A deep learning model to enhance lung cancer detection using 'Dual-Branch' model classification approach - Abstract

Sep 22, 2026

Upload by Logic

Cancer remains a life-threatening global challenge, and lung cancer is among the most devastating forms. Early detection and accurate classification are essential, with computed tomography (CT) serving as a key diagnostic tool. Prior work is constrained by shortages of available samples and limits in input modalities, reducing model effectiveness. This research proposes the Dual-Branch Model Classification Approach (DbMCA), a two-stage method integrating image and mask data to improve detection accuracy and scalability. Experiments on LIDC-IDRI show higher accuracy and F1 scores, while CNN sensitivity to sparse masks is observed; DbMCA outperforms baselines despite computational and bias-related limitations.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages24

Reading Time1 h 0 min

AccessFree to download

Abstract

Introduction

OPEN ACCESS Citation: Shweikeh E, Al-Rajab M, Lu J, Xu Q, Joy M, Ahmed A, et al. (2026) A deep learning model to enhance lung cancer detection using‘Dual-Branch’ model classification approach. PLoS One 21(1): e0339404. [https://doi](https://doi). org/10.1371/journal.pone.0339404 Editor: Ananth JP, Dayananda Sagar University, INDIA Received: May 14, 2024 Accepted: December 5, 2025 Published: January 9, 2026 Peer Review History: PLOS recognizes the benefits of transparency in the peer review process; therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. The editorial history of this article is available here: [https://doi.org/10.1371/journal](https://doi.org/10.1371/journal). pone.0339404 Copyright: © 2026 Shweikeh et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, RESEARCH ARTICLE A deep learning model to enhance lung cancer detection using ‘Dual-Branch’ model classification approach Emad Shweikeh1*, Murad Al-Rajab2 Joan Lu3, Qiang Xu1, Mike Joy4, Abderahman Ahmed5, Hong Chang6 1 Department of Computer Science, School of Computing and Engineering, University of Huddersfield, Huddersfield, United Kingdom, 2 Computer Science and IT Department, College of Engineering, Abu Dhabi University, Abu Dhabi, United Arab Emirates, 3 Leeds Beckett University, Leeds, United Kingdom, 4 Department of Computer Science, University of Warwick, Coventry, United Kingdom, 5 Department of Electronic Engineering, University of Seville, Seville, Spain, 6 Oxford MEStar Ltd, Yarnton, England * [emad.shweikeh@hotmail.com](emad.shweikeh@hotmail.com) Abstract Cancer remains a life-threatening global challenge, with lung cancer ranking among the most devastating forms, impacting millions annually. Early detection and accurate classification are essential for improving patient survival rates, and computed tomography (CT) has become a critical tool in lung cancer diagnosis. Despite advancements, previous studies have faced notable challenges, particularly a shortage of available samples and limitations in input modalities, both of which hinder model performance. Addressing these issues, this research introduces the Dual-Branch Model Classification Approach (DbMCA) , a two-stage strategy that integrates image and mask data to enhance detection accuracy and scalability. Two comparative experiments were conducted using the LIDC-IDRI dataset with varying data sizes to evaluate the impact of sample size and dual-input modalities. The DbMCA achieved remarkable results, as it performed higher accuracy results a 91.21% accuracy and 91. 18% F1-score in the smaller dataset and an exceptional 98.04% accuracy and 98.01% F1-score in the larger dataset. CNN performance on sparse mask data declines with scale, while DNN and SVM consistently outperform it, highlighting architecture sensitivity to sparsity. This demonstrates the model’s improved discriminative power and potential for detecting subtle lung cancer patterns, however, based on statistical evidence DbMCA significantly outperforms weaker baselines and successfully integrates multi-modal information. Nonetheless, certain limitations were observed, such as the high computational requirements stemming from large sample sizes, the constrained information provided by segmentation masks, and the presence of potential biases in the dataset. These challenges hinder the model’s ability to generalize effectively. Future research should aim to enhance image quality, broaden the scope of datasets, and overcome segmentation-related constraints to make further progress PLOS One | [https://doi.org/10.1371/journal.pone.0339404](https://doi.org/10.1371/journal.pone.0339404) January 9, 2026 1 / 24 and reproduction in any medium, provided the original author and source are credited. Data availability statement: The data

FAQs

What problem does DbMCA address in lung cancer detection?

It targets limitations in earlier studies, especially limited sample availability and constraints in input modalities, by improving detection accuracy and scalability.

How does the Dual-Branch Model Classification Approach work?

DbMCA uses a two-stage strategy that integrates image data with mask data to strengthen classification performance.

What dataset and evaluation comparisons were used?

The study uses the LIDC-IDRI dataset and runs comparative experiments with varying data sizes to evaluate the effect of sample size and dual-input modalities.

Sep 22, 2026

Upload by Logic