Multi-view attention-based deep learning for benign–malignant classification of pulmonary nodules
- 1School of Computer Science and Engineering, Jishou University, Zhangjiajie, Hunan, China
- 2College of Intelligent Construction, Jishou University, Zhangjiajie, Hunan, China
Abstract
Accurate classification of pulmonary nodules is essential for early lung cancer diagnosis, yet the limited spatial information provided by a single computed tomography slice may hinder the characterization of complex nodule morphology. Although multi-view strategies can capture complementary anatomical information, conventional fusion methods often fail to account for lesion-specific features and differences in the contribution of individual views. To address these limitations, we propose a tri-view pulmonary nodule classification framework that combines Lesion-Guided Attention (LGA) with View-Weighted Fusion (VWF). The framework extracts complementary representations from axial, coronal, and sagittal slices. LGA introduces lesion masks as weak spatial priors to refine lesion-related feature responses while preserving contextual information, whereas VWF learns sample-dependent weights to adaptively aggregate the three view representations. The framework was evaluated on 869 nodules (448 benign and 421 malignant) derived from the public Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset. It achieved an accuracy of 93.08%, an AUC of 97.06%, and an F1-score of 92.68%, representing the highest values for these three metrics among the models included in the baseline comparison. Ablation analysis further showed that the combined use of LGA and VWF provided the best overall balance among the evaluated configurations. In the displayed test cases, Gradient-weighted Class Activation Mapping visualizations showed that the learned responses were concentrated mainly within or adjacent to lesion-relevant regions. These findings support the potential value of combining lesion-aware feature refinement with adaptive multi-view fusion for pulmonary nodule classification within the evaluated LIDC-IDRI cohort.
Related
- Integrated transcriptomic and clinical prediction model for malignant pulmonary nodules : Model development, external dataset evaluation, and single-center expression validation
- Ultrasound-based deep learning radiomics with explainable machine learning for predicting benign and malignant thyroid nodules in lymphocytic thyroiditis: a multicenter study
- Association between uncertainty regarding malignant risk and anxiety in patients with pulmonary nodules: a serial mediation analysis of illness perception and rumination
- Feature-aware attention convolutional neural network for efficient pulmonary fibrosis classification from chest CT images with FPGA deployment
- Multi-scale convolution with efficient channel attention improves benign–malignant classification of spinal tumors on T2-weighted fat-suppressed MRI
BibTeX
@article{zhang2026multiview,
title = {{Multi-view attention-based deep learning for benign–malignant classification of pulmonary nodules}},
author = {Lijun Zhang and Debing Zhuo and Xiaolu Wu and Yuchou He and Guodong Kang},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0357963},
url = {https://doi.org/10.1371/journal.pone.0357963},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Multi-view attention-based deep learning for benign–malignant classification of pulmonary nodules
AU - Lijun Zhang
AU - Debing Zhuo
AU - Xiaolu Wu
AU - Yuchou He
AU - Guodong Kang
PY - 2026
DA - 2026/09/15
JO - PLOS One
DO - 10.1371/journal.pone.0357963
UR - https://doi.org/10.1371/journal.pone.0357963
AB - Accurate classification of pulmonary nodules is essential for early lung cancer diagnosis, yet the limited spatial information provided by a single computed tomography slice may hinder the characterization of complex nodule morphology. Although multi-view strategies can capture complementary anatomical information, conventional fusion methods often fail to account for lesion-specific features and differences in the contribution of individual views. To address these limitations, we propose a tri-view pulmonary nodule classification framework that combines Lesion-Guided Attention (LGA) with View-Weighted Fusion (VWF). The framework extracts complementary representations from axial, coronal, and sagittal slices. LGA introduces lesion masks as weak spatial priors to refine lesion-related feature responses while preserving contextual information, whereas VWF learns sample-dependent weights to adaptively aggregate the three view representations. The framework was evaluated on 869 nodules (448 benign and 421 malignant) derived from the public Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset. It achieved an accuracy of 93.08%, an AUC of 97.06%, and an F1-score of 92.68%, representing the highest values for these three metrics among the models included in the baseline comparison. Ablation analysis further showed that the combined use of LGA and VWF provided the best overall balance among the evaluated configurations. In the displayed test cases, Gradient-weighted Class Activation Mapping visualizations showed that the learned responses were concentrated mainly within or adjacent to lesion-relevant regions. These findings support the potential value of combining lesion-aware feature refinement with adaptive multi-view fusion for pulmonary nodule classification within the evaluated LIDC-IDRI cohort.
SN - 1932-6203
ER -