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)
- Lung cancer is a life-threatening disease; early identification of lung cancer increases the chances of successful treatment for patients. Imaging techniques generally followed for lung cancer detection are X-ray, Computed tomography (CT), and histopathological images. However, CT scan images are more reliable in detecting lung cancer; this paper focused on lung cancer detection as a ternary classification problem using CT scan images. This paper proposes classifying lung images as 'normal,' 'benign,' and 'malignant,' which helps doctors treat patients effectively. This ternary classification is proposed through deep learning models. Deep Neural Network (DNN), Long Short Term Memory (LSTM), and Convolutional Neural Network (CNN) were used. Experimental results showed more promising results on the CNN algorithm than other models. Thus, the CNN algorithm is enhanced using hyper parameter tuning, and HT-CNN is proposed. To improve the novelty of work and get high detection accuracy for the ternary classification of lung cancer, hyper parameter tuning with Grid search cross-validation technique is proposed. The GSCV identifies the best-fit parameter for deep learning models and enhances the algorithm's performance. Experimental results showed that CT images were normal, benign, and malignant for ternary classes of the lung with deep learning models DNN, LSTM, CNN, and HT-CNN. The results are compared, showing that the hyper-tuned CNN model has achieved the highest accuracy, 99.4%.
"Lung Cancer Detection using Hyper Parameter Tuned Convolution Neural Network ", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 12, page no.d867-d873, December-2023, Available :http://www.ijnrd.org/papers/IJNRD2312397.pdf
Downloads:
000118759
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