Multi-Granularity Dilated Transformer for Lung Nodule Classification via Local Focus Scheme

Kunlun Wu; Bo Peng; Donghai Zhai

doi:10.3390/app13010377

journal article Open Access Dec 28, 2022

Multi-Granularity Dilated Transformer for Lung Nodule Classification via Local Focus Scheme

Kunlun Wu

Bo Peng

Donghai Zhai

Applied Sciences Vol. 13 No. 1 pp. 377 · MDPI AG

View at Publisher Save 10.3390/app13010377

Abstract

Intelligent lung nodules classification is a meaningful and challenging research topic for early precaution of lung cancers, which aims to diagnose the malignancy of candidate nodules from the pulmonary computed tomography images. Nowadays, deep learning methods have made significant achievements in the medical field and promoted developments of lung nodules classification. Nevertheless, mainstream CNNs-based networks typically excel in learning coarse-grained local feature representations via stacked local-aware and weight-shared convolutions, and cannot practically model the long-range context interaction and the spatial dependencies. To tackle the above difficulties, we innovatively propose an effective Multi-Granularity Dilated Transformer to learn the long-range context relations, and explore fine-grained local details via the proposed Local Focus Scheme. Specifically, we delicately design a novel Deformable Dilated Transformer to incorporate diverse contextual information with self-attention for learning long-range global spatial dependencies. Moreover, numerous investigations indicate that local details are extremely crucial to classify indistinguishable lung nodules. Thus, we propose the Local Focus Scheme to focus on the more discriminative local features by modeling channel-wise grouped topology. Consequently, the Multi-Granularity Dilated Transformer is constructed by leveraging the Local Focus Scheme to guide the Deformable Dilated Transformer for learning fine-grained local cues. Experimental results on the mainstream benchmark LIDC-IDRI demonstrate the superiority of our model compared with the state-of-the-art methods.

Topics

No keywords indexed for this article. Browse by subject →

References

43

[1]

Zhang "Lung nodule classification with multilevel patch-based context analysis" IEEE Trans. Biomed. Eng. (2013) 10.1109/tbme.2013.2295593

[2]

Tajbakhsh "Comparing two classes of end-to-end machine-learning models in lung nodule detection and classification: MTANNs vs. CNNs" Pattern Recognit. (2017) 10.1016/j.patcog.2016.09.029

[3]

Hu "Deep learning for image-based cancer detection and diagnosis—A survey" Pattern Recognit. (2018) 10.1016/j.patcog.2018.05.014

[4]

Xie "Automated pulmonary nodule detection in CT images using deep convolutional neural networks" Pattern Recognit. (2019) 10.1016/j.patcog.2018.07.031

[5]

Lee "Gated-dilated networks for lung nodule classification in CT scans" IEEE Access (2019) 10.1109/access.2019.2958663

[6]

Xu "MSCS-DeepLN: Evaluating lung nodule malignancy using multi-scale cost-sensitive neural networks" Med. Image Anal. (2020) 10.1016/j.media.2020.101772

[7]

Squeeze-and-Excitation Networks

Jie Hu, Li Shen, Gang Sun

2018 IEEE/CVF Conference on Computer Vision and Pa... 10.1109/cvpr.2018.00745

[8]

Netto "Automatic segmentation of lung nodules with growing neural gas and support vector machine" Comput. Biol. Med. (2012) 10.1016/j.compbiomed.2012.09.003

[9]

Nibali "Pulmonary nodule classification with deep residual networks" Int. J. Comput. Assist. Radiol. Surg. (2017) 10.1007/s11548-017-1605-6

[10]

Hussein, S., Cao, K., Song, Q., and Bagci, U. (2017, January 25–30). Risk stratification of lung nodules using 3D CNN-based multi-task learning. Proceedings of the International Conference on Information Processing in Medical Imaging, Boon, NC, USA. 10.1007/978-3-319-59050-9_20

[11]

Zhu, W., Liu, C., Fan, W., and Xie, X. (2018, January 12–15). Deeplung: Deep 3d dual path nets for automated pulmonary nodule detection and classification. Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA. 10.1109/wacv.2018.00079

[12]

Jiang "Attentive and ensemble 3D dual path networks for pulmonary nodules classification" Neurocomputing (2020) 10.1016/j.neucom.2019.03.103

[13]

Silva "Lung nodules diagnosis based on evolutionary convolutional neural network" Multimed. Tools Appl. (2017) 10.1007/s11042-017-4480-9

[14]

Learning efficient, explainable and discriminative representations for pulmonary nodules classification

Hanliang Jiang, Fuhao Shen, Fei Gao et al.

Pattern Recognition 2021 10.1016/j.patcog.2021.107825

[15]

Shak "ProCAN: Progressive growing channel attentive non-local network for lung nodule classification" Pattern Recognit. (2022) 10.1016/j.patcog.2021.108309

[16]

Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23–28). End-to-end object detection with transformers. Proceedings of the European Conference on Computer Vision, Glasgow, UK. 10.1007/978-3-030-58452-8_13

[17]

Zhu, X., Su, W., Lu, L., Li, B., Wang, X., and Dai, J. (2020, January 26–30). Deformable DETR: Deformable Transformers for End-to-End Object Detection. Proceedings of the International Conference on Learning Representations, Addis Ababa, Ethiopia.

