Genetic Deep Learning for Lung Cancer Screening

TL;DR

This paper introduces a genetic algorithm-based neural architecture search to develop a novel CNN for early lung cancer detection in chest X-rays, achieving high accuracy and efficiency improvements over existing models.

Contribution

It presents a novel genetic algorithm approach for neural architecture search tailored to lung cancer detection in chest X-rays, outperforming standard models in accuracy and parameter efficiency.

Findings

Achieved 97.15% accuracy in lung cancer classification.

Reduced model parameters by factors of 4 and 14 compared to Inception-V3 and ResNet-152.

Outperformed existing CNN models in accuracy and efficiency.

Abstract

Convolutional neural networks (CNNs) have shown great promise in improving computer aided detection (CADe). From classifying tumors found via mammography as benign or malignant to automated detection of colorectal polyps in CT colonography, these advances have helped reduce the need for further evaluation with invasive testing and prevent errors from missed diagnoses by acting as a second observer in today's fast paced and high volume clinical environment. CADe methods have become faster and more precise thanks to innovations in deep learning over the past several years. With advancements such as the inception module and utilization of residual connections, the approach to designing CNN architectures has become an art. It is customary to use proven models and fine tune them for particular tasks given a dataset, often requiring tedious work. We investigated using a genetic algorithm (GA) to conduct a neural architectural search (NAS) to generate a novel CNN architecture to find early stage lung cancer in chest x-rays (CXR). Using a dataset of over twelve thousand biopsy proven cases of lung cancer, the trained classification model achieved an accuracy of 97.15% with a PPV of 99.88% and a NPV of 94.81%, beating models such as Inception-V3 and ResNet-152 while simultaneously reducing the number of parameters a factor of 4 and 14, respectively.