[an error occurred while processing this directive]

Advanced Ultrasound in Diagnosis and Therapy ›› 2023, Vol. 7 ›› Issue (3): 272-278.doi: 10.37015/AUDT.2022.220018

• • 上一篇    下一篇

  

  • 收稿日期:2022-04-29 修回日期:2023-07-01 接受日期:2022-08-05 出版日期:2023-09-30 发布日期:2023-10-09

Lung Nodule Classification in CT Images Using Improved DenseNet

Xiuping Men, PhDa,b,*(), Vladimir Y. Mariano, PhDb, Aihua Duan, PhDa,b, Xiaoyan Shi, PhDa,b   

  1. a School of Management Science and Engineering, Anhui University of Finance and Economics, Bengbu, Anhui, China
    b School of Computing and Information Technologies National University, Manila, Philippines
  • Received:2022-04-29 Revised:2023-07-01 Accepted:2022-08-05 Online:2023-09-30 Published:2023-10-09
  • Contact: Xiuping Men, PhD E-mail:menx@students.national-u.edu.ph

RichHTML

3

PDF (PC)

236

PDF (Mobile)

1

Abstract:

Objective: Computed tomography (CT) imaging of the chest is an effective diagnostic tool assisting physicians in making a diagnosis. This study aimed to propose a new convolutional neural network for classifying the lung nodules of the patient through chest CT scan data to determine whether the patient has related disease genes.
Methods: We proposed a DenseNet-based neural network structure that uses multi-scale convolutional kernels to obtain features of different receptive fields, which are fed into a DenseNet containing four improved DenseBlocks, followed by a classification module to obtain the model output, i.e., whether a lung nodule contains a cancer gene. We conducted classification experiments on a CT scan dataset containing 465 training samples and 117 test samples.
Results: The results showed that DenseNet was better than ResNet in terms of classification, whereas ResNet was better than VGG, which was consistent with the findings of previous studies. However, because these models were more complex, they suffered from overfitting problems. Among all of the models used in this paper, our proposed network achieved the best results in terms of accuracy, F1 score, and sensitivity without an over fitting. The accuracy was 72.0%, sensitivity was 78%, and F1 score was 68%.
Conclusion: The proposed DenseNet neural network can improve and assist medical imaging diagnostic physicians in the initial diagnosis of lung nodules.

Key words: Computed tomography (CT) imaging, Lung nodule classification

"

"

"

"

Items ACC F1 SE SP
VGG16 0.46 0.45 0.45 0.52
VGG16_AUG 0.4 0.39 0.30 0.61
ResNet18 0.57 0.55 0.57 0.57
ResNet18_AUG 0.58 0.55 0.55 0.60
ResNet34 0.62 0.59 0.59 0.65
ResNet34_AUG 0.56 0.49 0.44 0.67
ResNet50 0.58 0.41 0.31 0.83
ResNet50_AUG 0.57 0.53 0.52 0.62
DenseNet121 0.70 0.65 0.61 0.78
DenseNet121_AUG 0.66 0.62 0.58 0.67
DenseNet161 0.68 0.64 0.67 0.65
DenseNet161_AUG 0.60 0.58 0.59 0.60
DenseNet169 0.57 0.56 0.58 0.59
DenseNet169_AUG 0.54 0.47 0.48 0.52
Improved DenseNet 0.72 0.68 0.78 0.65
Improved DenseNet _AUG 0.67 0.57 0.71 0.59

"

"

