Chest x-ray analysis

CAD4TB

Chest radiography is the most common radiological exam in the world. In many hospitals 40% of all exams made in the radiology department are chest x-rays. The advent of deep learning has increased the interest for chest x-ray analysis. At DIAG, we have pioneered tuberculosis detection with chest x-ray, but we also have research projects aimed at detecting other diseases from chest radiographs.

Tuberculosis screening and chest radiography

Tuberculosis (TB) is a highly infectious disease that still kills 1.5 million people every year, despite the fact that a cheap cocktail of antibiotics can cure almost every TB patient. Finding TB before patients infect others and putting people on treatment is crucial.

Chest radiography has always been widely used to find TB. Digital chest radiography has made x-ray cheaper and easier to use. No films, chemicals and water are needed to produce a digital radiograph, automatic exposure control ensures high image quality, and images are instantly available. The cost per exam, once a digital unit is operational, is near zero. Digital chest radiography, therefore, has a large potential to be used in TB case finding and prevalence surveys, as an adjunct test, next to molecular testing. Molecular diagnostics for TB, such as the GeneXpert test have become a standard for TB diagnosis, because they can make a definitive diagnosis of TB in two hours. However, these tests are still much more expensive and time-consuming than radiography. Radiography can act as a filter: TB suspects undergo symptom screening and chest radiography, and those with symptoms and/or abnormalities in the chest radiograph undergo further testing.

One issue remains: the lack of human expert readers in countries with a high burden of TB. CAD4TB eliminates this problem by automating the reading process.

The CAD4TB project

Our work in developing software to detect signs of tuberculosis started in 1996 when digital x-ray machines were first entering the market. We work with Delft Imaging, famous as the inventor of the Odelca camera from the 1960s, one of the most widely used systems in x-ray TB screening in the world. Our project resulted in a prototype computer-aided detection system for TB in 2001. At that time, however, digital x-ray was not yet widely adopted for TB case finding.

In 2007, we attracted a research grant and established the CAD4TB project with partners in South Africa, the University of Cape Town Lung Institute, and in Zambia, the NGO Zambart.

The CAD4TB software

The first CAD4TB beta prototype (CAD4TB v0.01) was field-tested in 2010. In 2011, the first official prototype version was released (CAD4TB v1.08), notably improved by training the system with a much larger number of images. A string of new versions of the software has been released: in 2012 v2.09, in 2013 v3.07, and in 2014 v4.10. Version v4.10 was the first version to receive a CE label. In 2016, version 5 saw the light and in 2019 version 6 was released, based on deep learning. Algorithm development behind CAD4TB is now carried out at Thirona, a spin-off company from the Diagnostic Image Analysis Group.

CAD4TB is commercially available via Delft Imaging and has hundreds of installations in over 40 countries worldwide.

This BBC report shows CAD4TB in action in Ghana:

New research

Our current research focuses on extending the capabilities of the software to do more than outputting a single number related to the probability the subject has TB. We have developed a system for automatically measuring the cardiothoracic ratio, for childhood pneumonia detection, and we are working on detection of COVID-19 on the chest radiograph. In collaboration with Thirona, the Fondation Botnar, the Swiss Tropical and Public Health Institute and NGO SolidarMed, we will field test a combined TB and COVID-19 screening in district hospitals in Lesotho with a new AI system that uses a combination of chest x-ray and blood markers.

