Classification of Lung Cancer in Medical Imaging Using Convolutional Networks with CLAHE Preprocessing and Wavelet Transform

Convolutional neural networks (CNNs) play a crucial role in the early detection of diagnoses, assisting healthcare professionals in decision-making. This study uses different CNNs (AlexNet, ResNet-50, and EfficientNet) to classify computed tomography (CT) scan images for lung cancer detection, using the IQ-QTH/NCC and LIDC-IDRI datasets. The models were trained and evaluated with various magnifications and epochs, measuring the performance of each model based on metrics such as accuracy, precision, and recall. The results showed that ResNet-50 achieved an average accuracy of 96.12%. AlexNet reached 94.38%, and EfficientNet obtained 94.38%.