Classification of Lung Adenocarcinoma Using Convolutional Neural Networks: A Bioinformatics Approach

Abstract

Lung cancer, recognized as one of the most lethal malignancies globally, manifests predominantly as lung adenocarcinoma (LUAD) within the broader classification of nonsmall cell lung cancer (NSCLC). The imperative for accurate and prompt diagnosis to facilitate efficacious treatment underscores the significance of advancements in diagnostic methodologies. This study introduces a convolutional neural network (CNN) framework tailored for the interpretation of bioinformatics datasets, specifically focusing on the classification of lung adenocarcinoma. Emphasizing the integration of gene-based biomarker informatics, this approach endeavors to mitigate hierarchical discrepancies inherent within similarity indices encountered during dataset processing. Through the utilization of three gene expression datasets-GSE118370, GSE85841, and GSE32863sourced from the Gene Expression Omnibus (GEO), key features indicative of lung adenocarcinoma were meticulously analyzed. This methodology not only facilitates the precise categorization of data samples into lung adenocarcinoma but also enhances the reliability of the findings. The implementation of this CNN framework on the specified datasets yielded a classification accuracy of 93.32% and a precision of 94.56%, thereby surpassing the performance metrics of existing techniques. This research underscores the potential of integrating CNNs with bioinformatics for the refined classification of lung adenocarcinoma, heralding a significant step forward in the precise identification of this prevalent form of lung cancer.