Multi-view Convolutional Neural Network for lung nodule false positive reduction

被引:35
|
作者
El-Regaily, Salsabil Amin [1 ]
Salem, Mohammed Abdel Megeed [2 ,3 ]
Aziz, Mohamed Hassan Abdel [1 ]
Roushdy, Mohamed Ismail [4 ]
机构
[1] Ain Shams Univ, Basic Sci Dept, Fac Comp & Informat Sci, Cairo, Egypt
[2] Ain Shams Univ, Fac Comp & Informat Sci, Sci Comp Dept, Cairo, Egypt
[3] German Univ Cairo GUC, Fac Media Engn & Technol, Cairo, Egypt
[4] Future Univ Egypt, Fac Comp & Informat Technol, New Cairo, Egypt
关键词
Lung nodules; Computer Aided Detection; Convolutional Neural Networks; Computed tomography; IMAGE DATABASE CONSORTIUM; CT; LIDC; CLASSIFICATION; DIAGNOSIS;
D O I
10.1016/j.eswa.2019.113017
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Background and objective: Computer-Aided Detection (CAD) systems save radiologists time and provide a second opinion in detecting lung cancer by performing automated analysis of the scans. False positive reduction is one of the most crucial components of these systems that play a great role in the early diagnosis and treatment process. The objective of this paper is to efficiently handle this problem by detecting nodules and separating them from a large number of false positive candidates. Methods: The proposed algorithm segments lungs and nodules through a combination of 2D and 3D region growing, thresholding and morphological operations. Vessels and most of the internal lung structure have a tabular shape that differs from the compact rounded shape of nodules, therefore they are eliminated by building and thresholding a3D depth map, to produce the initial candidates. To reduce the number of false positives, a rule-based classifier is used to eliminate the obvious non-nodules, followed by a multi-view Convolutional Neural Network. The convolutional network is built specifically to handle the provided inputs and is customized to provide the best possible outputs without the extra computational complexity that is required when compared to a 3D network. 650 cases from the LIDC dataset are used to train and test the network. For each candidate, the axial, coronal and sagittal views are extracted and fed to the three network streams. Results: The proposed algorithm achieved a high detection sensitivity of 85.256%, a specificity of 90.658% and an accuracy of 89.895%. Experimental results indicate that the proposed algorithm outperforms most of the other algorithms in terms of accuracy and sensitivity. The proposed solution achieves a good trade-off between efficiency and effectivity and saves much computation time. Conclusion: The work shows that the proposed multi-view 2D network is a simple, yet effective algorithm for the false positive reduction problem. It can detect nodules that are isolated, linked to a vessel or attached to the lung wall. The network can be improved to detect ground glass nodules in the future. (C) 2019 Elsevier Ltd. All rights reserved.
引用
收藏
页数:10
相关论文
共 50 条
  • [1] False positive reduction in lymph node detection by using Convolutional Neural Network with Multi-view Input
    Wang, Jiaqi
    Xu, Li
    MIPPR 2019: PARALLEL PROCESSING OF IMAGES AND OPTIMIZATION TECHNIQUES; AND MEDICAL IMAGING, 2020, 11431
  • [2] A Multi-view Deep Convolutional Neural Network for Reduction of False Positive Findings in Breast Cancer Screening
    Derbel, Nouha
    Tmar, Hedi
    Mahfoudhi, Adel
    2020 5TH INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES FOR SIGNAL AND IMAGE PROCESSING (ATSIP'2020), 2020,
  • [3] Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks
    Setio, Arnaud Arindra Adiyoso
    Ciompi, Francesco
    Litjens, Geert
    Gerke, Paul
    Jacobs, Colin
    van Riel, Sarah J.
    Wille, Mathilde Marie Winkler
    Naqibullah, Matiullah
    Sanchez, Clara I.
    van Ginneken, Bram
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2016, 35 (05) : 1160 - 1169
  • [4] A Multi-view Deep Convolutional Neural Networks for Lung Nodule Segmentation
    Wang, Shuo
    Zhou, Mu
    Gevaert, Olivier
    Tang, Zhenchao
    Dong, Di
    Liu, Zhenyu
    Tian, Jie
    2017 39TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2017, : 1752 - 1755
  • [5] TUMORNET: LUNG NODULE CHARACTERIZATION USING MULTI-VIEW CONVOLUTIONAL NEURAL NETWORK WITH GAUSSIAN PROCESS
    Hussein, Sarfaraz
    Gillies, Robert
    Cao, Kunlin
    Song, Qi
    Bagci, Ulas
    2017 IEEE 14TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2017), 2017, : 1007 - 1010
  • [6] Convolutional neural network-based PSO for lung nodule false positive reduction on CT images
    Franca da Silva, Giovanni Lucca
    Azevedo Valente, Thales Levi
    Silva, Aristofanes Correa
    de Paiva, Anselmo Cardoso
    Gattass, Marcelo
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2018, 162 : 109 - 118
  • [7] Multi-view Convolutional Recurrent Neural Networks for Lung Cancer Nodule Identification
    Abid, Mian Muhammad Naeem
    Zia, Tehseen
    Ghafoor, Mubeen
    Windridge, David
    NEUROCOMPUTING, 2021, 453 : 299 - 311
  • [8] Lymph node detection in MR Lymphography: false positive reduction using multi-view convolutional neural networks
    Debats, Oscar A.
    Litjens, Geert J. S.
    Huisman, Henkjan J.
    PEERJ, 2019, 7
  • [9] 3D multi-view squeeze-and-excitation convolutional neural network for lung nodule classification
    Yang, Yang
    Li, Xiaoqin
    Fu, Jipeng
    Han, Zhenbo
    Gao, Bin
    MEDICAL PHYSICS, 2023, 50 (03) : 1905 - 1916
  • [10] 3D multi-view convolutional neural networks for lung nodule classification
    Kang, Guixia
    Liu, Kui
    Hou, Beibei
    Zhang, Ningbo
    PLOS ONE, 2017, 12 (11):