Advertisement

Development of Deep Learning-based Automatic Scan Range Setting Model for Lung Cancer Screening Low-dose CT Imaging

Published:February 09, 2022DOI:https://doi.org/10.1016/j.acra.2021.12.001

      Rationale and Objectives

      To develop an automatic setting of a deep learning-based system for detecting low-dose computed tomography (CT) lung cancer screening scan range and compare its efficiency with the radiographer's performance.

      Materials and Methods

      This retrospective study was performed using 1984 lung cancer screening low-dose CT scans obtained between November 2019 and May 2020. Among 1984 CT scans, 600 CT scans were considered suitable for an observational study to explore the relationship between the scout landmarks and the actual lung boundaries. Further, 1144 CT scans data set was used for the development of a deep learning-based algorithm. This data set was split into an 8:2 ratio divided into a training set (80%, n = 915) and a validation set (20%, n = 229). The performance of the deep learning algorithm was evaluated in the test set (n = 240) using actual lung boundaries and radiographers' scan ranges.

      Results

      The mean differences between the upper and lower boundaries of the deep learning-based algorithm and the actual lung boundaries were 4.72 ± 3.15 mm and 16.50 ± 14.06 mm, respectively. The accuracy and over-scanning of the scan ranges generated by the system were 97.08% (233/240) and 0% (0/240) for the upper boundary, and 96.25% (231/240) and 29.58% (71/240) for the lower boundary.

      Conclusion

      The developed deep learning-based algorithm system can effectively predict lung cancer screening low-dose CT scan range with high accuracy using only the frontal scout.

      Key Words

      Abbreviations:

      CNN (Convolutional Neural Networks), CT (computed tomography), Dl (the distance between the lowermost costophrenic angle and actual lowermost lung boundaries), Du (the distance between the uppermost pulmonary apex and actual uppermost lung boundaries), LCPA (left costophrenic angle), LDCT (low-dose computed tomography), LPA (left pulmonary apex), PACS (picture archiving and communication system), PCK (Percentage of Correct Key points), RCPA (right costophrenic angle), RPA (right pulmonary apex)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Academic Radiology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Sung H
        • Ferlay J
        • Siegel RL
        • et al.
        Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries.
        CA Cancer J Clin. 2021; 71: 209-249
        • Aberle DR
        • Adams AM
        • Berg CD
        • et al.
        Reduced lung-cancer mortality with low-dose computed tomographic screening.
        N Engl J Med. 2011; 365: 395-409
        • Wu FZ
        • Huang YL
        • Wu YJ
        • et al.
        Prognostic effect of implementation of the mass low-dose computed tomography lung cancer screening program: a hospital-based cohort study.
        Eur J Cancer Prev. 2020; 29: 445-451
        • Wu FZ
        • Huang YL
        • Wu CC
        • et al.
        Assessment of Selection Criteria for Low-Dose Lung Screening CT Among Asian Ethnic Groups in Taiwan: From Mass Screening to Specific Risk-Based Screening for Non-Smoker Lung Cancer.
        Clinical lung cancer. 2016; 17: e45-e56
        • Moyer VA.
        Screening for lung cancer: U.S. Preventive Services Task Force recommendation statement.
        Ann Intern Med. 2014; 160: 330-338
        • Landy R
        • Young CD
        • Skarzynski M
        • et al.
        Using Prediction-Models to Reduce Persistent Racial/Ethnic Disparities in Draft 2020 USPSTF Lung-Cancer Screening Guidelines.
        J Natl Cancer Inst. 2021; 113: 1590-1594
        • Krist AH
        • Davidson KW
        • et al.
        US Preventive Services Task Force, Screening for Lung Cancer: US Preventive Services Task Force Recommendation Statement.
        JAMA. 2021; 325: 962-970
        • Digiulio S.
        USPSTF Updates Lung Cancer Screening Guidelines.
        Oncology Times. 2021; : 43
        • Cohen SL
        • Ward TJ
        • Cham MD.
        The relationship between CT scout landmarks and lung boundaries on chest CT: guidelines for minimizing excess z-axis scan length.
        Eur Radiol. 2020; 30: 581-587
        • Colevray M
        • Tatard-Leitman VM
        • Gouttard S
        • Douek P
        • Boussel L.
        Convolutional neural network evaluation of over-scanning in lung computed tomography.
        Diagn Interv Imaging. 2019; 100: 177-183
        • Li L
        • Liu Z
        • Huang H
        • Lin M
        • Luo D.
        Evaluating the performance of a deep learning-based computer-aided diagnosis (DL-CAD) system for detecting and characterizing lung nodules: Comparison with the performance of double reading by radiologists.
        Thorac Cancer. 2019; 10: 183-192
        • Hwang EJ
        • Park S
        • Jin KN
        • et al.
        Development and Validation of a Deep Learning-based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs.
        Clin Infect Dis. 2019; 69: 739-747
        • Anthimopoulos M
        • Christodoulidis S
        • Ebner L
        • Christe A
        • Mougiakakou S.
        Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network.
        IEEE Trans Med Imaging. 2016; 35: 1207-1216
        • Demircioğlu A
        • Kim MS
        • Stein MC
        • Guberina N
        • Umutlu L
        • Nassenstein K.
        Automatic Scan Range Delimitation in Chest CT Using Deep Learning.
        Radiol Artif Intell. 2021; 3e200211
        • Payer C
        • Stern D
        • Bischof H
        • Urschler M.
        Integrating spatial configuration into heatmap regression based CNNs for landmark localization.
        Med Image Anal. 2019; 54: 207-219
        • Russakovsky O
        • Deng J
        • Su H
        • et al.
        ImageNet Large Scale Visual Recognition Challenge.
        Int J Comput Vis. 2014; : 1-42
        • Kingma D
        • Ba J.
        Adam: A Method for Stochastic Optimization.
        Computer Science. 2014; (https://arxiv.org/abs/1412.6980)
      1. Chen Y, Wang Z, Peng Y, Zhang Z, Yu G, Sun J. Cascaded Pyramid Network for Multi-Person Pose Estimation. 2017. https://arxiv.org/abs/1711.07319.

      2. Li W, Wang Z, Yin B, et al. Rethinking on Multi-Stage Networks for Human Pose Estimation. 2019. https://arxiv.org/abs/1901.00148.

        • Simonyan K
        • Vedaldi A
        • Zisserman A.
        Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps.
        Computer ence. 2013; (https://arxiv.org/abs/1312.6034)
        • Schwartz F
        • Stieltjes B
        • Szucs-Farkas Z
        • Euler A.
        Over-scanning in chest CT: Comparison of practice among six hospitals and its impact on radiation dose.
        Eur J Radiol. 2018; 102: 49-54
        • Cohen SL
        • Ward TJ
        • Makhnevich A
        • Richardson S
        • Cham MD.
        Retrospective analysis of 1118 outpatient chest CT scans to determine factors associated with excess scan length.
        Clin Imaging. 2020; 62: 76-80
        • Huda W
        • Ogden KM
        • Khorasani MR.
        Converting dose-length product to effective dose at CT.
        Radiology. 2008; 248: 995-1003
        • Chen HC
        • Lin CJ
        • Wu CH
        • Wang CK
        • Sun YN.
        Automatic Insall-Salvati ratio measurement on lateral knee x-ray images using model-guided landmark localization.
        Phys Med Biol. 2010; 55: 6785-6800
        • Yar O
        • Onur MR
        • Idilman IS
        • Akpinar E
        • Akata D.
        Excessive z-axis scan coverage in body CT: frequency and causes.
        Eur Radiol. 2021; 31: 4358-4366
        • Huo D
        • Kiehn M
        • Scherzinger A.
        Investigation of Low-Dose CT Lung Cancer Screening Scan "Over-Range" Issue Using Machine Learning Methods.
        Journal of digital imaging. 2019; 32: 931-938
        • Hoye J
        • Sharma S
        • Zhang Y
        • et al.
        Organ doses from CT localizer radiographs: Development, validation, and application of a Monte Carlo estimation technique.
        Medical physics. 2019; 46: 5262-5272
        • Bu Q
        • Zeng K
        • Wang R
        • Feng J
        Multi-depth dilated network for fashion landmark detection with batch-level online hard keypoint mining.
        Image and Vision Computing. 2020; 99103930
      3. Iglovikov V, Shvets A. TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation. 2018. https://arxiv.org/abs/1801.05746.

        • He K
        • Zhang X
        • Ren S
        • Sun J
        Deep Residual Learning for Image Recognition.
        in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016 (https://arxiv.org/abs/1512.03385)
        • Li X
        • Dou Q
        • Chen H
        • et al.
        3D multi-scale FCN with random modality voxel dropout learning for Intervertebral Disc Localization and Segmentation from Multi-modality MR Images.
        Med Image Anal. 2018; 45: 41-54
        • Cohen SL
        • Ward TJ
        • Jacobi AH
        • Cham M.
        Institutional Impact of a Personalized Technologist Feedback Program on Scan Length and Radiation Dose.
        J Am Coll Radiol. 2019; 16: 1073-1076