skip to main content
10.1145/3403782.3403808acmotherconferencesArticle/Chapter ViewAbstractPublication PagesbibeConference Proceedingsconference-collections
research-article

A Simple Residual Network for Lung Nodule Classification

Published: 21 July 2020 Publication History

Abstract

Purpose: Lung nodules have very diverse shapes, sizes, densities and textures, which makes predicting the malignancy of lung nodules a very challenging problem. In this paper, we propose a simple global-local residual network to classify pulmonary nodules as benign or malignant.
Methods: Different from previous models, we suppose that global features effect lung nodule classification tasks before local features logically. Thus, we propose to use Self-Attention mechanism to detect global features firstly. After that, inceptionlike module is introduced to extract multi-scale local features. The detected local features would be treated as complementary part of global features with residual connection.
Results: We trained and validated the proposed network on the public and comprehensive LIDC-IDRI dataset. The comparison with five state-of-the-art models and five self-designed methods shows that, the proposed GLR network achieved state-of-the-art results with an AUC of 96.07%.
Conclusions: On the basis of the present results, the GLR network works well on predicting the malignancy of lung nodules.

References

[1]
Leigh J. "Global, Regional, and National Cancer Incidence, Mortality, Years of Life Lost, Years Lived with Disability, and Disability-Adjusted Life Years for 29 Cancer Groups, 1990 to 2017". JAMA Oncology.
[2]
Siegel R L, Miller K D, and Jemal A (2016). Cancer statistics, [J]. CA Cancer Journal. Clin., 2016, 66, 7--30.
[3]
American Cancer Society (2016). "Cancer Facts & Figures 2016". American Cancer Society, Atlanta.
[4]
Al-Shabi M, Lee H K, and Tan M. Gated-Dilated Networks for Lung Nodule Classification in CT scans[J]. 2019.
[5]
Cadrin-Ch A. "Lung Cancer: Bridging the Gap Between Medical Imaging and Data Science". [Online]: https://medium.com/@alexandrecadrin/lung-cancer-bridging-the-gapbetween-medical-imaging-and-data-science-a92b0bb08fda
[6]
Monkam P, Qi S L, and Ma H, et al. (2019). Detection and Classification of Pulmonary Nodules Using Convolutional Neural Networks: A Survey[J]. IEEE ACCESS, 7, 78075--78091.
[7]
Horeweg N, Rosmalen J, and Heuvelmans M A, et al. (2014). Lung cancer probability in patients with CT-detected pulmonary nodules: a prespecified analysis of data from the NELSON trial of low-dose CT screening[J]. Lancet Oncol. 15(12), 1332--41.
[8]
Erasmus J J, Connolly J E, and McAdams H P, et al. (2000). Solitary pulmonary nodules: Part I. Morphologic evaluation for differentiation of benign and malignant lesions. Radiographics. 20(1), 43--58.
[9]
Lindell R M, Hartman T E, and Swensen S J, et al. (2007). Five-year lung cancer screening experience: CT appearance, growth rate, location, and histologic features of 61 lung cancers. Radiology. 242(2), 555--62.
[10]
Zhang H, Goodfellow I, and Metaxas D, et al. (2018). Self-Attention Generative Adversarial Networks. arXiv: 1805.08318.
[11]
Al-Shabi M, Lan B L, and Chan W Y, et al. (2019). Lung nodule classification using deep Local-Global networks[J]. International Journal of Computer Assisted Radiology and Surgery.
[12]
Armato S G, McLennan G, and Bidaut L, et al. (2011). 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, 38(2), 915--931.
[13]
Kingma D P, Ba J. Adam: A method for stochastic optimization[J]. Computer Science, 2014.
[14]
Metz C E, Herman B A, and Roe C A. (1998). Statistical Comparison of Two ROC-curve Estimates Obtained from Partially-paired Datasets[J]. Medical Decision Making, 18(1), 110--121.
[15]
Liu Y, Hao P, and Zhang P, et al. (2018). Dense convolutional binary-tree networks for lung nodule classification[J]. IEEE Access, 6, 49080--49088.
[16]
Shen S, Han S X, and Aberle D R, et al. (2018). An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification[J]. Expert Systems with Applications, 128, 84--95.
[17]
Zhang B H, Qi S L, and Monkam P, et al. (2019). Ensemble Learners of Multiple Deep CNNs for Pulmonary Nodules Classification Using CT Images[J]. IEEE Access, 7, 110358--110371.

Cited By

View all
  • (2022)Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open ChallengesJournal of Personalized Medicine10.3390/jpm1203048012:3(480)Online publication date: 16-Mar-2022
  • (2021)A new Multi-scale Dilated deep ResNet model for Classification of Lung Nodules in CT imagesProceedings of the 7th International Conference on Communication and Information Processing10.1145/3507971.3507988(89-95)Online publication date: 16-Dec-2021

Index Terms

  1. A Simple Residual Network for Lung Nodule Classification

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    BIBE2020: Proceedings of the Fourth International Conference on Biological Information and Biomedical Engineering
    July 2020
    219 pages
    ISBN:9781450377096
    DOI:10.1145/3403782
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    In-Cooperation

    • ASciE: Association for Science and Engineering

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 21 July 2020

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Convolutional neural network
    2. Global-local features
    3. Lung nodules classification
    4. Residual connection
    5. Self-attention mechanism

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    BIBE2020

    Acceptance Rates

    BIBE2020 Paper Acceptance Rate 36 of 116 submissions, 31%;
    Overall Acceptance Rate 36 of 116 submissions, 31%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)3
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 16 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2022)Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open ChallengesJournal of Personalized Medicine10.3390/jpm1203048012:3(480)Online publication date: 16-Mar-2022
    • (2021)A new Multi-scale Dilated deep ResNet model for Classification of Lung Nodules in CT imagesProceedings of the 7th International Conference on Communication and Information Processing10.1145/3507971.3507988(89-95)Online publication date: 16-Dec-2021

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media