[1] Facts Figures American Cancer Society, Amer. Cancer Soc., Atlanta, GA, USA, 2021.
[2] Winer-Muram HT. The solitary pulmonary nodule. Radiology 2006; 239:34-49.
doi: 10.1148/radiol.2391050343 pmid: 16567482
[3] Niki N, Kawata Y, Kubo M. ACADsystem for lung cancer based on CT image. In: International Congress Series. Elsevier 2001; 1230: 631-638.
[4] Abe Y, Hanai K, Nakano M, Ohkubo Y, Hasizume T, Kakizaki T, et al. A computer-aided diagnosis (CAD) system in lung cancer screening with computed tomography. Anticancer Res 2005; 25:483-488.
pmid: 15816616
[5] El-Baz A, Beache GM, Gimel’farb G, Suzuki K, Okada K, Elnakib A, et al. Computer-aided diagnosis systems for lung cancer: challenges and methodologies. Int J Biomed Imaging 2013; 2013:46.
[6] Awan R, Koohbanani NA, Shaban M, Lisowska A, Rajpoot N, et al. Context-aware learning using transferable features for classification of breast cancer histology images. Springer, Cham 2018:788-795.
[7] Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 2016; 316:2402-2410.
doi: 10.1001/jama.2016.17216 pmid: 27898976
[8] Farooq A, Anwar SM, Awais M, Rehman S. A deep CNN based multi-class classification of Alzheimer's disease using MRI. IEEE 2017:1-6.
[9] Islam MZ, Islam MM, Asraf A. A combined deep CNN-LSTM network for the detection of novel coronavirus (COVID-19) using X-ray images. Inform Med Unlocked 2020; 20:100412.
doi: 10.1016/j.imu.2020.100412
[10] Shanthi T, Sabeenian R S. Modified AlexNet architecture for classification of diabetic retinopathy images. Computers & Electrical Engineering 2019; 76:56-64.
[11] Li X, Shen L, Xie X, Huang S, Xie Z, Hong X, et al. Multi-resolution convolutional networks for chest X-ray radiograph based lung nodule detection. Artificial intelligence in medicine 2020; 103:101744.
doi: 10.1016/j.artmed.2019.101744
[12] Labati RD, Muñoz E, Piuri V, Sassi R, Scotti F. Deep-ECG: Convolutional neural networks for ECG biometric recognition. Pattern Recognition Letters 2019; 126:78-85.
doi: 10.1016/j.patrec.2018.03.028
[13] Ma X, Dai Z, He Z, Ma J, Wang Y, Wang Y. Learning Traffic as Images: A deep convolutional neural network for large-scale transportation network speed prediction. Sensors (Basel) 201; 17:818.
doi: 10.3390/s17040818
[14] Huang S, Li F, Chen Q. Computational tomography image classification algorithm based on improved deep residual network. Acta Optics 2020; 456:56-64.
[15] Fulton LV, Dolezel D, Harrop J, Yan Y, Fulton CP.Classification of Alzheimer's disease with and without imagery using gradient boosted machines and resnet-50. Brain Sci 2019; 9:212.
doi: 10.3390/brainsci9090212
[16] Dey R, Lu Z, Hong Y.Diagnostic classification of lung nodules using 3D neural networks. IEEE 2018:774-778.
[17] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv 2014; 1409.1556.
[18] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2016:770-778.
[19] Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2017:4700-4708.
[20] Zhang K, Guo Y, Wang X, Yuan J, Ding Q. Multiple features reweight densenet for image classification. IEEE Access 2019; 7:9872-9880.
doi: 10.1109/ACCESS.2018.2890127
[21] Iandola F, Moskewicz M, Karayev S, Girshick R, Darrell T, Keutzer K. Densenet: Implementing efficient convnet descriptor pyramids. arXiv preprint arXiv 2014; 1404.1869.
[22] Tong W, Chen W, Han W, Li X, Wang L. Channel-attention-based DenseNet network for remote sensing image scene classification. IEEE J Sel Top Appl Earth Obs Remote Sens 2020; 13:4121-4132.
doi: 10.1109/JSTARS.4609443
[23] Chen X, Williams BM, Vallabhaneni SR, Czanner G, Williams R, Zheng Y. (2019). Learning active contour models for medical image segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019:11632-11640
[24] Xu X, Lin J, Tao Y, Wang X. An improved DenseNet method based on transfer learning for fundus medical images. IEEE 2018:137-140.
[25] Zunair H, Rahman A, Mohammed N, Cohen JP.Uniformizing techniques to process CT scans with 3D CNNs for tuberculosis prediction. Springer, Cham 2020:156-168.
[26] Lee Y, Hwang J, Lee S, Bae Y, Park J.An energy and GPU-computation efficient backbone network for real-time object detection. 2019.
No related articles found!
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
[an error occurred while processing this directive]