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)
A vital field of study is multiple illness detection, which attempts to enhance healthcare outcomes by simultaneously recognizing many diseases in individuals. A single illness is identified at a time in the conventional method of disease identification, which is time-consuming, expensive, and usually leads to missed diagnoses. Because of developments in machine learning and artificial intelligence, many illness detection models have been created that can aid in the accurate and speedy diagnosis of multiple diseases. These models use information from a variety of sources, including medical records, lab test results, and imaging data, to discover trends and forecast the risk of certain illnesses.
Pneumonia, COVID19, and tuberculosis are just a few of the diseases and disorders that are analyzed, classified, and
predicted using the many models that are put forward in this study and research. The public dataset utilized for illness
categorization and prediction comprises 7135 chest X-ray images that have been divided into four categories: normal,
COVID19, pneumonia, and tuberculosis. Since the dataset being utilized is imbalanced, we gave Class weights to it in order to reduce overfitting while training deep learning models. Several Machine Learning and Deep Transfer
Learning Models, including Convolutional Neural Network, Inception-V3, EfficientNetB0, Resnet, and VGG-16, have
been deployed for the prediction and classification of multiple diseases. The accuracy of the CNN deep learning model is 82%, the accuracy of Inception-V3 is 86%, EfficientNetB0 is 91%, and Resnet15V2 is 92%. On top of that, the VGG-16 deep learning model outperformed competing models to reach accuracy of 95.3%, with precision, recall, and F1-Score at 96%, 97%, and 98%, respectively.
Keywords:
Cite Article:
"DETECTION OF MULTIPLE DISEASES FROM CHEST X-RAY IMAGES USING VARIOUS DEEP LEARNING APPROACHES", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 11, page no.b517-b526, November-2023, Available :http://www.ijnrd.org/papers/IJNRD2311166.pdf
Downloads:
000118765
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