ICN-DETR: Inter-Slice Continuity and Nodule-Aware Pulmonary Nodule Detection
DOI:
https://doi.org/10.63313/AJET.9074Keywords:
Pulmonary Nodule Detection, Computed Tomography, RT-DETR, Inter-Slice Continuity, Cross-Scale Feature FusionAbstract
Pulmonary nodule detection in computed tomography images remains challenging, especially for small nodules with low contrast and limited image features. To improve detection performance, we propose ICN-DETR, a pulmonary nodule detection model based on RT-DETR-R18. The model uses three consecutive CT slices as input and introduces feature interaction between adjacent slices to strengthen the representation of pulmonary nodules. In addition, shallow high-resolution features are incorporated into multi-scale feature fusion to reduce the loss of boundary and texture information during downsampling. The query selection and localization process is also improved to increase the sensitivity of the detector to small nodules and reduce localization errors. Experiments on the LUNA16 dataset show that ICN-DETR achieves a Precision of 89.5%, Recall of 90.3%, F1-score of 89.9%, and [email protected] of 91.9%. Compared with RT-DETR-R18, the F1-score and [email protected] increase by 3.9 and 4.3 percentage points, respectively. The results demonstrate that ICN-DETR can effectively improve pulmonary nodule detection with a moderate increase in model complexity.
References
[1] Bray F, Laversanne M, Sung H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, 2024, 74(3): 229–263. DOI: 10.3322/caac.21834.
[2] National Lung Screening Trial Research Team. Reduced lung-cancer mortality with low-dose computed tomographic screening. New England Journal of Medicine, 2011, 365(5): 395–409. DOI: 10.1056/NEJMoa1102873.
[3] Setio A A A, Ciompi F, Litjens G, et al. Pulmonary nodule detection in CT images: False positive reduction using multi-view convolutional networks. IEEE Transactions on Medical Imaging, 2016, 35(5): 1160–1169. DOI: 10.1109/TMI.2016.2536809.
[4] Dou Q, Chen H, Jin Y, et al. Automated pulmonary nodule detection via 3D ConvNets with online sample filtering and hybrid-loss residual learning. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2017, 2017: 630–638. DOI: 10.1007/978-3-319-66179-7_72.
[5] Su Y, Li D, Chen X. Lung nodule detection based on Faster R-CNN framework. Computer Methods and Programs in Biomedicine, 2021, 200: 105866. DOI: 10.1016/j.cmpb.2020.105866.
[6] Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2117–2125. DOI: 10.1109/CVPR.2017.106.
[7] Carion N, Massa F, Synnaeve G, et al. End-to-end object detection with transformers. In: European Conference on Computer Vision, 2020: 213–229. DOI: 10.1007/978-3-030-58452-8_13.
[8] Zhao Y, Lv W, Xu S, et al. DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024: 16965–16974.
[9] Tang J, Chen X, Fan L, Zhu Z, Huang C. LN-DETR: An efficient Transformer architecture for lung nodule detection with multi-scale feature fusion. Neurocomputing, 2025, 633: 129827. DOI: 10.1016/j.neucom.2025.129827.
[10] Zhou D, Xu H, Liu W, Liu F. LN-DETR: Cross-scale feature fusion and re-weighting for lung nodule detection. Scientific Reports, 2025, 15: 15543. DOI: 10.1038/s41598-025-00309-7.
[11] Xie H, Yang D, Sun N, Chen Z, Zhang Y. Automated pulmonary nodule detection in CT images using deep convolutional neural networks. Pattern Recognition, 2019, 85: 109–119. DOI: 10.1016/j.patcog.2018.07.031.
[12] Li Y, Fan Y. DeepSEED: 3D squeeze-and-excitation encoder-decoder convolutional neural networks for pulmonary nodule detection. In: 2020 IEEE 17th International Symposium on Biomedical Imaging, 2020: 1866–1869. DOI: 10.1109/ISBI45749.2020.9098317.
[13] Zhu X, Su W, Lu L, Li B, Wang X, Dai J. Deformable DETR: Deformable transformers for end-to-end object detection. In: International Conference on Learning Representations, 2021.
[14] Armato S G III, McLennan G, Bidaut L, et al. The Lung Image Database Consortium and Image Database Resource Initiative: A completed reference database of lung nodules on CT scans. Medical Physics, 2011, 38(2): 915–931. DOI: 10.1118/1.3528204.
[15] Setio A A A, Traverso A, de Bel T, et al. Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge. Medical Image Analysis, 2017, 42: 1–13. DOI: 10.1016/j.media.2017.06.015.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 by author(s) and Erytis Publishing Limited
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
