Advertisement

Deep Learning–Based Digitally Reconstructed Tomography of the Chest in the Evaluation of Solitary Pulmonary Nodules: A Feasibility Study

      HIGHLIGHTS

      • Digitally reconstructed tomograms (DRTs) with frontal and lateral radiographic projections (planar radiography, PR) showed higher diagnostic performance than PR alone (area under the receiver operating characteristic curve 0.95–0.98 versus 0.80–0.85; p < 0.02) in the identification of solitary pulmonary nodules (SPNs).
      • SPNs were diagnosed in 11 more patients using DRTs than using PR alone.

      Rationale and Objectives

      Computed tomography (CT) is preferred for evaluating solitary pulmonary nodules (SPNs) but access or availability may be lacking, in addition, overlapping anatomy can hinder detection of SPNs on chest radiographs. We developed and evaluated the clinical feasibility of a deep learning algorithm to generate digitally reconstructed tomography (DRT) images of the chest from digitally reconstructed frontal and lateral radiographs (DRRs) and use them to detect SPNs.

      Methods

      This single-institution retrospective study included 637 patients with noncontrast helical CT of the chest (mean age 68 years, median age 69 years, standard deviation 11.7 years; 355 women) between 11/2012 and 12/2020, with SPNs measuring 10–30 mm. A deep learning model was trained on 562 patients, validated on 60 patients, and tested on the remaining 15 patients. Diagnostic performance (SPN detection) from planar radiography (DRRs and CT scanograms, PR) alone or with DRT was evaluated by two radiologists in an independent blinded fashion. The quality of the DRT SPN image in terms of nodule size and location, morphology, and opacity was also evaluated, and compared to the ground-truth CT images

      Results

      Diagnostic performance was higher from DRT plus PR than from PR alone (area under the receiver operating characteristic curve 0.95–0.98 versus 0.80–0.85; p < 0.05). DRT plus PR enabled diagnosis of SPNs in 11 more patients than PR alone. Interobserver agreement was 0.82 for DRT plus PR and 0.89 for PR alone; and interobserver agreement for size and location, morphology, and opacity of the DRT SPN was 0.94, 0.68, and 0.38, respectively.

      Conclusion

      For SPN detection, DRT plus PR showed better diagnostic performance than PR alone. Deep learning can be used to generate DRT images and improve detection of SPNs.

      Key Words

      Abbreviation:

      AUC (Area under the curve), BMI (Body mass index), CI (Confidence interval), COPD (Chronic obstructive pulmonary disease), CT (Computed tomography), CXR (Chest radiograph), DRR (Digitally reconstructed radiograph), DRT (Digitally reconstructed tomogram), LSTM (Long short-term memory), MSE (Mean squared error), PIL (Python image library), PR (Planar radiography), SD (Standard deviation), SPN (Solitary pulmonary nodule)
      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

      1. National Health Service. Diagnostic Imaging Dataset Statistical Release. Published Accessed at: December 19, 2019. Accessed from: https://www.england.nhs.uk/statistics/wp-content/uploads/sites/2/2019/12/Provisional-Monthly-Diagnostic-Imaging-Dataset-Statistics-2019-12-19-1.pdf

        • Schalekamp S
        • van Ginneken B
        • Koedam E
        • et al.
        Computer-aided detection improves detection of pulmonary nodules in chest radiographs beyond the support by bone-suppressed images.
        Radiology. 2014; 272: 252-261
        • Swensen SJ
        • Jett JR
        • Hartman TE
        • et al.
        Lung cancer screening with CT: mayo clinic experience.
        Radiology. 2003; 226: 756-761
        • Gohagan J
        • Marcus P
        • Fagerstrom R
        • et al.
        Baseline findings of a randomized feasibility trial of lung cancer screening with spiral CT scan vs chest radiograph: the lung screening study of the national cancer institute.
        Chest. 2004; 126: 114-121
        • Wyker A
        • Henderson WW.
        Solitary pulmonary nodule.
        StatPearls. Updated. July 26, 2021; (Accessed at:Accessed from:)
        • Shankar A
        • Saini D
        • Dubey A
        • et al.
        Feasibility of lung cancer screening in developing countries: challenges, opportunities and way forward.
        Transl Lung Cancer Res. 2019; 8: S106-S121https://doi.org/10.21037/tlcr.2019.03.03
        • Lubuzo B
        • Ginindza T
        • Hlongwana K.
        The barriers to initiating lung cancer care in low-and middle-income countries.
        Pan Afr Med J. 2020; 35: 38https://doi.org/10.11604/pamj.2020.35.38.17333
        • Shaw NJ
        • Hendry M
        • Eden OB.
        Inter-observer variation in interpretation of chest X-rays.
        Scott Med J. 1990; 35: 140-141https://doi.org/10.1177/003693309003500505
        • Finigan JH
        • Kern JA.
        Lung cancer screening: past, present and future.
        Clin Chest Med. 2013; 34: 365-371
        • Quekel LG
        • Kessels AG
        • Goei R
        • et al.
        Miss rate of lung cancer on the chest radiograph in clinical practice.
        Chest. 1999; 115: 720-724
        • Maboreke T
        • Banhwa J
        • Pitcher RD.
        An audit of licensed Zimbabwean radiology equipment resources as a measure of healthcare access and equity.
        Pan Afr Med J. 2019; 34: 60https://doi.org/10.11604/pamj.2019.34.60.18935
      2. Silverstein J. Most of the world doesn't have access to x-rays [Internet]. The Atlantic. Accessed at: January 1, 2022. Accessed from: https://www.theatlantic.com/health/archive/2016/09/radiology-gap/501803/

