System of Digital Vision for X-Ray Lung Pathology and Foreign Body Detection

DOI: https://doi.org/10.29296/25877305-2020-05-07
Download full text PDF
Issue: 
5
Year: 
2020

E. Zhukov(1); D. Blinov(1), MD; V. Leontiev(2); P. Gavrilov(3), Candidate of Medical Sciences; U. Smolnikova(3); Professor E. Blinova(4), MD; I. Kamishanskaya(5), Candidate of Medical Sciences (1)Care Mentor AI, Moscow (2)Inozemtzev Moscow State Clinical Hospital, Moscow (3)Saint-Petersburg Research Institute of Phthisiopulmonology (4)I.M. Sechenov First Moscow State Medical University (Sechenov University) (5)Saint-Petersburg State University

Goal and objectives: to develop an effective computer vision system for detecting pathology and foreign bodies of medical and unmedical origin on plain chest radiographs. Material and methods: in order to build the model, aggregation of convolutional artificial neural networks of the InceptionV3, ResNet-50 and GlobalAveragePooling architectures was used. The outputs from all models were combined into a single vector and used as input for the boosting model, which was used as the XGBoost model. For training and testing the system, 276840 anonymized chest x-ray in a frontal view were used. Results. A number of computer vision models have been developed for the analysis of X-ray examinations of the lungs. To achieve a satisfactory balance between the prediction accuracy indicators, a decision threshold of 0.4 was chosen empirically. Such a balance makes it possible to reduce the number of false-negative model predictions and increase the number of cases where pathological changes are suspected. Conclusions. The developed model of computer vision can be considered as an effective assistant to the radiologists in the analysis of chest x-ray images, allowing them to create a list of priority images for immediate and delayed analysis and description.
Keywords: 
neural network
artificial intelligence
lung pathology
foreign body
detection

It appears your Web browser is not configured to display PDF files. Download adobe Acrobat или click here to download the PDF file.

References: 
  1. Yao L., Poblenz E., Dagunts D. et al. Learning to diagnose from scratch by exploiting dependencies among labels. arXiv:1710.10501v2 [cs.CV]. 2018; 1: 1–18.
  2. Sabih D.E., Sabih A., Sabih Q. et al. Image perception and interpretation of abnormalities; can we believe our eyes? Can we do something about it? Insights Imaging. 2011; 2: 47–55. https://doi.org/10.1007/s13244-010-0048-1
  3. Makary M.A., Daniel M. Medical error: the third leading cause of death in the US. BMJ. 2016; 353: i2139. https://doi.org/10.1136/bmj.i2139
  4. Kohn L.T., Corrigan J.M., Donaldson M.S. et al. To err is human: building a safer health system. Washington, DC: National Academies Press, 2000. pp. 287. https://doi.org/10.17226/9728
  5. Busby L.P., Courtier J.L., Glastonbury C.M. Bias in radiology: the How and Why of misses and misinterpretation. Radiographics. 2018; 38: 236–47. https://doi.org/10.1148/rg.2018170107
  6. Waite S., Scott J., Gale J. et al. Interpretative error in radiology. AJR. 2017; 208: 739–49. https://doi.org/10.2214/ajr.16.16963
  7. Ropp A., Waite S., Reede D. et al. Did I miss that: subtle and commonly missed findings on chest radiographs. Curr Probl Diagn Radiol. 2015; 44: 277–89. https://doi.org/10.1067/j.cpradiol.2014.09.003
  8. Del Ciello A., Franchi D., Contegiacomo A. et al. Missed lung cancer: when, where, and why? Diagn Interv Radiol. 2017; 23 (2): 118–26. https://doi.org/10.5152/dir.2016.16187
  9. Garland L.H. On the scientific evaluation of diagnostic procedures. Radiology. 1949; 52: 309–28. https://doi.org/10.1148/52.3.30910
  10. Er O., Yumusak N., Temurtas F. Chest diseases diagnosis using artificial neural networks. Expert Sys Appl. 2010; 37 (12): 7648–55. https://doi.org/10.1016/j.eswa.2010.04.078
  11. Er O., Sertkaya C., Temurtas F. et al. A comparative study on chronic obstructive pulmonary and pneumonia diseases diagnosis using neural networks and artificial immune system. J. Med. Sys. 2009; 33 (6): 485–92. https://doi.org/10.1007/s10916-008-9209-x
  12. Khobragade S., Tiwari A., Pati C.Y. et al. Automatic detection of major lung diseases using chest radiographs and classification by feed-forward artificial neural network. Proceedings of 1st IEEE International Conference on Power Electronics. Intelligent Control and Energy Systems (ICPEICES-2016) 2016 IEEE, p. 1–5. https://doi.org/10.1109/icpeices.2016.7853683
  13. Litjens G., Kooi T., Bejnordi E.B. et al. A survey on deep learning in medical image analysis. Medical Image Analysis. 2017; 42: 60–88. https://doi.org/10.1016/j.media.2017.07.005
  14. Albarqouni S., Baur C., Achilles F. et al. Aggnet: deep learning from crowds for mitosis detection in breast cancer histology images. IEEE Transactions on Medical Imaging. 2016; 35 (5): 1313–21. https://doi.org/10.1109/tmi.2016.2528120
  15. Avendi M.R., Kheradvar A., Jafarkhani H.A. combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI. Medical Image Analysis. 2016; 30: 108–19. https://doi.org/10.1016/j.media.2016.01.005
  16. Shin H.-C., Roberts K., Lu L. et al. Learning to read chest X-rays: recurrent neural cascade model for automated image annotation. Cornel University library. 2016. https://arxiv.org/abs/1603.08486.
  17. Wang X.S., Peng Y.F., Lu L. et al. ChestX-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). Honolulu, HI, USA: IEEE. 2017. p. 3462–71. http://dx.doi.org/10.1109/CVPR.2017.369
  18. XGBoost Documentation,