Classification of Pulmonary Nodule by Combining Long-Distance Channel Attention and Pathological Feature

doi:10.12068/j.issn.1005-3026.2023.04.003

Abstract

Abstract: Aiming at the common problems of existing deep learning networks， such as lack of correlation of long-distance feature channels and network self-extraction features obliterating the dominant pathological features of pulmonary nodules. Firstly， by combining channel attention and spatial attention， an attention module LCA (long-distance channel attention) that can effectively establish the correlation of long-distance feature channels is proposed. Secondly， the dominant pathological features such as pulmonary nodule diameter， texture and calcification are fused with their depth features to enhance the importance of these dominant features. Finally， a feature extraction network DLCANet (dual-connected long-distance channel attention network) and a classifier model MARTM (multiple additive regression tree model) are built. The classification experiments are carried out on the datasets LIDC-LDRI and LUNA16. Compared with the benchmark model DPN (dual path network)， the accuracy rate is increased by 3.63%， the false positive rate is decreased by 8.66%， and the overall performance is better than those of current mainstream models.

Key words: benign and malignant classification; long-distance channel attention mechanism; pathological dominant features; feature fusion; iterative decision tree algorithm

CLC Number:

TP391.4

DING Qi-chuan， WANG Li， LIU Cheng. Classification of Pulmonary Nodule by Combining Long-Distance Channel Attention and Pathological Feature[J]. Journal of Northeastern University(Natural Science), 2023, 44(4): 476-485.

