A Two-Stage Framework for Automated Malignant Pulmonary Nodule Detection in CT Scans

被引:29
作者
EL-Bana, Shimaa [1 ]
Al-Kabbany, Ahmad [2 ,3 ,4 ]
Sharkas, Maha [3 ]
机构
[1] Alexandria Higher Inst Engn & Technol, Alexandria 21311, Egypt
[2] Arab Acad Sci Technol & Maritime Transport, Intelligent Syst Lab, Alexandria 21937, Egypt
[3] Arab Acad Sci Technol & Maritime Transport, Dept Elect & Commun Engn, Alexandria 21937, Egypt
[4] VRapeutic, Dept Res & Dev, Cairo 11728, Egypt
关键词
CAD system; lung cancer; pulmonary nodules; DeepLab-V3; CNN; transfer learning; tensorflow;
D O I
10.3390/diagnostics10030131
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
This research is concerned with malignant pulmonary nodule detection (PND) in low-dose CT scans. Due to its crucial role in the early diagnosis of lung cancer, PND has considerable potential in improving the survival rate of patients. We propose a two-stage framework that exploits the ever-growing advances in deep neural network models, and that is comprised of a semantic segmentation stage followed by localization and classification. We employ the recently published DeepLab model for semantic segmentation, and we show that it significantly improves the accuracy of nodule detection compared to the classical U-Net model and its most recent variants. Using the widely adopted Lung Nodule Analysis dataset (LUNA16), we evaluate the performance of the semantic segmentation stage by adopting two network backbones, namely, MobileNet-V2 and Xception. We present the impact of various model training parameters and the computational time on the detection accuracy, featuring a 79.1% mean intersection-over-union (mIoU) and an 88.34% dice coefficient. This represents a mIoU increase of 60% and a dice coefficient increase of 30% compared to U-Net. The second stage involves feeding the output of the DeepLab-based semantic segmentation to a localization-then-classification stage. The second stage is realized using Faster RCNN and SSD, with an Inception-V2 as a backbone. On LUNA16, the two-stage framework attained a sensitivity of 96.4%, outperforming other recent models in the literature, including deep models. Finally, we show that adopting a transfer learning approach, particularly, the DeepLab model weights of the first stage of the framework, to infer binary (malignant-benign) labels on the Kaggle dataset for pulmonary nodules achieves a classification accuracy of 95.66%, which represents approximately 4% improvement over the recent literature.
引用
收藏
页数:19
相关论文
共 42 条
  • [1] Abadi M., 2015, TENSORFLOW LARGE SCA
  • [2] Abbas S. M., 2018, PhD thesis, P1
  • [3] The Lung Image Database Consortium, (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT Scans
    Armato, Samuel G., III
    McLennan, Geoffrey
    Bidaut, Luc
    McNitt-Gray, Michael F.
    Meyer, Charles R.
    Reeves, Anthony P.
    Zhao, Binsheng
    Aberle, Denise R.
    Henschke, Claudia I.
    Hoffman, Eric A.
    Kazerooni, Ella A.
    MacMahon, Heber
    van Beek, Edwin J. R.
    Yankelevitz, David
    Biancardi, Alberto M.
    Bland, Peyton H.
    Brown, Matthew S.
    Engelmann, Roger M.
    Laderach, Gary E.
    Max, Daniel
    Pais, Richard C.
    Qing, David P-Y
    Roberts, Rachael Y.
    Smith, Amanda R.
    Starkey, Adam
    Batra, Poonam
    Caligiuri, Philip
    Farooqi, Ali
    Gladish, Gregory W.
    Jude, C. Matilda
    Munden, Reginald F.
    Petkovska, Iva
    Quint, Leslie E.
    Schwartz, Lawrence H.
    Sundaram, Baskaran
    Dodd, Lori E.
    Fenimore, Charles
    Gur, David
    Petrick, Nicholas
    Freymann, John
    Kirby, Justin
    Hughes, Brian
    Casteele, Alessi Vande
    Gupte, Sangeeta
    Sallam, Maha
    Heath, Michael D.
    Kuhn, Michael H.
    Dharaiya, Ekta
    Burns, Richard
    Fryd, David S.
    [J]. MEDICAL PHYSICS, 2011, 38 (02) : 915 - 931
  • [4] SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
    Badrinarayanan, Vijay
    Kendall, Alex
    Cipolla, Roberto
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (12) : 2481 - 2495
  • [5] Fully Convolutional Neural Network with Augmented Atrous Spatial Pyramid Pool and Fully Connected Fusion Path for High Resolution Remote Sensing Image Segmentation
    Chen, Guangsheng
    Li, Chao
    Wei, Wei
    Jing, Weipeng
    Wozniak, Marcin
    Blazauskas, Tomas
    Damasevicius, Robertas
    [J]. APPLIED SCIENCES-BASEL, 2019, 9 (09):
  • [6] CHEN L. C., 2015, 3 INT C LEARN REPR I, DOI [10.48550/arXiv.1412.7062, DOI 10.48550/ARXIV.1412.7062]
  • [7] DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
    Chen, Liang-Chieh
    Papandreou, George
    Kokkinos, Iasonas
    Murphy, Kevin
    Yuille, Alan L.
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) : 834 - 848
  • [8] Chen LB, 2017, IEEE INT SYMP NANO, P1, DOI 10.1109/NANOARCH.2017.8053709
  • [9] Xception: Deep Learning with Depthwise Separable Convolutions
    Chollet, Francois
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 1800 - 1807
  • [10] Chon A., 2017, Deep convolutional neural networks for lung cancer detection