COMPARATIVE EVALUATION OF VGG19 AND RESNET50 ARCHITECTURE FOR LUNG NODULE DETECTION USING CT SCAN IMAGES

Lung nodule detection is a critical step in the early diagnosis and treatment of lung cancer, requiring reliable and efficient methods for analyzing CT scan images.This paper aims to present a comparative evaluation of two deep learning models: VGG19 and RESNET 50.VGG19 is a deep Convolutional Neural Network (CNN) architecture consists of 19 layers, including 16 convolutional layers and 3 fully connected layers .RESNET50 refers to a variant with 50 layers, where the network is made up of several residual blocks.Implemented in MATLAB, each model was trained and evaluated on a dataset of lung CT scans to assess their effectiveness in detecting and classifying lung nodules.VGG19, known for its deep convolutional layers, was compared with the residual learning-based ResNet50, which incorporates skip connections to mitigate the vanishing gradient problem.The results indicate that ResNet50 outperforms VGG19 in terms of classification accuracy, demonstrating the effectiveness of residual networks in complex medical image analysis.The findings suggest that deep learning models, particularly ResNet50, hold significant promise for improving lung nodule detection and early diagnosis in medical imaging, with MATLAB serving as a suitable environment for developing and testing these models.