close
close

Better performance of lung nodule detection with deep learning over computed tomography using chest radiography with pixel-level labels: data quality matters

Better performance of lung nodule detection with deep learning over computed tomography using chest radiography with pixel-level labels: data quality matters

  • Mortality Rate, GBD, Causes of Death C. Global, regional and national life expectancy, all-cause mortality and cause-specific mortality for 249 causes of death, 1980–2015: a systematic analysis for the Global Burden of Disease Study 2015. Lancet 3881459–1544 (2016).

    Article

    Google Scholar

  • Brogdon, BG, Kelsey, CA and Moseley, RD Jr. Factors affecting the detection of lung lesions. Radiol. Clin. North America. 21633–654 (1983).

    Article
    CAS
    PubMed

    Google Scholar

  • Forrest, JV and Friedman, PJ Radiologic errors in patients with lung cancer. Western J Med. 134485–490 (1981).

    CAS
    PubMed
    PubMed Central

    Google Scholar

  • Levin, DC, Rao, VM, Parker, L. and Frangos, AJ Analysis of radiologists’ imaging workload trends by site of service. J. Am. Coll. Radiol. 10760–763 (2013).

    Article
    PubMed

    Google Scholar

  • Bhargavan, M., Kaye, A. H., Forman, H. P. and Sunshine, J. H. Workload of radiologists in the United States in 2006-2007 and trends since 1991-1992. Radiology. 252458–467 (2009).

    Article
    PubMed

    Google Scholar

  • LeCun, Y., Bengio, Y., and Hinton, G. Deep learning. Nature. 521436–444 (2015).

    Article
    ADS
    CAS
    PubMed

    Google Scholar

  • Nam, JG and others. Development and validation of a deep learning-based algorithm for automatic detection of malignant pulmonary nodules on chest radiographs. Radiology. 290218–228 (2019).

    Article
    PubMed

    Google Scholar

  • Liu, V. and others. Automatic identification of pneumonia in chest radiography reports in critically ill patients. BMC Med. Inform. Decis. Mak. 1390 (2013).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • Hua, KL, Hsu, CH, Hidayati, SC, Cheng, WH and Chen, YJ Computer-aided classification of lung nodules in computed tomography images by deep learning technique. Oncol. Targets Ther. 82015–2022 (2015).

    CAS

    Google Scholar

  • Lakhani, P. and Sundaram, B. Deep learning in chest radiography: Automatic classification of pulmonary tuberculosis using convolutional neural networks. Radiology. 284574–582 (2017).

    Article
    PubMed

    Google Scholar

  • Wang, X., Peng, Y., Lu, L., Lu, Z., and Summers, R. M. Tienet: Text-to-image embedding network for common chest diseases classification and reporting in chest X-rays, 9049–9058 (2018).

  • Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., et al. Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison, 590–597 (2019).

  • Johnson, AE, Pollard, TJ, Greenbaum, NR, Lungren, MP, Deng, C., Peng, Y., et al. MIMIC-CXR-JPG, a large public domain database of labeled chest radiographs. arXiv preprint arXiv:190107042 (2019).

  • Rajpurkar, P. and others. Deep learning in chest radiography diagnosis: A retrospective comparison of the CheXNeXt algorithm for practicing radiologists. PLoS Medicine. 15e1002686 (2018).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • Oakden-Rayner, L. Exploring Large-Scale Public Medical Image Datasets. Academy Radiol. 27106–112 (2020).

    Article
    PubMed

    Google Scholar

  • Arpit, D., Jastrzębski, S., Ballas, N., Krueger, D., Bengio, E., Kanwal, M. S., et al. A closer look at memorization in deep networks. PMLR, 233–242 (2017).

  • Loverdos, K., Fotiadis, A., Kontogianni, C., Iliopoulou, M. and Gaga, M. Lung nodules: a comprehensive review of current approaches and management. Ann. Chest. Medicine. 14226–238 (2019).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • Bernard, M. and others. Efficient label cleaning for improved dataset quality under resource constraints. National Community. 131161 (2022).

    Article
    ADS
    CAS
    PubMed
    PubMed Central

    Google Scholar

  • Liang, PRC and others. Identifying pulmonary nodules or masses on chest radiography using deep learning: External validation and strategies to improve clinical practice. Clinical Radiol. 7538–45 (2020).

    Article
    PubMed

    Google Scholar

  • Yoo, H., Kim, KH, Singh, R., Digumarthy, SR and Kalra, MK Validation of deep learning algorithm for detection of malignant lung nodules on chest radiographs. JAMA Clear Open. 3e2017135 (2020).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • You s. and others. Diagnostic performance and clinical value of deep learning-based nodule detection system on the effect of lung nodule location. Insight Imaging. 14149 (2023).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., et al. Chexnet: Radiologist-level pneumonia detection in chest X-rays with deep learning. arXiv preprint arXiv:171105225 (2017).

