A new approach to early Diagnosis of Lung Cancer Employing Neural Networks Utilising Hybrid Deep Learning
Journal of Advances in Science and Technology · 2025
DOI: 10.29070/0ntgfm39 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Advances in Science and Technology, 2025. Verfasst von Ramveer Gurjar und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Lung cancer is the leading cause of cancer-related deaths worldwide, primarily due to its late-stage diagnosis and aggressive progression. This research presents a new approach to improving the accuracy & timeliness of lung cancer diagnoses: Cancer Cell Detection utilising Hybrid Neural Network (CCDC-HNN). Applying a hybrid deep learning framework, the suggested model processes CT scan data using the LIDC-IDRI, which stands for Lung Image Database Consortium & Image Database Resource Initiative. In order to improve patient survival rates, feature extraction is done utilising deep neural networks with an emphasis on early-stage detection. To increase diagnostic accuracy, the system incorporates a 3D Convolutional Neural Network (3D-CNN). This method successfully distinguishes between benign & malignant tumours, and its efficacy is confirmed by utilising established statistical measures. The suggested hybrid deep learning method for early diagnosis of lung cancer has been shown to be both effective & reliable according to experimental data.
Zitieren
APA
Gurjar, R., & Bhatiya, R. (2025). A new approach to early Diagnosis of Lung Cancer Employing Neural Networks Utilising Hybrid Deep Learning. Journal of Advances in Science and Technology. https://doi.org/10.29070/0ntgfm39
Vancouver
Gurjar R, Bhatiya R. A new approach to early Diagnosis of Lung Cancer Employing Neural Networks Utilising Hybrid Deep Learning. Journal of Advances in Science and Technology. 2025. doi:10.29070/0ntgfm39
BibTeX
@article{Gurjar2025,
author = {Gurjar, Ramveer and Bhatiya, Rakesh},
title = {A new approach to early Diagnosis of Lung Cancer Employing Neural Networks Utilising Hybrid Deep Learning},
journal = {Journal of Advances in Science and Technology},
year = {2025},
doi = {10.29070/0ntgfm39}
}
EUVIMED