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)
Stroke is a severe medical condition that requires prompt diagnosis and treatment to prevent disastrous consequences. In this piece of work, we present a unique approach to detect brain strokes using machine learning techniques. We employ a variety of machine learning techniques, including support vector machines (SVM), decision trees, and deep learning models, to efficiently identify and categorize stroke cases from medical imaging data. Machine learning techniques are applied for stroke identification after preprocessing processes are critical in improving the quality of the medical pictures and lowering noise. We examine many machine learning architectures and methods, such as random forests, k- nearest neighbours (KNNs), and convolutional neural networks (CNNs), and evaluate their efficacy in accurately detecting strokes from brain imaging data.
The models are trained and validated using an extensive dataset of labeled brain imaging scans, enabling thorough performance assessment. The identification accuracy of stroke cases is further enhanced by applying transfer learning from pre-trained models and data augmentation techniques. Furthermore, post-processing methods such as morphological operations and feature extraction are utilized to improve the overall detection performance by fine-tuning the identified stroke regions. Our findings reveal that machine learning algorithms perform promisingly when it comes to identifying brain strokes from medical imaging data, especially deep learning models like CNNs. The suggested method provides accurate and efficient stroke detection, which may help medical practitioners diagnose and treat stroke patients more quickly. As a result, our research concludes that machine learning algorithms are a useful diagnostic tool for brain strokes, offering medical professionals a useful resource in clinical situations.
Keywords:
Brain Tumor Segmentation (BTS), Magnetic Resonance Imaging (MRI), Deep Learning (DL), Convolutional Neural Networks (CNNs)
Cite Article:
"Brain Stroke Detection Using Machine Learning", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.9, Issue 4, page no.d355-d359, April-2024, Available :http://www.ijnrd.org/papers/IJNRD2404343.pdf
Downloads:
00053
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