Lung cancer is the uncontrolled growth of cells that originates in the lung parenchyma or cells that line the air passages. These cells divide rapidly to form malicious tumors. This paper proposes a multi-task ensemble of three dimensional (3D) deep neural network (DNN) based model, namely: pre-trained EfficientNetB0, BiGRU-based SEResNext101, and the proposed LungNet. The ensemble model performs binary classification and regression tasks to accurately classify the benign and malignant pulmonary nodules. This study also explores the attribute importance and proposes a domain knowledge-based regularization technique. The proposed model is evaluated on the public benchmark LIDC-IDRI dataset. Through a comparative study, it was shown that when coefficients generated by the random forest (RF) are used in the loss function, the proposed ensemble model offers a better prediction capability of the accuracy of 96.4% compared to the state-of-the-art methods. In addition, the receiver operating characteristic curves show that the proposed ensemble model has better performance than the base learners. Thus, the proposed CAD-based model can efficiently detect malignant pulmonary nodules.
VenugopalVKVaidhyaKMurugavelM, et al. Unboxing AI - radiological insights into a deep neural network for lung nodule characterization. Acad Radiol2020; 27(1): 88–95.
3.
GaoNTianSLiX, et al. Three-dimensional texture feature analysis of pulmonary nodules in CT images: lung cancer predictive models based on support vector machine classifier. J Digit Imaging2020; 33(2): 414–422.
4.
ZhangBQiSMonkamP, et al. Ensemble learners of multiple deep CNNs for pulmonary nodules classification using CT images. IEEE Access2019; 7: 110358–110371.
5.
HeWLiBLiaoR, et al. An ISHAP-based interpretation-model-guided classification method for malignant pulmonary nodule. Knowl Based Syst2022; 237: 107778.
6.
AbdouMA. Literature review: Efficient deep neural networks techniques for medical image analysis. Neural Comput Appl2022; 34: 5791–5812.
7.
ShiFChenBCaoQ, et al. Semi-supervised deep transfer learning for benign-malignant diagnosis of pulmonary nodules in chest CT images. IEEE Trans Med Imaging2022; 41(4): 771–781.
8.
XieYZhangJXiaY. Semi-supervised adversarial model for benign-malignant lung nodule classification on chest CT. Med Image Anal2019; 57: 237–248.
9.
ZhengSGuoJCuiX, et al. Automatic pulmonary nodule detection in CT scans using convolutional neural networks based on maximum intensity projection. IEEE Trans Med Imaging2020; 39(3): 797–805.
10.
OzdemirORussellRLBerlinAA. A 3D probabilistic deep learning system for detection and diagnosis of lung cancer using low-dose CT scans. IEEE Trans Med Imaging2020; 39(5): 1419–1429.
11.
MasoodAYangPShengB, et al. Cloud-based automated clinical decision support system for detection and diagnosis of lung cancer in chest CT. IEEE J Transl Eng Health Med2020; 8: 4300113.
12.
CaoHLiuHSongE, et al. A two-stage convolutional neural networks for lung nodule detection. IEEE J Biomed Health Inform2020; 24(7): 2006–2015.
13.
HalderAChatterjeeSDeyD. Adaptive morphology aided 2-pathway convolutional neural network for lung nodule classification. Biomed Signal Process Control2022; 72: 103347.
14.
Al-ShabiMShakKTanM. 3D axial-attention for lung nodule classification. Int J Comput Assist Radiol Surg2021; 16(8): 1319–1324.
15.
TongCLiangBSuQ, et al. Pulmonary nodule classification based on heterogeneous features learning. IEEE J Sel Areas Commun2021; 39(2): 574–581.
16.
ZhangCXuSLiZ. PanelNet: A Novel Deep Neural Network for Predicting Collective Diagnostic Ratings by a Panel of Radiologists for Pulmonary Nodules. In: Proceedings of the 28th ACM International Conference on Multimedia, New York, United States, Association for Computing Machinery, 2020, pp.2290–2298.
17.
ShenSHanSXAberleDR, et al. An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification. Expert Syst Appl2019; 128: 84–95.
18.
FerreiraJROliveiraMCde Azevedo-MarquesPM. Characterization of pulmonary nodules based on features of margin sharpness and texture. J Digit Imaging2018; 31(4): 451–463.
19.
MarquesSSchiavoFFerreiraCA, et al. A multi-task CNN approach for lung nodule malignancy classification and characterization. Expert Syst Appl2021; 184: 115469.
20.
ZhaoJZhangCLiD, et al. Combining multi-scale feature fusion with multi-attribute grading, a CNN model for benign and malignant classification of pulmonary nodules. J Digit Imaging2020; 33(4): 869–878.
21.
KayaACanAB. A weighted rule based method for predicting malignancy of pulmonary nodules by nodule characteristics. J Biomed Inform2015; 56: 69–79.
22.
WangWCharkbortyG. Automatic prognosis of lung cancer using heterogeneous deep learning models for nodule detection and eliciting its morphological features. Appl Intell2021; 51(4): 2471–2484.
23.
LiuLDouQChenH, et al. Multi-task deep model with margin ranking loss for lung nodule analysis. IEEE Trans Med Imaging2020; 39(3): 718–728.
24.
FuXBiLKumarA, et al. An attention-enhanced cross-task network to analyse lung nodule attributes in CT images. Pattern Recognit2022; 126: 108576.
25.
ArmatoSGMcLennanGBidautL, et al. The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Med Phys2011; 38(2): 915–931.
26.
McNitt-GrayMFArmatoSg3rdMeyerCR, et al. The Lung Image Database Consortium (LIDC) data collection process for nodule detection and annotation. Acad Radiol2007; 14(12): 1464–1474.
27.
TanMLeQ. Efficientnet: Rethinking model scaling for convolutional neural networks. In: International conference on machine learning, Long Beach, California, PMLR, 2019, pp.6105–6114.
28.
HuJShenLSunG. Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, IEEE, 2018, pp.7132–7141.
29.
XieSGirshickRDollärP, et al. Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, IEEE, 2017, pp.1492–1500.
30.
DinaMINadaMEAmanyMS. Deep-chest: multi-classification deep learning model for diagnosing COVID-19, pneumonia, and lung cancer chest diseases. Comput Biol Med2021; 132: 104348.
31.
HancockMCMagnanJF. Lung nodule malignancy classification using only radiologist-quantified image features as inputs to statistical learning algorithms: probing the Lung Image Database Consortium dataset with two statistical learning methods. J Med Imaging2016; 3(4): 044504.
32.
FriedmanJHastieTTibshiraniR. Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). Ann Stat2000; 28(2): 337–407.
