Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (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 one of the leading causes of death worldwide, and early detection can make a huge difference in saving lives. In this project, we built a deep learning model that can automatically detect and classify different types of lung cancer from chest X-ray images. We used a pre-trained ResNet50 model and improved it with transfer learning so that it could better understand our specific dataset. Before feeding the images into the model, we enhanced them using a method called CLAHE to improve contrast and applied data augmentation techniques like rotation, brightness adjustment, and flipping to make the model more robust.
We trained the model using the Adam optimizer along with a cosine learning rate schedule, and we added early stopping to prevent overfitting. The dataset was carefully split into training, validation, and test sets to ensure fair evaluation. Our model performed very well, achieving high accuracy and showing strong ability to differentiate between lung cancer types. We also visualized the results using confusion matrices and ROC curves for better understanding.
To make it user-friendly, we built an interface where anyone can upload an X-ray image and get instant predictions with confidence scores. Overall, this project shows how deep learning can play a powerful role in supporting doctors with fast, reliable lung cancer detection.
Keywords:
Lung Cancer Detection , Chest X-ray Classification, Deep Learning ResNet50 , Transfer Learning , Image Preprocessing , CLAHE (Contrast Limited Adaptive Histogram Equalization) , Data Augmentation , Medical Imaging.
Cite Article:
" Lung Disease Detection using ResNet50 and Image Classification", International Journal of Science & Engineering Development Research (www.ijrti.org), ISSN:2455-2631, Vol.10, Issue 4, page no.a706-a710, April-2025, Available :http://www.ijrti.org/papers/IJRTI2504088.pdf
Downloads:
000302
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator