INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Brain tumors are a serious health concern that can affect individuals of all ages, and their diagnosis and treatment require prompt and accurate identification. Brain tumors are often diagnosed using magnetic resonance imaging (MRI), which is an extensively utilized diagnostic technique, but interpreting these images can be challenging and time-consuming for medical professionals. Recent advancements in machine learning techniques, particularly deep learning, have demonstrated potential for increasing the precision and effectiveness of brain tumor diagnosis. In this study, we present a two-stage approach using a convolutional neural network and transfer learning with fine-tuning in ResNet50 for identifying and categorizing brain tumors. The initial stage of the proposed approach involves the identification of brain tumors in the provided scan, while the second stage involves categorizing the tumors into one of three types: pituitary tumor, glioma, or meningioma. To train our detection model, we employed a dataset comprising 4,600 grayscale images of brain tumors. Meanwhile, for the classification model, the dataset is obtained from Figshare(a reputable data-sharing platform) which includes T1-weighted contrast-enhanced scans obtained from a total of 233 patients, with a total of 3,064 scans diagnosed with glioma, meningioma, and pituitary tumor. Specifically, the dataset contains 1426 scans from patients with glioma, 708 scans from patients with meningioma, and 930 scans from patients with a pituitary tumor. This study's goal is to evaluate the efficiency of machine learning methods in enhancing the detection and classification of brain tumors. We believe that our findings have significant implications for the development of tools and technologies that can aid medical professionals in accurately diagnosing, decision-making, and treating brain tumors, potentially leading to improved patient outcomes.
Keywords:
brain tumor, magnetic resonance imaging, resnet50, convolutional neural network
Cite Article:
"A Robust Two-Stage Method for Accurate Brain Tumor Detection and Classification using Convolutional Neural Network and ResNet50", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 4, page no.f179-f186, April-2023, Available :http://www.ijnrd.org/papers/IJNRD2304596.pdf
Downloads:
000118755
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn