3D-DHA-MAFNet: A Multi-View Attention-Enhanced Deep Learning System for Lung Nodule Detection and Classification
Abstract
Lung cancer, one of the most lethal malignancies globally, has a high mortality rate, making early screening and accurate diagnosis crucial for improving patient survival rates. Low-dose computed tomography (LDCT) has significantly increased the detection rate of lung nodules, but the vast amount of imaging data poses a significant challenge for manual interpretation. This article proposed a lung nodule computer-aided quantitative diagnostic system based on a three-dimensional convolutional neural network (3D CNN), named 3D-DHA-MAFNet. By integrating deformable convolution network (DCN), hybrid attention mechanism (HAM), and multi-view adaptive fusion network (MAFN), this system significantly enhanced the detection and benign/malignant classification capabilities for small and irregular lung nodules. The model was trained and evaluated on the lung nodule analysis 2016 (LUNA16) and LIDC-IDRI datasets with a patient-level split in the ratio of 7:2:1. The number of training epochs was 200. Data augmentation methods included random rotation (±15°), translation (±5 pixels), and elastic deformation. The performance was compared with baseline models including 3D-UNet, AttentNet, 3DAGNet, 3D multi-scale capsule network (3D-MCN), and 3D multi-view SE CNN (3D MVSECNN). Experiments showed that on the LUNA16 dataset, the model achieved a detection sensitivity of 98.7% with a low false-positive rate of 1.2 per scan, which was a notable improvement over baseline models like 3D-UNet. On the LIDC-IDRI dataset, the classification accuracy for benign and malignant nodules reached 96.8%, with an AUC value of 0.983, and particularly, the sensitivity for malignant nodules was enhanced to 97.5%. Ablation studies verified the synergistic gains of each module, and cross-clinical dataset testing further demonstrated its strong generalization ability. This article presents a high-precision and interpretable intelligent diagnostic tool designed for clinical applications, which holds strong potential to promote the clinical translation of early lung cancer screening.References
Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, Jemal A. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin, 2024, 74(3):229-263. D
Ramaswamy A. Lung cancer screening: Review and 2021 update. Curr Pulmonol Rep, 2022,11(1):15-28.
Lu Z, Long F, He X. Classification and segmentation algorithm in benign and malignant pulmonary nodules under different CT reconstruction. Comput Math Methods Med, 2022, 2022:3490463.
Li Y, Hui L, Wang X, Zou L, Chua S. Lung nodule detection using a multi-scale convolutional neural network and global channel spatial attention mechanisms. Sci Rep, 2025,15(1):12313.
Hammad M, ElAffendi M, El-Latif AAA, Ateya AA, Ali G, Plawiak P. Explainable AI for lung cancer detection via a custom CNN on CT images. Sci Rep, 2025, 15(1):12707.
Peng H, Sun H, Guo Y. 3D multi-scale deep convolutional neural networks for pulmonary nodule detection. PLoS One, 2021,16(1):e0244406.
Pan J, He Z, Li Y, Zeng W, Guo Y, Jia L, Jiang H, Chen W, Lu Y. Atypical architectural distortion detection in digital breast tomosynthesis: a multi-view computer-aided detection model with ipsilateral learning. Phys Med Biol, 2023, 68(23).
Tong C, Liang B, Zhang M, Chen R, Sangaiah AK, Zheng Z, Wan T, Yue C, Yang X. Pulmonary nodule detection based on ISODATA-improved faster RCNN and 3D-CNN with Focal loss. Acm T Multim Comput (TOMM), 2020.
Li Y, Li P, Wang H, Gong X, Fang Z. CAML-PSPNet: A medical image segmentation network based on coordinate attention and a mixed loss function. Sensors (Basel), 2025, 25(4):1117.
Tan M, Wu F, Yang B, Ma J, Kong D, Chen Z, Long D. Pulmonary nodule detection using hybrid two-stage 3D CNNs. Med Phys, 2020, 47(8):3376-3388.
Song L, Zhang M, Wu L. Detection of low-dose computed tomography pulmonary nodules based on 3D CNN-CapsNet. Electronics Letters, 2023, 59(18).
Almahasneh M, Xie X, Paiement A. AttentNet: Fully convolutional 3D attention for lung nodule detection. Sn Comput. Sci. 2025, 6, 292.
Xiao Z, Liu B, Geng L, Zhang F, Liu Y. Segmentation of lung nodules using improved 3D-UNet neural network. Symmetry, 2020, 12(11):1787.
Xu X, Du L, Yin D. Dual-branch feature fusion S3D V-Net network for lung nodules segmentation. J Appl Clin Med Phys, 2024, 25(6):e14331.
Liu JJ, Li YQ, Li WT, Li ZS, Lan YH. Multiscale lung nodule segmentation based on 3D coordinate attention and edge enhancement. Electronic Research Archive, 2024, 32(5): 3016-3037.
Jian M, Zhang L, Jin H, Li X. 3DAGNet: 3D deep attention and global search network for pulmonary nodule detection. Electronics, 2023, 12(10):14.
Yang Y, Li X, Fu J, Han Z, Gao B. 3D multi-view squeeze-and-excitation convolutional neural network for lung nodule classification. Med Phys, 2023, 50(3):1905-1916.
Afshar P, Oikonomou A, Naderkhani F, Tyrrell PN, Plataniotis KN, Farahani K, Mohammadi A. 3D-MCN: A 3D multi-scale capsule network for lung nodule malignancy prediction. Sci Rep, 2020, 10(1):7948.
Huang YS, Wang TC, Huang SZ, Zhang J, Chen HM, Chang YC, Chang RF. An improved 3-D attention CNN with hybrid loss and feature fusion for pulmonary nodule classification. Comput Methods Programs Biomed, 2023, 229:107278.
Prithvika P C S, Anbarasi L J. V-3DResNets: a 3D convolutional neural network based on residual network variants and slice grouping for pulmonary nodule detection. Multimedia Tools & Applications, 2024, 83(31).
DOI:
https://doi.org/10.31449/inf.v49i25.11184Downloads
Published
How to Cite
Issue
Section
License
I assign to Informatica, An International Journal of Computing and Informatics ("Journal") the copyright in the manuscript identified above and any additional material (figures, tables, illustrations, software or other information intended for publication) submitted as part of or as a supplement to the manuscript ("Paper") in all forms and media throughout the world, in all languages, for the full term of copyright, effective when and if the article is accepted for publication. This transfer includes the right to reproduce and/or to distribute the Paper to other journals or digital libraries in electronic and online forms and systems.
I understand that I retain the rights to use the pre-prints, off-prints, accepted manuscript and published journal Paper for personal use, scholarly purposes and internal institutional use.
In certain cases, I can ask for retaining the publishing rights of the Paper. The Journal can permit or deny the request for publishing rights, to which I fully agree.
I declare that the submitted Paper is original, has been written by the stated authors and has not been published elsewhere nor is currently being considered for publication by any other journal and will not be submitted for such review while under review by this Journal. The Paper contains no material that violates proprietary rights of any other person or entity. I have obtained written permission from copyright owners for any excerpts from copyrighted works that are included and have credited the sources in my article. I have informed the co-author(s) of the terms of this publishing agreement.
Copyright © Slovenian Society Informatika
