Year: 2025
Type: book-chapter
Abstract: Lung cancer ranks among the foremost causes of cancer-related mortality, and early identification is essential for enhancing survival rates.This research introduces a deep learning methodology employing a customised VGG16 convolutional neural network model for the autonomous classification of lung cancer.The model categorises CT scan pictures into three classes: normal, benign, and malignant.To improve the model transparency, we use Grad-CAM, an explainability technique that visualises the significant regions of an image impacting the model decision.Our experiments, performed on the IQ-OTH/NCCD dataset, indicate that the suggested method attains a classification accuracy of 96%, hence confirming its efficacy in lung cancer diagnosis.Employing Grad-CAM yields significant insights into the decision-making process, fostering trust and interpretability in AI-driven healthcare systems.
Authors: Souaad Hamza-Cherif, Taleb Tariq, Zineb Aziza Elaouaber, Messadi Mohammed
Institution: University of Abou Bekr Belkaïd
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4412937871