Funding

People

Bram van Ginneken

Bram van Ginneken

Professor, Scientific Co-Director

Keelin Murphy

Keelin Murphy

Assistant Professor

Ecem Sogancioglu

Ecem Sogancioglu

PhD Candidate

Publications

  • K. Murphy, H. Smits, A. Knoops, M. Korst, T. Samson, E. Scholten, S. Schalekamp, C. Schaefer-Prokop, R. Philipsen, A. Meijers, J. Melendez, B. van Ginneken and M. Rutten, "COVID-19 on the Chest Radiograph: A Multi-Reader Evaluation of an AI System", Radiology, 2020;296:E166-E172.
  • S. Habib, S. Rafiq, S. Zaidi, R. Ferrand, J. Creswell, B. Van Ginneken, W. Jamal, K. Azeemi, S. Khowaja and A. Khan, "Evaluation of computer aided detection of tuberculosis on chest radiography among people with diabetes in Karachi Pakistan", Scientific Reports, 2020;10(1):6276.
  • N. Mahomed, B. van Ginneken, R. Philipsen, J. Melendez, D. Moore, H. Moodley, T. Sewchuran, D. Mathew and S. Madhi, "Computer-aided diagnosis for World Health Organization-defined chest radiograph primary-endpoint pneumonia in children", Pediatric Radiology, 2020;50(4):482-491.
  • K. Murphy, S. Habib, S. Zaidi, S. Khowaja, A. Khan, J. Melendez, E. Scholten, F. Amad, S. Schalekamp, M. Verhagen, R. Philipsen, A. Meijers and B. van Ginneken, "Computer aided detection of tuberculosis on chest radiographs: An evaluation of the CAD4TB v6 system", Scientific Reports, 2020;10:5492.
  • B. van Ginneken, "Deep Learning for Triage of Chest Radiographs: Should Every Institution Train Its Own System?", Radiology, 2019;290:545-546.
  • R. Philipsen, C. Sánchez, J. Melendez, W. Lew and B. van Ginneken, "Automated chest X-ray reading for tuberculosis in the Philippines to improve case detection: a cohort study", International Journal of Tuberculosis and Lung Disease, 2019;23(7):805-810.
  • J. Melendez, L. Hogeweg, C. Sánchez, R. Philipsen, R. Aldridge, A. Hayward, I. Abubakar, B. van Ginneken and A. Story, "Accuracy of an automated system for tuberculosis detection on chest radiographs in high-risk screening", International Journal of Tuberculosis and Lung Disease, 2018;22(5):567-571.
  • R. Koesoemadinata, K. Kranzer, R. Livia, N. Susilawati, J. Annisa, N. Soetedjo, R. Ruslami, R. Philipsen, B. van Ginneken, R. Soetikno, R. van Crevel, B. Alisjahbana and P. Hill, "Computer-assisted chest radiography reading for tuberculosis screening in people living with diabetes mellitus", International Journal of Tuberculosis and Lung Disease, 2018;22(9):1088-1094.
  • J. Melendez, R. Philipsen, P. Chanda-Kapata, V. Sunkutu, N. Kapata and B. van Ginneken, "Automatic versus human reading of chest X-rays in the Zambia National Tuberculosis Prevalence Survey", International Journal of Tuberculosis and Lung Disease, 2017;21(8):880-886.
  • J. Melendez, C. Sánchez, R. Philipsen, P. Maduskar, R. Dawson, G. Theron, K. Dheda and B. van Ginneken, "An automated tuberculosis screening strategy combining X-ray-based computer-aided detection and clinical information", Scientific Reports, 2016;6:25265.
  • A. Steiner, C. Mangu, J. van den Hombergh, H. van Deutekom, B. van Ginneken, P. Clowes, F. Mhimbira, S. Mfinanga, A. Rachow, K. Reither and M. Hoelscher, "Screening for pulmonary tuberculosis in a Tanzanian prison and computer-aided interpretation of chest X-rays", Public Health Action, 2015;5(4):249-254.
  • R. Philipsen, C. Sánchez, P. Maduskar, J. Melendez, L. Peters-Bax, J. Peter, R. Dawson, G. Theron, K. Dheda and B. van Ginneken, "Automated chest-radiography as a triage for Xpert testing in resource-constrained settings: a prospective study of diagnostic accuracy and costs", Scientific Reports, 2015;5.
  • M. Muyoyeta, P. Maduskar, M. Moyo, N. Kasese, D. Milimo, R. Spooner, N. Kapata, L. Hogeweg, B. van Ginneken and H. Ayles, "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, 2014;9(4):e93757.
  • P. Maduskar, M. Muyoyeta, H. Ayles, L. Hogeweg, L. Peters-Bax and B. van Ginneken, "Detection of tuberculosis with digital chest radiography: automatic reading versus interpretation by clinical officers", International Journal of Tuberculosis and Lung Disease, 2013;17(12):1613-1620.
  • M. Breuninger, B. van Ginneken, R. Philipsen, F. Mhimbira, J. Hella, F. Lwilla, J. van den Hombergh, A. Ross, L. Jugheli, D. Wagner and K. Reither, "Diagnostic accuracy of computer-aided detection of pulmonary tuberculosis in chest radiographs: a validation study from sub-saharan Africa", PLoS One, 2014;9(9):e106381.
