Computer-aided diagnosis for World Health Organization-defined chest radiograph primary-endpoint pneumonia in children



The chest radiograph is the most common imaging modality to assess childhood pneumonia. It has been used in epidemiological and vaccine efficacy/effectiveness studies on childhood pneumonia.


To develop computer-aided diagnosis (CAD4Kids) for chest radiography in children and to evaluate its accuracy in identifying World Health Organization (WHO)-defined chest radiograph primary-endpoint pneumonia compared to a consensus interpretation.

Materials and methods

Chest radiographs were independently evaluated by three radiologists based on WHO criteria. Automatic lung field segmentation was followed by manual inspection and correction, training, feature extraction and classification. Radiographs were filtered with Gaussian derivatives on multiple scales, extracting texture features to classify each pixel in the lung region. To obtain an image score, the 95th percentile score of the pixels was used. Training and testing were done in 10-fold cross validation.


The radiologist majority consensus reading of 858 interpretable chest radiographs included 333 (39%) categorised as primary-endpoint pneumonia, 208 (24%) as other infiltrate only and 317 (37%) as no primary-endpoint pneumonia or other infiltrate. Compared to the reference radiologist consensus reading, CAD4Kids had an area under the receiver operator characteristic (ROC) curve of 0.850 (95% confidence interval [CI] 0.823–0.876), with a sensitivity of 76% and specificity of 80% for identifying primary-endpoint pneumonia on chest radiograph. Furthermore, the ROC curve was 0.810 (95% CI 0.772–0.846) for CAD4Kids identifying primary-endpoint pneumonia compared to other infiltrate only.


Further development of the CAD4Kids software and validation in multicentre studies are important for future research on computer-aided diagnosis and artificial intelligence in paediatric radiology.

This is a preview of subscription content, log in to check access.

Access options

Buy single article

Instant unlimited access to the full article PDF.

US$ 39.95

Price includes VAT for USA

Subscribe to journal

Immediate online access to all issues from 2019. Subscription will auto renew annually.

US$ 199

This is the net price. Taxes to be calculated in checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7


  1. 1.

    Black RE, Cousens S, Johnson HL et al (2010) Global, regional, and national causes of child mortality in 2008: a systematic analysis. Lancet 375:1969–1987

  2. 2.

    O'Brien KL, Wolfson LJ, Watt JP et al (2009) Burden of disease caused by Streptococcus pneumoniae in children younger than 5 years: global estimates. Lancet 374:893–902

  3. 3.

    Watt JP, Wolfson LJ, O'Brien KL et al (2009) Burden of disease caused by Haemophilus influenzae type b in children younger than 5 years: global estimates. Lancet 374:903–911

  4. 4.

    Pitcher RD, Lombard C, Cotton MF et al (2014) Clinical and immunological correlates of chest X-ray abnormalities in HIV-infected South African children with limited access to anti-retroviral therapy. Pediatr Pulmonol 49:581–588

  5. 5.

    Qin C, Yao D, Shi Y, Song Z (2018) Computer-aided detection in chest radiography based on artificial intelligence: a survey. Biomed Eng Online 17:113

  6. 6.

    Cherian T, Mulholland EK, Carlin JB et al (2005) Standardized interpretation of paediatric chest radiographs for the diagnosis of pneumonia in epidemiological studies. Bull World Health Organ 83:353–359

  7. 7.

    Mahomed N, Fancourt N, de Campo J et al (2017) Preliminary report from the World Health Organisation Chest Radiography in Epidemiological Studies project. Pediatr Radiol 47:1399–1404

  8. 8.

    Mouton A, Pitcher RD, Douglas TS (2010) Computer-aided detection of pulmonary pathology in pediatric chest radiographs. Med Image Comput Comput Assist Interv 13:619–625

  9. 9.

    Breuninger M, van Ginneken B, Philipsen RH et al (2014) Diagnostic accuracy of computer-aided detection of pulmonary tuberculosis in chest radiographs: a validation study from sub-Saharan Africa. PLoS One 9:e106381

  10. 10.

    Muyoyeta M, Maduskar P, Moyo M et al (2014) The sensitivity and specificity of using a computer aided diagnosis program for automatically scoring chest X-rays of presumptive TB patients compared with Xpert MTB/RIF in Lusaka Zambia. PLoS One 9:e93757

  11. 11.

    van Ginneken B, ter Haar Romeny BM, Viergever MA (2001) Computer-aided diagnosis in chest radiography: a survey. IEEE Trans Med Imaging 20:1228–1241

  12. 12.

    Oliveira LL, Silva SA, Ribeiro LH et al (2008) Computer-aided diagnosis in chest radiography for detection of childhood pneumonia. Int J Med Inform 77:555–564

  13. 13.

    Pneumonia Etiology Research for Child Health (PERCH) Study Group (2019) Causes of severe pneumonia requiring hospital admission in children without HIV infection from Africa and Asia: the PERCH multi-country case-control study. Lancet 394:757–779

  14. 14.