        • Lee SM
        • JSeo JB
        • Yun J
        • et al.
        Deep learning applications in chest radiography and computed tomography: current state of the art.
        J Thorac Imaging. 2019; 34: 75-85https://doi.org/10.1097/RTI.0000000000000387
        • Nakamura Y
        • Higaki T
        • Tatsugami F
        • et al.
        Deep learning–based CT image reconstruction: Initial evaluation targeting hypovascular hepatic metastases.
        Radiol Artif Intell. 2019; 1: 6
        • Brady SL
        • Trout AT
        • Somasundaram E
        • et al.
        Improving image quality and reducing radiation dose for pediatric CT by using deep learning reconstruction.
        Radiol. 2021; 298: 180-188
        • Zarshenas A
        • Liu J
        • Forti P
        • et al.
        Separation of bones from soft tissue in chest radiographs: anatomy-specific orientation-frequency-specific deep neural network convolution.
        Med Phys. 2019; 46 (10.100e2/mp.13468): 2232-2242
        • Ying X
        • Guo H
        • Ma K
        • et al.
        X2CT-GAN: reconstructing CT from biplanar X-rays with generative adversarial networks.
        in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019 (Accessed at: January 3, 2022. Accessed from:)
        • Lewis A
        • Mahmoodi E
        • Zhou Y
        • et al.
        Improving tuberculosis (TB) prediction using synthetically generated computed tomography (CT) images.
        in: Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021 (Accessed at: January 3, 2022. Accessed from:)
        • Shibata H
        • Hanaoka S
        • Nomura Y
        • et al.
        Reconstruction of multiple volumetric chest computed tomography images with different likelihoods from a uni-or biplanar chest X-ray image using a flow-based generative model.
        • Lee MH
        • Lubner MG
        • Mellnick VM
        • et al.
        The CT scout view: complementary value added to abdominal CT interpretation.
        Abdom Radiol. 2021; 46: 5021-5036
        • Pyrros A
        • Flanders AE
        • Rodríguez-Fernández JM
        • et al.
        Predicting prolonged hospitalization and supplemental oxygenation in patients with COVID-19 infection from ambulatory chest radiographs using deep learning.
        Acad Radiol. 2021; 28: 1151-1158https://doi.org/10.1016/j.acra.2021.05.002
        • Choy CB
        • Xu D
        • Gwak J
        • et al.
        3D-R2N2: A unified approach for single and multi-view 3D object reconstruction.
        in: European Conference on Computer Vision. Springer, 2016: 628-644
        • Ronneberger O
        • Fischer P
        • Brox T.
        U-net: Convolutional networks for biomedical image segmentation.
        in: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2015: 234-241
      3. Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv 2015. https://arxiv.org/abs/1502.03167.

      4. Kingma DP, Ba J. Adam: a method for stochastic optimization. arXiv 2014. https://arxiv.org/abs/1412.6980.

        • DeLong ER
        • DeLong DM
        • Clarke-Pearson DL.
        Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach.
        Biometrics. 1988; 44: 837-845
      5. Mansilla L, Milone DH, Ferrante E. Learning deformable registration of medical images with anatomical constraints. arXiv 2020. https://arxiv.org/abs/2001.07183.

        • Zarshenas A
        • Liu J
        • Forti P
        • et al.
        Separation of bones from soft tissue in chest radiographs: anatomy-specific orientation-frequency-specific deep neural network convolution.
        Med Phys. 2019; 46: 2232-2242https://doi.org/10.1002/mp.13468