[18]

Residual Attention Network for Image Classification

Fei Wang, Mengqing Jiang, Chen Qian et al.

2017 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2017.683

[19]

Bello, I., Zoph, B., Vaswani, A., Shlens, J., and Le, Q.V. (November, January 27). Attention augmented convolutional networks. Proceedings of the PIEEE/CVF International Conference on Computer Vision, Seoul, Korea.

[20]

Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., and Shlens, J. (2019). Stand-alone self-attention in vision models. Adv. Neural Inf. Process. Syst., 32.

[21]

Deformable ConvNets V2: More Deformable, Better Results

Xizhou Zhu, Han Hu, Stephen Lin et al.

2019 IEEE/CVF Conference on Computer Vision and Pa... 10.1109/cvpr.2019.00953

[22]

Yang, Z., He, X., Gao, J., Deng, L., and Smola, A. (2016, January 27–30). Stacked attention networks for image question answering. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA. 10.1109/cvpr.2016.10

[23]

SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning

Long Chen, Hanwang Zhang, Jun Xiao et al.

2017 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2017.667

[24]

Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv.

[25]

Jaderberg, M., Simonyan, K., and Zisserman, A. (2015). Spatial transformer networks. Adv. Neural Inf. Process. Syst., 28.

[26]

Mnih, V., Heess, N., and Graves, A. (2014). Recurrent models of visual attention. Adv. Neural Inf. Process. Syst., 27.

[27]

Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., and Bengio, Y. (2015, January 7–9). Show, attend and tell: Neural image caption generation with visual attention. Proceedings of the International Conference on Machine Learning, PMLR, Lille, France.

[28]

Qin, Z., Zhang, P., Wu, F., and Li, X. (2021, January 11–17). Fcanet: Frequency channel attention networks. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada. 10.1109/iccv48922.2021.00082

[29]

Choi, M., Kim, H., Han, B., Xu, N., and Lee, K.M. (2020, January 7–12). Channel attention is all you need for video frame interpolation. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA. 10.1609/aaai.v34i07.6693

[30]

Bastidas, A.A., and Tang, H. (2019, January 16–17). Channel attention networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA. 10.1109/cvprw.2019.00117

[31]

Zhou "Automatic COVID-19 CT segmentation using U-Net integrated spatial and channel attention mechanism" Int. J. Imaging Syst. Technol. (2021) 10.1002/ima.22527

[32]

Fang, W., and Han, X.h. (2020, January 30). Spatial and channel attention modulated network for medical image segmentation. Proceedings of the Proceedings of the Asian Conference on Computer Vision, Kyoto, Japan. 10.1007/978-3-030-69756-3_1

[33]

Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8–14). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany. 10.1007/978-3-030-01234-2_1

[34]

Wu, Y., and He, K. (2018, January 8–14). Group normalization. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany. 10.1007/978-3-030-01261-8_1

[35]

Yu, F., and Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv.

[36]

The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT Scans

Samuel G. Armato, Geoffrey McLennan, Luc Bidaut et al.

Medical Physics 2011 10.1118/1.3528204

[37]

Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.

[38]

An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification

Shiwen Shen, Simon X Han, Denise R Aberle et al.

Expert Systems with Applications 2019 10.1016/j.eswa.2019.01.048

[39]

Shen "Multi-crop convolutional neural networks for lung nodule malignancy suspiciousness classification" Pattern Recognit. (2017) 10.1016/j.patcog.2016.05.029

[40]

Lan "Lung nodule classification using deep local–global networks" Int. J. Comput. Assist. Radiol. Surg. (2019) 10.1007/s11548-019-01981-7

[41]

Nedjah "Detection and classification of pulmonary nodules using deep learning and swarm intelligence" Multimed. Tools Appl. (2020) 10.1007/s11042-019-7473-z

[42]

Knowledge-based Collaborative Deep Learning for Benign-Malignant Lung Nodule Classification on Chest CT

Yutong Xie, Yong Xia, Jianpeng Zhang et al.

IEEE Transactions on Medical Imaging 2018 10.1109/tmi.2018.2876510

[43]

Semi-supervised adversarial model for benign–malignant lung nodule classification on chest CT

Yutong Xie, Jianpeng Zhang, Yong Xia

Medical Image Analysis 2019 10.1016/j.media.2019.07.004

Metrics

14

Citations

43

References

Details

Published: Dec 28, 2022
Vol/Issue: 13(1)
Pages: 377
License: View

Authors

K

Kunlun Wu

School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China

B

Bo Peng

School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China

D

Donghai Zhai

School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China

Funding

Key Research and Development Program of Sichuan Province Award: 23ZDYF0090

Cite This Article

Kunlun Wu, Bo Peng, Donghai Zhai (2022). Multi-Granularity Dilated Transformer for Lung Nodule Classification via Local Focus Scheme. Applied Sciences, 13(1), 377. https://doi.org/10.3390/app13010377

Multi-Granularity Dilated Transformer for Lung Nodule Classification via Local Focus Scheme

You May Also Like