcare professionals. The methodology incorporates robust data preprocessing via histogram equalization and data augmentation to handle limited image data full implement transfer learning using optimised convolutional neural network architectures especially Res net 50 and VGG 16 for multiclass tumour categorization alongside a modified u-net model for pixel level structure segmentation evaluated on comprehensive open source benchmark site dataset or our unified framework achieves peak classification accuracy of 98.9% and a high dyes similarity coefficient. By delivering high localised and rapid tumour boundaries evaluation this system minimises clinical falls and detection rates significantly ultimately this research bridges the gap between artificial intelligence and empathetic healthcare offering a reliable high-speed solution for accelerate clinical decision making improve long term patient outcomes and preserve human life The findings indicate that deep learning-based approaches can serve as valuable computer-aided diagnostic tools for supporting radiologists and healthcare professionals in clinical decision-making. The proposed system contributes to the advancement of intelligent healthcare technologies by providing an efficient, accurate, and scalable solution for brain tumor detection and classification. Future enhancements may include the integration of advanced transfer learning architectures, larger multi-institutional datasets, and explainable artificial intelligence techniques to further improve diagnostic performance and clinical applicability. |
| AUTHOR | ANJUM AFSANA T. A, DR.CHARAN K.V M.Tech Student, Dept. of CSE, Shridevi Institute of Technology, Tumakuru, Karnataka, India Associate Professor, Dept. of ISE, Shridevi Institute of Technology, Tumakuru, Karnataka, India |
| VOLUME | 185 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1406018 |
| pdf/18_Deep Learning-Based Brain Tumor Detection and Classification.pdf | |
| KEYWORDS | |
| References | 1. 12th International Conference on Computational Intelligence and Data Science (ICCIDS 2017) Investigating Brain Tumor Segmentation and Detectio Techniques Mansi Lathera,*, Dr. Parvinder Singh. 2. Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI. Kai Roman Laukamp1 & Frank Thiele1,2 & Georgy Shakirin1,2 & David Zopfs1 & Andrea Faymonville3 & Marco Timmer3 & David Maintz1 & Michael Perkuhn1,2 & Jan Borggrefe 1.2018. 3. Brain tumor detection using fusion of hand crafted and deep learning features Tanzila Saba a , Ahmed Sameh Mohamed a , Mohammad El-Affendi a , Javeria Amin b,c , Muhammad Sharif c,f .2019. 4. Brain Tumor Detection and Segmentation in MR Images Using Deep Learning Sidra Sajid1· Saddam Hussain2 · Amna Sarwar1.2020. 5. Brain tumor detection and classification using machine learning: a comprehensive survey. Javaria Amin1,2 · Muhammad Sharif2 · Anandakumar Haldorai3 · Mussarat Yasmin2 · Ramesh Sundar Nayak2.2021. 6. Received December 7, 2021, accepted December 26, 2021, date of publication January 4, 2022, date of current version January 10, 2022” A New Convolutional Neural Network Architecture for Automatic Detection of Brain Tumors in Magnetic Resonance Imaging Images. 7. “Received 17 May 2023, accepted 9 June 2023, date of publication 20 June 2023, date of current version 3 July 2023.” Automated Segmentation of Brain Tumor MRI Images Using Deep Learning. 8. Fink JR, Muzi M, Peck M, Krohn KA (2015) Multimodality brain tumor imaging: MR imaging, PET, and PET/MR imaging. J Nucl Med 56:1554–1561. |
