Optimizing Lung Cancer Detection in CT Imaging: A Wavelet Multi-Layer Perceptron (WMLP) Approach Enhanced by Dragonfly Algorithm (DA)

TL;DR

The study tackles automated lung cancer classification from CT images by fusing wavelet-based feature extraction with a Multi-Layer Perceptron (MLP), whose hyperparameters are optimized using the Dragonfly Algorithm (DA). By applying Canny edge detection and Haar wavelet transforms, discriminative features are derived and fed into an MLP whose parameters are fine-tuned via DA, achieving high diagnostic performance. The approach demonstrates superior metrics compared with baselines, reporting near-perfect accuracy and AUC in the evaluated setup, and discusses data augmentation and processing strategies that bolster robustness. This work signals a promising route toward reliable, automated computer-aided diagnosis to aid radiologists in early and accurate lung cancer detection.

Abstract

Lung cancer stands as the preeminent cause of cancer-related mortality globally. Prompt and precise diagnosis, coupled with effective treatment, is imperative to reduce the fatality rates associated with this formidable disease. This study introduces a cutting-edge deep learning framework for the classification of lung cancer from CT scan imagery. The research encompasses a suite of image pre-processing strategies, notably Canny edge detection, and wavelet transformations, which precede the extraction of salient features and subsequent classification via a Multi-Layer Perceptron (MLP). The optimization process is further refined using the Dragonfly Algorithm (DA). The methodology put forth has attained an impressive training and testing accuracy of 99.82\%, underscoring its efficacy and reliability in the accurate diagnosis of lung cancer.

Figures (7)

• Figure 1: Confusion Matrix
• Figure 2: Predicted Labels for Benign Cases
• Figure 3: Scattered Box Plot of Model Performance
• Figure :
• Figure :