References

[1]Zhang S W，Sun K X，Zheng R S，et al.Cancer incidence and mortality in China，2015［J］.Journal of The National Cancer Center，2021，1(1):2-11.
[2]Sun W Q，Zheng B，Qian W.Computer aided lung cancer diagnosis with deep learning algorithms［C］//Medical Imaging 2016:Computer-Aided Diagnosis.San Diego:SPIE，2016:241-248.
[3]Buty M，Xu Z Y，Gao M C，et al.Characterization of lung nodule malignancy using hybrid shape and appearance features［C］//International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham:Springer，2016:662-670.
[4]Kumar D，Wong A，Clausi D A，et al.Lung nodule classification using deep features in CT images［C］//12th Conference on Computer and Robot Vision.Halifax，2015:133-138.
[5]Onishi Y，Teramoto A，Tsujimoto M，et al.Multiplanar analysis for pulmonary nodule classification in CT images using deep convolutional neural network and generative adversarial networks［J］.International Journal of Computer Assisted Radiology and Surgery，2020，15(1):173-178.
[6]Zhu W T，Liu C C，Fan W，et al.DeepLung:3D deep convolutional nets for automated pulmonary nodule detection and classification［C］//2018 IEEE Winter Conference on Applications of Computer Vision (WACV).Lake Tahoe，2018:673-681.
[7]孙华聪，彭延军，郭燕飞，等.3D多尺度深度卷积神经网络肺结节检测［J］.中国图象图形学报，2021，26(7):1716-1725.(Sun Hua-cong，Peng Yan-jun，Guo Yan-fei，et al.3D multi-scale deep convolutional neural networks in pulmonary nodule detection［J］.Journal of Image and Graphics，2021，26(7):1716-1725.)
[8]Hu J，Shen L，Albanie S，et al.Squeeze-and-excitation networks［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City，2018:7132-7141.
[9]Zhang G，Yang Z，Gong L，et al.Classification of lung nodules based on CT images using squeeze-and-excitation network and aggregated residual transformations［J］.La Radiologia Medica，2020，125(4):374-383.
[10]Woo S，Park J，Lee J Y，et al.CBAM:convolutional block attention module［C］//Proceedings of the European Conference on Computer Vision (ECCV).Cham:Springer，2018:3-19.
[11]Jiang H，Gao F，Xu X，et al.Attentive and ensemble 3D dual path networks for pulmonary nodules classification［J］.Neurocomputing，2020，398:422-430.
[12]张福玲，张少敏，支力佳，等.融合注意力机制和特征金字塔网络的CT图像肺结节检测［J］.中国图象图形学报，2021，26(9):2156-2170.(Zhang Fu-ling，Zhang Shao-min，Zhi Li-jia，et al.Detection of pulmonary nodules in CT images by combining an attention mechanism and a feature pyramid network［J］.Journal of Image and Graphics，2021，26(9):2156-2170.)
[13]Al-Shabi M，Lan B L，Chan W Y，et al.Lung nodule classification using deep local-global networks［J］.International Journal of Computer Assisted Radiology and Surgery，2019，14(10):1815-1819.
[14]刘秀玲，戚帅帅，熊鹏，等.融合多尺度信息的肺结节自动检测算法［J］.生物医学工程学杂志，2020，37(3):434-441.(Liu Xiu-ling，Qi Shuai-shuai，Xiong Peng，et al.An automatic pulmonary nodules detection algorithm with multi-scale information［J］.Journal of Biomedical Engineering，2020，37(3):434-441.)
[15]Zhang B H，Qi S L，Monkam P.Ensemble learners of multiple deep CNNs for pulmonary nodules classification using CT images［J］.IEEE Access，2019，7:110358-110371.
[16]Wang Y，Zhang H，Chae K J，et al.Novel convolutional neural network architecture for improved pulmonary nodule classification on computed tomography［J］.Multidimensional Systems and Signal Processing，2020，31(3):1163-1183.
[17]Zhao J M，Zhang C，Li D，et al.Combining multi-scale feature fusion with multi-attribute grading，a CNN model for benign and malignant classification of pulmonary nodules［J］.Journal of Digital Imaging，2020，33(4):869-878.
[18]Chen Y P，Li J N，Xiao H X，et al.Dual path networks［EB/OL］.［2021-12-17］.https://arxiv.org/pdf/1707.01629.pdf.
[19]Friedman J H.Greedy function approximation:a gradient boosting machine［J］.Annals of Statistics，2001，29(5):1189-1232.
[20]Armato III S G，McLennan G，Bidaut L，et al.The lung image database consortium (LIDC) and image database resource initiative (IDRI):a completed reference database of lung nodules on CT scans［J］.Medical Physics，2011，38(2):915-931.
[21]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［J］.Medical Image Analysis，2017，42:1-13.
[22]Zhang H，Zu K，Lu J，et al.EPSANet:an efficient pyramid squeeze attention block on convolutional neural network［EB/OL］.［2021-12-17］.https://arxiv.org/pdf/2105.14447.pdf
[23]He K，Zhang X，Ren S，et al.Deep residual learning for image recognition［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas，2016:770-778.
[24]Xie Y，Zhang J，Xia Y，et al.Fusing texture，shape and deep model-learned information at decision level for automated classification of lung nodules on chest CT［J］.Information Fusion，2018，42:102-110.
[25]Polat H，Mehr D H.Classification of pulmonary CT images by using hybrid 3D-deep convolutional neural network architecture［J］.Applied Sciences，2019，9(5):940-955.
[26]Lima L L，Ferreira J R，Oliveira M C.Toward classifying small lung nodules with hyperparameter optimization of convolutional neural networks［J］.Computational Intelligence，2021，37(4):1599-1618.
[27]Liu H，Cao H，Song E，et al.Multi-model ensemble learning architecture based on 3D CNN for lung nodule malignancy suspiciousness classification［J］.Journal of Digital Imaging，2020，33(5):1242-1256.
[28]Jiang H，Shen F，Gao F，et al.Learning efficient，explainable and discriminative representations for pulmonary nodules classification［J］.Pattern Recognition，2021，113:107825-107834.
[29]Ali I，Muzammil M，Haq I U，et al.Deep feature selection and decision level fusion for lungs nodule classification［J］.IEEE Access，2021，9:18962-18973.
[30]Al-Shabi M，Shak K，Tan M.3D axial-attention for lung nodule classification［J］.International Journal of Computer Assisted Radiology and Surgery，2021，16(8):1319-1324.［31］Mastouri R，Khlifa N，Neji H，et al.A bilinear convolutional neural network for lung nodules classification on CT images［J］.International Journal of Computer Assisted Radiology and Surgery，2021，16(1):91-101.