    Mahomed N, Sewchuran T, Moodley H, Madhi SA (2016) Chest x-ray findings in children hospitalized with WHO-defined severe, very severe pneumonia in a high HIV prevalence setting in the era of bacterial conjugate vaccines. Paper presented at the 7th International Pediatric Radiology (IPR) Conjoint Meeting & Exhibition, Chicago, Illinois, 15-20 May 2016

  15. 15.

    Scott JA, Wonodi C, Moisi JC et al (2012) The definition of pneumonia, the assessment of severity, and clinical standardization in the Pneumonia Etiology Research for Child Health study. Clin Infect Dis 54:S109–S116

  16. 16.

    van Ginneken B, Stegmann MB, Loog M (2006) Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database. Med Image Anal 10:19–40

  17. 17.

    Meyers A, Shah A, Cleveland RH et al (2001) Thymic size on chest radiograph and rapid disease progression in human immunodeficiency virus 1-infected children. Pediatr Infect Dis J 20:1112–1118

  18. 18.

    Mendelson DS (2001) Imaging of the thymus. Chest Surg Clin N Am 11:269–293

  19. 19.

    Menashe SJ, Iyer RS, Parisi MT et al (2016) Pediatric chest radiographs: common and less common errors. AJR Am J Roentgenol 207:1–9

  20. 20.

    Hogeweg L, Sanchez CI, Maduskar P et al (2015) Automatic detection of tuberculosis in chest radiographs using a combination of textural, focal, and shape abnormality analysis. IEEE Trans Med Imaging 34:2429–2442

  21. 21.

    Loog M, Van Ginneken B (2004) Static posterior probability fusion for signal detection: applications in the detection of interstitial diseases in chest radiographs. In: Proceedings of the 17th International Conference on Pattern Recognition, 26 August 2004, Cambridge, UK, pp 644-647

  22. 22.

    Elemraid MA, Muller M, Spencer DA et al (2014) Accuracy of the interpretation of chest radiographs for the diagnosis of paediatric pneumonia. PLoS One 9:e106051

  23. 23.

    Patel AB, Amin A, Sortey SZ et al (2007) Impact of training on observer variation in chest radiographs of children with severe pneumonia. Indian Pediatr 44:675–681

  24. 24.

    WHO HiB Initiative Radiology Workshop, Hanoi, Vietnam, 11-12 October 2011

  25. 25.

    Fancourt N, Deloria Knoll M, Baggett HC et al (2017) Chest radiograph findings in childhood pneumonia cases from the multisite PERCH study. Clin Infect Dis 64:S262–S270

  26. 26.

    Moore MM, Slonimsky E, Long AD et al (2019) Machine learning concepts, concerns and opportunities for a pediatric radiologist. Pediatr Radiol 49:509–516

  27. 27.

    Rajpurkar P, Irvin J, Zhu K et al (2018) CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning. Accessed 4 Jun 2019

  28. 28.

    You D, Hug L, Ejdemyr S et al (2015) Global, regional, and national levels and trends in under-5 mortality between 1990 and 2015, with scenario-based projections to 2030: a systematic analysis by the UN Inter-agency Group for Child Mortality Estimation. Lancet 386:2275–2286

  29. 29.

    Wang X, Peng Y, Lu L et al (2017) ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Accessed 4 Jun 2019

  30. 30.

    van Ginneken B, Katsuragawa S, ter Haar Romeny BM et al (2002) Automatic detection of abnormalities in chest radiographs using local texture analysis. IEEE Trans Med Imaging 21:139–149

  31. 31.

    Sousa RT, Marques O, Curado GTF et al (2014) Evaluation of classifiers to a childhood pneumonia computer-aided diagnosis system. Proceedings of the IEEE 27th International Symposium on Computer-Based Medical Systems, 477-478.

Download references


The study received Carnegie PhD Fellowship funding and a South African Medical Research Council Self-Initiated Research Grant. We thank staff at the Respiratory and Meningeal Pathogens Research Unit involved in enrolling study patients: Azwifarwi Mudau, Debra Katisi, Audrey Kubheka, Magare Lelaka, Tsekabe Makgoba, Matshediso Moilwa, Malebo Motiane, Sibonsile Moya, Thondani Netshishivhe, Minah Nkuna, Mmabatho Selela, Ndulela Titi, Nonhlanhla Tsholetsane, Lerato Mapetla and Gudani Singo.

Author information

Correspondence to Nasreen Mahomed.

Ethics declarations

Conflicts of interest


Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material


(DOCX 19 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Mahomed, N., van Ginneken, B., Philipsen, R.H.H.M. et al. Computer-aided diagnosis for World Health Organization-defined chest radiograph primary-endpoint pneumonia in children. Pediatr Radiol (2020).

Download citation


  • Accuracy
  • Children
  • Computer-aided diagnosis
  • Pneumonia
  • Primary-endpoint
  • Radiography
  • World Health Organization