AN APPROACH FOR LUNG CANCER DETECTION AND CLASSIFICATION USING LENET-DENSENET

Abstract

Lung cancer is a malicious disorder that affects millions of people around the globe. Premature detection and classification of malignant cells can gradually improve the rate of survival of the patients. The study proposed an innovative strategy for lung cancer identification and classification by utilizing the hybrid deep learning (DL) technique. The presented strategy contains two major parts, segmentation and classification. Attention gated (AG) network is used for segmenting the affected regions. AGs guide a method’s attention to significant regions while repressing the activation of features in non-related fields. This augments the model’s representative influence without significantly increasing computing cost or the number of model parameters. For the lung cancer classification, by combining the architectures of LeNet and Dense Convolutional Network (DenseNet), the proposed LeNet–DenseNet was developed. LeNet and DenseNet are two popular CNN architectures known for the classification of images. LeNet comprises alternating and convolutional layers, followed by fully connected layers. As per the idea of densely connected layers, each layer in DenseNet, which is a recent CNN architecture, is associated with other layers in a feed-forward fashion. This allows for better feature reuse and gradient flow and lessens the parameter count. The findings stated that the proposed method outperforms when compared to other traditional strategies corresponding to specificity, sensitivity and accuracy. The presented approach assists in early-stage detection of high-accuracy lung cancer, which is considered crucial for the treatment procedures in time. The findings stipulated that the presented LeNet–DenseNet model procured accuracy of 94.8%, sensitivity of 96.8% and specificity of 93.5%.