Abstract
In this stage of pulmonary nodules image processing, the pulmonary nodule detection and recognition based on 3D CNN has achieved great success in medical image processing. The tradition pulmonary nodule detection model has a low detection accuracy, in order to more accurately detect the pathological pulmonary nodules, this paper proposes a novel 3D CNN model based on multiscale architecture with channel and spatial attention. That is to say, multi-scale feature extraction module and attention mechanism are added to some residual blocks in 3D Fast-R-CNN, which can improve the performance of the whole network and better learn the features of candidate nodes; Secondly, in the part of regional proposal network, U-Net network and Fast RCNN are combined. The method on LUNA16 dataset shows that the average free-response receiver operating characteristic (FROC) score is 0.848 which is better than other methods. The proposed method can well reduce false positives and improve detection accuracy, providing a reference for clinical medicine.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Horsfall, L.J., Burgess, S., Hall, I.: Genetically raised serum bilirubin levels and lung cancer. A cohort study and Mendelian randomisation using UK Biobank. Thorax 75(11), 955–964 (2020)
Harry, J.D.: Reduced lung-cancer mortality with volume CT screening in a randomized trial. Power Antibody-Based Surveill. 382(6), 503–513 (2020)
Ning, J.X., Zhao, H., Lan, L.: A computer-aided detection system for the detection of lung nodules based on 3D-ResNet. Appl. Sci. 9(24), 5544 (2019)
Zhu, W., Liu, C., Fan, W., Xie, X.: Deep lung: deep 3D dual path nets for automated pulmonary nodule detection and classification. In: Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (2018)
Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. 42(8), 2011–2023 (2020)
Lee, D., Yoo, J., Tak, S.: Deep residual learning for accelerated MRI using magnitude and phase networks (2018)
Liu, M., Jiang, X., Liu, Y.: A semi-supervised convolutional transfer neural network for 3D pulmonary nodules detection. Neurocomputing 391, 199–209 (2020)
Setio, A.A.A., et al.: Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks. IEEE Trans. Med. Imaging 35(5), 1160–1169 (2016)
Shi, Y., Li, H., Zhang, H., Wu, Z., Ren, S.: Accurate and efficient LIF-Nets for 3D detection and recognition. IEEE Access 8, 98562–98571 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhao, Y., Wang, J., Wang, X., Wan, H. (2023). A New Pulmonary Nodule Detection Based on Multiscale Convolutional Neural Network with Channel and Attention Mechanism. In: Sun, J., Wang, Y., Huo, M., Xu, L. (eds) Signal and Information Processing, Networking and Computers. Lecture Notes in Electrical Engineering, vol 917. Springer, Singapore. https://doi.org/10.1007/978-981-19-3387-5_120
Download citation
DOI: https://doi.org/10.1007/978-981-19-3387-5_120
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-3386-8
Online ISBN: 978-981-19-3387-5
eBook Packages: EngineeringEngineering (R0)