  • L. Hogeweg, C. Sánchez, P. Maduskar, R. Philipsen and B. van Ginneken, "Fast and effective quantification of symmetry in medical images for pathology detection: application to chest radiography", Medical Physics, 2017;44(6):2242-2256.
  • J. Melendez, B. van Ginneken, P. Maduskar, R. Philipsen, H. Ayles and C. Sánchez, "On Combining Multiple-Instance Learning and Active Learning for Computer-Aided Detection of Tuberculosis", IEEE Transactions on Medical Imaging, 2016;35(4):1013-1024.
  • P. Maduskar, R. Philipsen, J. Melendez, E. Scholten, D. Chanda, H. Ayles, C. Sánchez and B. van Ginneken, "Automatic detection of pleural effusion in chest radiographs", Medical Image Analysis, 2016;28:22-32.
  • R. Philipsen, P. Maduskar, L. Hogeweg, J. Melendez, C. Sánchez and B. van Ginneken, "Localized energy-based normalization of medical images: application to chest radiography", IEEE Transactions on Medical Imaging, 2015;34(9):1965-75.
  • L. Hogeweg, C. Sánchez, P. Maduskar, R. Philipsen, A. Story, R. Dawson, G. Theron, K. Dheda, L. Peters-Bax and B. van Ginneken, "Automatic detection of tuberculosis in chest radiographs using a combination of textural, focal, and shape abnormality analysis", IEEE Transactions on Medical Imaging, 2015;34(12):2429-2442.
  • J. Melendez, B. van Ginneken, P. Maduskar, R. Philipsen, K. Reither, M. Breuninger, I. Adetifa, R. Maane, H. Ayles and C. Sánchez, "A Novel Multiple-Instance Learning-Based Approach to Computer-Aided Detection of Tuberculosis on Chest X-Rays", IEEE Transactions on Medical Imaging, 2015;34(1):179-192.
  • P. Maduskar, L. Hogeweg, P. de Jong, L. Peters-Bax, R. Dawson, H. Ayles, C. Sánchez and B. van Ginneken, "Cavity contour segmentation in chest radiographs using supervised learning and dynamic programming", Medical Physics, 2014;41(7):071912-1 - 071912-15.
  • L. Hogeweg, C. Sánchez, J. Melendez, P. Maduskar, A. Story, A. Hayward and B. van Ginneken, "Foreign object detection and removal to improve automated analysis of chest radiographs", Medical Physics, 2013;40(7):071901.
  • L. Hogeweg, C. Sánchez, J. Melendez, P. Maduskar, A. Story, A. Hayward and B. van Ginneken, "Foreign object detection and removal to improve automated analysis of chest radiographs", Medical Physics, 2013;40(7):071901.
  • L. Hogeweg, C. Sánchez, P. de Jong, P. Maduskar and B. van Ginneken, "Clavicle segmentation in chest radiographs", Medical Image Analysis, 2012;16(8):1490 - 1502.
  • L. Hogeweg, C. Mol, P. de Jong, R. Dawson, H. Ayles and B. van Ginneken, "Fusion of local and global detection systems to detect tuberculosis in chest radiographs", Medical Image Computing and Computer-Assisted Intervention, 2010;6363:650-657.
  • Y. Arzhaeva, D. Tax and B. van Ginneken, "Dissimilarity-based classification in the absence of local ground truth: application to the diagnostic interpretation of chest radiographs", Pattern Recognition, 2009;42(9):1768-1776.
  • Y. Arzhaeva, M. Prokop, D. Tax, P. de Jong, C. Schaefer-Prokop and B. van Ginneken, "Computer-aided detection of interstitial abnormalities in chest radiographs using a reference standard based on computed tomography", Medical Physics, 2007;34(12):4798-4809.
  • B. van Ginneken, M. Stegmann and M. Loog, "Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database", Medical Image Analysis, 2006;10(1):19-40.
  • B. van Ginneken, S. Katsuragawa, B. ter Haar Romeny, K. Doi and M. Viergever, "Automatic detection of abnormalities in chest radiographs using local texture analysis", IEEE Transactions on Medical Imaging, 2002;21(2):139-149.
  • R. Philipsen, "Automated chest radiography reading. Improvements, validation, and cost-effectiveness analysis", PhD thesis, 2019.
  • P. Maduskar, "Automated analysis of tuberculosis in chest radiographs", PhD thesis, 2015.
  • J. Melendez, "Improving computer-aided detection systems through advanced pattern recognition techniques", PhD thesis, 2015.
  • L. Hogeweg, "Automatic detection of tuberculosis in chest radiographs", PhD thesis, 2013.
  • B. van Ginneken, "Computer-aided diagnosis in chest radiography", PhD thesis, 2001.