| Autor: |
Narad, Supriya, Reddy, K. T. V. |
| Zdroj: |
AIP Conference Proceedings; 2024, Vol. 3188 Issue 1, p1-7, 7p |
| Abstrakt: |
Accurate detection and treatment of Non-Small Cell Lung Cancer (NSCLC) can save life of a cancerous patient suffering through any stage of cancer. Survival possibilities can be improved if cancer is detected at early stage. Many mechanisms are available in Artificial Intelligence and Machine Learning which helps to predict the cancer accurately and provides best diagnosis. It necessitates early and accurate detection for effective treatment. This research presents a novel deep learning framework for NSCLC detection using image fusion techniques. By combining multiple medical imaging modalities, such as CT scans and PET scans, our approach enhances the diagnostic accuracy and reliability. Convolutional Neural Networks (CNNs) are employed for feature extraction and feature classification, enabling the automated detection of cancerous lesions. Preliminary results indicate promising results in terms of sensitivity and specificity, offering a potential breakthrough in early NSCLC diagnosis, which can significantly improve the patient outcomes and reduces the cost for healthcare management. This study addresses the requirement for an effective deep learning feature selection and representation model for NSCLC prediction. Distinguishing characteristics are extracted by Deep learning method from the input data, allowing for a more accurate and thorough representation of NSCLC characteristics. Feature selection method implemented in this paper got accuracy of 84 %. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
