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)
According to the World Health Organization (WHO), lung tumors are responsible for the highest number of deaths globally. To improve a patient's chance of survival, a practical computer-aided diagnosis (CAD) system has been developed in this study. Early detection of lung cancer through computed tomography (CT) has the potential to save numerous lives annually. Nevertheless, analyzing a vast number of these scans is a daunting task for radiologists who frequently experience observer fatigue, resulting in reduced performance. As a result, there is a need to efficiently read, detect, and evaluate CT scans. This paper proposes a method to detect lung cancer in a CT scan using various models such as Resnet50, Resnet101, GoogleNet, VGG16, and AlexNet. Among these models, AlexNet provided the most accurate results. The author cropped 3D cancer masks on the reference image using the center of the lung cancer provided in the dataset and trained a model with different techniques and hyperparameters. Finally, the author evaluated the result using dice coefficient and confusion matrix metrics, achieving a 94.4% accuracy, 94.5% precision, 94.4% recall, and a score of 94.4% using the AlexNet algorithm on a test set of positive and negative samples.
Keywords:
Deep Learning, Lung Cancer, AlexNet, Computed tomography.
Cite Article:
"Lung Tumor Classification and Detection using Deep CNN ", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 4, page no.e71-e77, April-2023, Available :http://www.ijnrd.org/papers/IJNRD2304412.pdf
Downloads:
000118752
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