Deep learning-based lung cancer classification of CT images
Top Cited Papers
Open Access
- 1 July 2025
- journal article
- research article
- Published by Springer Nature in BMC Cancer
- Vol. 25 (1) , 1-12
Abstract
Lung cancer remains a leading cause of cancer-related deaths worldwide, with accurate classification of lung nodules being critical for early diagnosis. Traditional radiological methods often struggle with high false-positive rates, underscoring the need for advanced diagnostic tools. In this work, we introduce DCSwinB, a novel deep learning-based lung nodule classifier designed to improve the accuracy and efficiency of benign and malignant nodule classification in CT images. Built on the Swin-Tiny Vision Transformer (ViT), DCSwinB incorporates several key innovations: a dual-branch architecture that combines CNNs for local feature extraction and Swin Transformer for global feature extraction, and a Conv-MLP module that enhances connections between adjacent windows to capture long-range dependencies in 3D images. Pretrained on the LUNA16 and LUNA16-K datasets, which consist of annotated CT scans from thousands of patients, DCSwinB was evaluated using ten-fold cross-validation. The model demonstrated superior performance, achieving 90.96% accuracy, 90.56% recall, 89.65% specificity, and an AUC of 0.94, outperforming existing models such as ResNet50 and Swin-T. These results highlight the effectiveness of DCSwinB in enhancing feature representation while optimizing computational efficiency. By improving the accuracy and reliability of lung nodule classification, DCSwinB has the potential to assist radiologists in reducing diagnostic errors, enabling earlier intervention and improved patient outcomes.Keywords
Funding Information
- National Natural Science Foundation of China (62376183, 62376183, 62376183, 62376183, 62376183, 62376183, 62376183)
- The central government guides local science and technology development funding projects (YDZJSX2022C004, YDZJSX2022C004, YDZJSX2022C004, YDZJSX2022C004, YDZJSX2022C004, YDZJSX2022C004, YDZJSX2022C004)
- National Natural Science Foundation of China (U21A20469, U21A20469, U21A20469, U21A20469, U21A20469, U21A20469, U21A20469)
- Supported by the special fund for Science and Technology Innovation Teams of Shanxi Province (202304051001009, 202304051001009, 202304051001009, 202304051001009, 202304051001009, 202304051001009, 202304051001009)
This publication has 28 references indexed in Scilit:
- Robust kidney carcinoma prognosis and characterization using Swin-ViT and DeepLabV3+ with multi-model transfer learningApplied Soft Computing, 2024
- TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformersMedical Image Analysis, 2024
- Semi-Mamba-UNet: Pixel-level contrastive and cross-supervised visual Mamba-based UNet for semi-supervised medical image segmentationKnowledge-Based Systems, 2024
- Classification of lung cancer subtypes on CT images with synthetic pathological priorsMedical Image Analysis, 2024
- Enhancing the Quality and Authenticity of Synthetic Mammogram Images for Improved Breast Cancer DetectionIEEE Access, 2024
- Non-invasively Discriminating the Pathological Subtypes of Non-small Cell Lung Cancer with Pretreatment 18F-FDG PET/CT Using Deep LearningAcademic Radiology, 2023
- Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 CountriesCA: A Cancer Journal for Clinicians, 2021
- CornerNet: Detecting Objects as Paired KeypointsInternational Journal of Computer Vision, 2019
- Estimating the global cancer incidence and mortality in 2018: GLOBOCAN sources and methodsInternational Journal of Cancer, 2018
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016