Gene-based lung cancer detection system through omix data and optimized convolutional neural network
Authors:
- 3 March 2026
- journal article
- Published by Springer Nature in Journal of Computer-Aided Molecular Design
- Vol. 40 (1)
Abstract
Among the cancers that pose the greatest threat to life worldwide is lung cancer. According to estimates from the World Cancer Research Fund International, there will be 1.8 million new instances of this disease diagnosed in 2022. When medical personnel diagnose and classify patients' conditions proactively, they may treat them safely and efficiently. The advent of the microarray method has made it possible to examine the connections between genes and various diseases, including lung malignancies. Numerous methods have been developed to forecast gene-based diseases, but they still have problems with high computational cost, time consumption, complex data, and inaccurate prediction. Therefore, create an efficient lung cancer detection system in this research by designing an Improved Convolutional Neural Network with Honey Bee Mating Optimization (ICNN-HBMO). First, the system is trained using Omix data, and the dataset is normalized using min-max normalization. Then Kernel Principal Component Analysis (KPCA) technique is employed for feature reduction. Furthermore, an enhanced CNN is employed to classify lung cancer using HBMO. The HBMO algorithm optimizes the weight and bias parameters of the ICNN to improve prediction performance. The developed method is implemented in the Matlab tool, and the improved performance is compared to other existing methods. The developed technique attains high accuracy and high precision of 99.2% and 99%.Keywords
This publication has 48 references indexed in Scilit:
- Construction of the XGBoost model for early lung cancer prediction based on metabolic indicesBMC Medical Informatics and Decision Making, 2023
- [Retracted] Developing an Efficient Cancer Detection and Prediction Tool Using Convolution Neural Network Integrated with Neural Pattern RecognitionBioMed Research International, 2023
- Identification of immune microenvironment subtypes and signature genes for Alzheimer’s disease diagnosis and risk prediction based on explainable machine learningFrontiers in Immunology, 2022
- A Deep Ranking Weighted Multihashing Recommender System for Item RecommendationComputational Intelligence and Neuroscience, 2022
- Gene-Based Diagnosis of Tuberculosis from Oral Swabs with a New Generation Pathogen Enrichment TechniqueMicrobiology Spectrum, 2022
- Gene-Based Therapeutics for Inherited Retinal DiseasesFrontiers in Genetics, 2022
- The Lactate/Albumin Ratio Predicts Mortality in Critically Ill Patients with Acute Kidney Injury: An Observational Multicenter Study on the eICU DatabaseInternational Journal of General Medicine, 2021
- Treatment response to low-dose ketamine infusion for treatment-resistant depression: A gene-based genome-wide association studyGenomics, 2021
- [Retracted] Automatic Detection of High‐Frequency Oscillations Based on an End‐to‐End Bi‐Branch Neural Network and Clinical Cross‐ValidationComputational Intelligence and Neuroscience, 2021
- Label-free detection of cancer related gene based on target recycling and palindrome-mediated strand displacement amplificationTalanta, 2020