Brain Tumor Detection Through CNN: Techniques, Dataset Insights, and Methodology

Year : 2025 | Volume :12 | Issue : 01 | Page : 1-11
    By

    Ganesh Pandurang Jadhav,

  • Swati Andhale,

  1. Student, Department of Computer Application, Parvatibai Genba Moze College of Engineering, Wagholi, Pune, Maharashtra, India
  2. Assistant Professor, Master of Computer Application, Parvatibai Genba Moze College of Engineering, Wagholi, Pune, Maharashtra, India

Abstract

document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_abs_154424’);});Edit Abstract & Keyword

Computer technologies are playing huge roles in some areas of the medical domain like surgery and therapy of different diseases. Researchers are doing studies and trying to experiment to detect different diseases like cancer, virus infections, and leprosy. There are many different medical imaging datasets that are publicly available for medical research purposes of diseases like cancer, virus infections, and leprosy, etc. where we can be able to access large databases free of cost. Brain tumor detection is an active and vast area of research in image processing. A brain tumor is one of the diseases which leads to a mortality rate of the human species. The brain is one of the crucial parts of the human body where maximum problems occur. The development of blood lumps or abnormal cells by birth in the brain or due to some accidental brain damage is very common nowadays. Blood lumps or abnormal cells are called tumors, and they can again be divided into many types. In this project, the methodology is proposed to detect brain tumors by segmentation, normalization, and feature extraction from magnetic resonance images, and neural networks are used for tumor classification and detection. First, the MR images are converted into jpeg or jpg image format and are given as input, then they are added to an array, and images get labeled and resized, and after that images are split into two batches train and test. Train and test image batches are then passed through feature extraction processes and are feeded to the convolutional neural network. After feeding the model is trained. Through this research project, we can build a classification model that would take brain MRI images of the patient and by computing those images the model predicts whether the brain is having a tumor or not.

Keywords: Computer technologies, surgery, brain tumor detection, brain tumor classification, neural networks, tumor detection

[This article belongs to Research & Reviews: A Journal of Bioinformatics (rrjobi)]

How to cite this article:
Ganesh Pandurang Jadhav, Swati Andhale. Brain Tumor Detection Through CNN: Techniques, Dataset Insights, and Methodology. Research & Reviews: A Journal of Bioinformatics. 2025; 12(01):1-11.
How to cite this URL:
Ganesh Pandurang Jadhav, Swati Andhale. Brain Tumor Detection Through CNN: Techniques, Dataset Insights, and Methodology. Research & Reviews: A Journal of Bioinformatics. 2025; 12(01):1-11. Available from: https://journals.stmjournals.com/rrjobi/article=2025/view=0

document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_ref_154424’);});Edit

References

  1. Hemanth G, Janardhan M, Sujihelen L. Design and implementing brain tumor detection using machine learning a 3rd International Conference on Trends in Electronics and Informatics (ICOEI). Tirunelveli, India. 2019, April 23–25. 1289–1294. IEEE.
  2. Akram MU, Usman A. Computer-aided system for brain tumor detection and s International Conference on Computer Networks and Information Technology (ICCNIT). Abbottabad, Pakistan. 2011, July 11–13. 299–302. IEEE.
  • Abdulbaqi HS, Jafri MZM, Abood LK, Omar AF. Detecting brain tumor in Magnetic Resonance Images using Hidden Markov Random Fields and Threshold t Student Conference on Research and Development. Penang, Malaysia
  1. . 2014, Dec 16– 1–5. IEEE.
  • Shaikh SA, Fattah A, Shahnaz C. An automatic scheme for brain tumor region detection from 3D MRI data based on enhanced intensity v TENCON 2017 – 2017 IEEE Region 10 Conference
  1. . Penang, Malaysia. 2017, Nov 5-8. 1–6. IEEE.
  2. Li Q, Gao Z, Wang Q. Glioma segmentation with a unified algorithm in multimodal MRI i IEEE Access. 2018;6:9543–9553.
  3. Lunga D, Yang HL, Reith A, Weaver J, Yuan J, Bhaduri B. Domain-adapted convolutional networks for satellite image classification: A large-scale interactive learning w IEEE J Sel Topics Appl Earth Obs Remote Sens. 2018;11(3):962–977.
  4. Menze BH, Jakab A, Bauer S, Kalpathy-Cramer J, Farahani K, Kirby J, et al. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging. 2015;34(10):1993–2024.
  5. Somasundaram S, Gobinath R. Current trends on deep learning models for brain tumor segmentation and detection – A r International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon). Faridabad, India. 2019, Feb 14–16. 217–221. IEEE.
  6. Keras. Keras Application [Online]. Available from: https://keras.io/applications/.
  7. Saha S. (2018, Dec 15). A comprehensive guide to convolutional neural networks the ELI5 Way [Online]. Towards Data Science. Available from: https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53.
  8. Marcelino P. (2018, Oct 23). Transfer learning from pre-trained models [Online]. Towards Data Science. Available from: https://towardsdatascience.com/transfer-learning-from-pre-trained-models-f2393f124751.
  9. Lowekamp BC, Chen DT, Ibáñez L, Blezek D. The design of SimpleITK. Front Neuroinform. 2013;7:45.
  10. (2019, Jan 23).ResNet (34, 50, 101): Residual CNNs for image classification tasks [Online]. Available from: https://neurohive.io/en/popular-networks/resnet/.
Regular Issue Subscription Review Article
Volume 12
Issue 01
Received 14/12/2024
Accepted 08/01/2025
Published 04/02/2025
105