skip to main content
10.1145/3107411.3108174acmconferencesArticle/Chapter ViewAbstractPublication PagesbcbConference Proceedingsconference-collections
research-article

Ensemble Convolution Neural Network with a Simple Voting Method for Lung Tumor Detection

Published: 20 August 2017 Publication History

Abstract

Lung cancer is the leading cause of cancer deaths in the United States. Approximately 225,000 people each year are diagnosed with lung cancer in the US alone. Early detection is a crucial part of giving patients the best chance of recovery. Current methods suffer from high false positive rates. Deep learning gives us an opportunity to increase the accuracy of the automated initial diagnosis. Here we present an ensemble of Convolution Neural Networks (CNN) that is built from two individual CNNs: one uses unprocessed images and the other images smoothed with a Gaussian filter. The ensemble method decreases the number of false positives in the automated labeling of the scans using a voting system. If both CNNs have the same output, a negative (0) or a positive (1) cancer prediction, the voting system outputs that prediction. However, if the CNNs do not have the same output then the voting system outputs a negative (0) prediction. Our ensemble method has an average accuracy of 85.91% and false positive rate of 0.50%. This is a decrease in the false positive rate of approximately 99.47% from current methods. This is a great improvement over the currently used methods and shows that our method has promise as an initial diagnosis technique.

References

[1]
Christopher M Bishop. 2006. Pattern recognition.
[2]
Centers for Disease Control and Prevention 2013 (accessed April, 2017). 1999 to 2013 Cancer Incidence and Mortality Data. https://nccd.cdc.gov/uscs/
[3]
Francesco Ciompi, Kaman Chung, Sarah J. van Riel, Arnaud Arindra Adiyoso Setio, Paul K. Gerke, Colin Jacobs, Ernst Th. Scholten, Cornelia Schaefer-Prokop, Mathilde M. W. Wille, Alfonso Marchiano, Ugo Pastorino, Mathias Prokop, and Bram van Ginneken. 2016. Towards automatic pulmonary nodule management in lung cancer screening with deep learning. CoRR Vol. abs/1610.09157 (October 2016). http://arxiv.org/abs/1610.09157
[4]
Jennifer M Croswell, David F Ransohoff, and Barnett S Kramer 2010. Principles of cancer screening: lessons from history and study design issues Seminars in oncology, Vol. Vol. 37. Elsevier, 202--215.
[5]
Howard Demuth and Mark Beale 2009. Matlab neural network toolbox user's guide version 6. The MathWorks Inc. (2009).
[6]
Debapriya Maji, Anirban Santara, Pabitra Mitra, and Debdoot Sheet 2016. Ensemble of Deep Convolutional Neural Networks for Learning to Detect Retinal Vessels in Fundus Images. CoRR Vol. 1603.04833 (March 2016). {arxiv}arXiv:1603.04833v1
[7]
Mathworks. 2016. Matlab 2016b. Mathworks Inc., Natick, MA.
[8]
Virginia A Moyer. 2014. Screening for lung cancer: US Preventive Services Task Force recommendation statement. Annals of internal medicine Vol. 160, 5 (2014), 330--338.
[9]
David Martin Powers. 2011. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. (December 2011).
[10]
M Patricia Rivera, Atul C Mehta, and Momen M Wahidi. 2013. Establishing the diagnosis of lung cancer: Diagnosis and management of lung cancer: American College of Chest Physicians evidence-based clinical practice guidelines. CHEST Journal, Vol. 143, 5_suppl (2013), e142S--e165S.
[11]
Holger R Roth, Le Lu, Jiamin Liu, Jianhua Yao, Ari Seff, Kevin Cherry, Lauren Kim, and Ronald M Summers. 2016. Improving Computer-Aided Detection Using Convolutional Neural Networks and Random View Aggregation. IEEE transactions on medical imaging Vol. 35, 5 (May 2016), 1170--1181.
[12]
Divakar Sharma, Thomas G Newman, and Wilbert S Aronow. 2015. Lung cancer screening: history, current perspectives, and future directions. Arch Med Sci, Vol. 11, 5 (May 2015), 1033--1043.
[13]
National Lung Screening Trial Research Team and others 2011. Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med, Vol. 2011, 365 (August 2011), 395--409.
[14]
He Yang, Hengyong Yu, and Ge Wang 2016. Deep Learning for the Classification of Lung Nodules. CoRR Vol. arXiv:1611.06651 (November 2016). https://arxiv.org/abs/1611.06651

Cited By

View all
  • (2023)Diplin: A Disease Risk Prediction Model Based on EfficientNetV2 and Transfer Learning Applied to Nursing HomesElectronics10.3390/electronics1212258112:12(2581)Online publication date: 7-Jun-2023
  • (2019)Lung Cancer Detection with 3D Ensemble Convolution Neural NetworkProceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence10.1145/3374587.3374588(64-70)Online publication date: 6-Dec-2019

Index Terms

  1. Ensemble Convolution Neural Network with a Simple Voting Method for Lung Tumor Detection

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Conferences
      ACM-BCB '17: Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health Informatics
      August 2017
      800 pages
      ISBN:9781450347228
      DOI:10.1145/3107411
      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]

      Sponsors

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 20 August 2017

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. automated diagnoses
      2. cancer
      3. convolutional neural networks
      4. deep learning
      5. false positive rate
      6. lung tumors

      Qualifiers

      • Research-article

      Conference

      BCB '17
      Sponsor:

      Acceptance Rates

      ACM-BCB '17 Paper Acceptance Rate 42 of 132 submissions, 32%;
      Overall Acceptance Rate 254 of 885 submissions, 29%

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)3
      • Downloads (Last 6 weeks)1
      Reflects downloads up to 15 Feb 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2023)Diplin: A Disease Risk Prediction Model Based on EfficientNetV2 and Transfer Learning Applied to Nursing HomesElectronics10.3390/electronics1212258112:12(2581)Online publication date: 7-Jun-2023
      • (2019)Lung Cancer Detection with 3D Ensemble Convolution Neural NetworkProceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence10.1145/3374587.3374588(64-70)Online publication date: 6-Dec-2019

      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