  • Ait Nasser, A., & Akhloufi, M. A. Chest diseases classification using CXR and deep ensemble learning. Proceedings of the 19th International Conference on Content-Based Multimedia Indexing 2022, 116–120.

  • Blais, M.-A., & Akhloufi, M.A. Deep learning and binary relevant classification of multiple diseases using chest X-ray images. 2021 43rd Annual International Conference of the IEEE Medical and Biological Engineering Society (EMBC)IEEE, 2794–2797 (2021).

  • Chen, Y., Liu, F., Tian, ​​Y., Liu, Y., & Carneiro, G. Semantic guided image virtual feature learning for noisy multi-label chest X-ray classification. arXiv preprint arXiv:220301937 (2022).

  • Oakden-Rayner, L. Exploring large-scale public medical image datasets. Academy Radiol. 27106–112 (2020).

    Article
    PubMed

    Google Scholar

  • Gundel, S. and others. Robust classification from noisy labels: Integrating additional information for chest radiograph abnormality assessment. Medical Image Anal. 72102087 (2021).

    Article
    PubMed

    Google Scholar

  • Arun, N. and others. Evaluating the reliability of saliency maps in localizing abnormalities in medical imaging. Radiol. Artificial. Intelligence. 3e200267 (2021).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • Chiu, H.-Y. and others. Artificial intelligence for early detection of nodules in chest X-ray images. Biomedical 102839 (2022).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • Yoo, H., Kim, KH, Singh, R., Digumarthy, SR and Kalra, MK Validation of deep learning algorithm for detection of malignant lung nodules on chest radiographs. JAMA Netw. Open. 3e2017135 (2020).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • Nguyen, Headquarters and others. VinDr-CXR: Open dataset of chest X-rays with radiologists’ annotations. Science. Data 9429 (2022).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • Teixeira, L.O. and others. Impact of lung segmentation on diagnosis and explanation of COVID-19 in chest X-ray images. Sensors. 217116 (2021).

    Article
    ADS
    CAS
    PubMed
    PubMed Central

    Google Scholar

  • DeLong, ER, DeLong, DM and Clarke-Pearson, DL Comparing areas under two or more related receiver operating characteristic curves: A nonparametric approach. Biometric. 44837–845 (1988).

    Article
    CAS
    PubMed

    Google Scholar

  • Rolnick, D., Veit, A., Belongie, S., and Shavit, N. Deep learning is robust to large label noise. arXiv preprint arXiv:170510694 (2017).

  • Jang, R. and others. Evaluating the robustness of convolutional neural networks in labeling noise using chest X-ray images from multiple centers. JMIR Med.Info. 8e18089 (2020).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • Karimi, D., Dou, H., Warfield, SK and Gholipour, A. Deep learning with noisy labels: Exploring techniques and solutions in medical image analysis. Medical Image Anal. 65101759 (2020).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • Guan, H. & Liu, M. Domain adaptation for medical image analysis: A survey. IEEE Trans. Biomedical Eng. 691173–1185 (2022).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A. Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2921–2929 (2016).

  • Huff, DT, Weisman, AJ, & Jeraj, R. Interpretation and visualization techniques for deep learning models in medical imaging. Physics, Medicine, Biology 6604TR1 (2021).

    Article

    Google Scholar

  • Seah, J. and others. Do comprehensive deep learning algorithms suffer from hidden stratification? A retrospective study on pneumothorax detection on chest radiography. BMJ Open. 11the053024 (2021).

    Article
    PubMed
    PubMed Central

    Google Scholar

  • DeGrave, AJ, Janizek, JD, and Lee, SI AI chooses shortcuts over signal for radiographic COVID-19 detection. medRxiv 196105608 (2020).

    Google Scholar

  • Behrendt, F. and others. A systematic approach to nodule detection in chest radiographs based on deep learning. Science Representative 1310120 (2023).

    Article
    ADS
    CAS
    PubMed
    PubMed Central

    Google Scholar

  • Cellina, M. and others. Artificial intelligence in lung cancer screening: The future is now. Cancers. 154344 (2023).

    Article
    CAS
    PubMed
    PubMed Central

    Google Scholar

  • Ranschaert, E., Topff, L. & Pianykh, O. Optimization of radiology workflow with artificial intelligence. Radiol. Clin. North America. 59955–966 (2021).

    Article
    PubMed

    Google Scholar

  • Gavelli, G. & Giampalma, E. Sensitivity and specificity of chest X-ray screening for lung cancer. Cancer. 892453–2456 (2000).

    Article
    CAS
    PubMed

    Google Scholar