International Journal of Advanced Research in Computer and Communication Engineering

Abstract: Lung cancer remains the leading cause of fatalities in all patients with cancer worldwide, thus reflecting highly on the urgent requirement for early detection and diagnostics. This abstract describes a summary of the different databases and methods using an artificial neural network (ANN) algorithm for lung cancer diagnosis. For the deep learning models, we need annotated CT scan images. They are accessible in publicly available datasets such as the Lung Image Database Consortium (LIDC), Lung-PET-CT-Dx, and NSCLC-Radio genomics.

These datasets have contributed to the automation of lung cancer diagnosis. Tumor detection and classification are also performed based on X-rays and PET scan imaging data. Several ANN-based methods have been reported for optimal detection of lung cancer. The employed methods included: hybrid learning schemes, data augmentation, feedback in neural network training, multilayer perceptron’s and radiomic feature extraction. These methods aim to enhance the diagnostic accuracy by reducing the false positive rate and help physicians spot malignant nodules early on.

Downloads: | DOI: 10.17148/IJARCCE.2025.1411154