Automated Lung Region Segmentation in Pediatric Chest Radiography

Afonso Ueslei Fonseca; Juliana de Paula Félix; Gabriel da Silva Vieira; Deborah  Fernandes; Fabrizzio Soares

doi:10.22456/2175-2745.130579

Authors

Afonso Ueslei Fonseca Universidade Federal de Goiás https://orcid.org/0000-0001-5517-2051
Juliana Félix Universidade Federal de Goiás https://orcid.org/0000-0003-4095-1639
Gabriel Vieira Instituto Federal Goiano - Campus Uruta´i https://orcid.org/0000-0002-6976-7811
Deborah Fernandes Universidade Federal de Goiás
Fabrizzio Soares Universidade Federal de Goiás https://orcid.org/0000-0003-1598-1377

DOI:

https://doi.org/10.22456/2175-2745.130579

Keywords:

Lung segmentation, chest radiograph, rules, image processing

Abstract

In chest radiographs, the automatic identification of regions, structures, or objects that compose it can help the professional in the area to perform their reading and analysis more assertively, promoting the improvement and efficiency of the diagnosis. In the present work, we propose a method to segment the lung fields in pediatric chest radiographs (PCXR). Based on digital image processing operations and rules, the proposal is evaluated on a PCXR images dataset. The results are satisfactory for the different classes of images analyzed, indicating that the proposed method can be helpful in the preprocessing stages of more complex flows.

Downloads

Download data is not yet available.

Author Biographies

Juliana Félix, Universidade Federal de Goiás

Juliana Félix is a PhD student in Computer Science at Federal University of Goiás (UFG), Brazil. She has a Master of Science degree in Computer Science (2018) and a Bachelor degree in Computer Science (2015), both from UFG. During my undergraduate studies, I was awarded a visiting scholarship (2013--2014) at the University of Manitoba (UofM), Canada, where she has also worked on a summer project at the Faculty of Science. My research interests include Machine Learning, Internet of Things, and Theoretical Computer Science.

Gabriel Vieira, Instituto Federal Goiano - Campus Uruta´i

Started his PhD in Computer Science in 2019. Master in Computer Science (UFG). Master in Music (UFG). Bachelor in Software Engineering (UFG). Degree in Music Education (UFG). He specializes in Higher Education Teaching. Teacher of Basic, Technical and Technological Education at IF Goiano - Campus Urutaí. Areas of interest: computer vision, software construction, software design, project management, computational intelligence.

Deborah Fernandes, Universidade Federal de Goiás

Deborah Fernandes is a professor at the Institute of Informatics at the Federal University of Goiás – Campus Samambaia, Goiânia/Goiás. She is a Computer Scientist (Pontifical Catholic University of Goiás), a Master in Electrical Engineering with emphasis on Computational Vision (School of Engineering - University of Brasília/DF), and PhD in Electronic Systems Engineering and Automation (School of Engineering - University of Brasília / DF) with an emphasis on social network data analysis and decision support.

Fabrizzio Soares, Universidade Federal de Goiás

Fabrizzio Soares is a professor of Computer Science, Information Systems and Software Engineering at INF/UFG. His research interests include Computer Vision, Human Computer Interaction, Machine Learning and Programming topics. He is the leader of the Pixellab group, which develops solutions for accesibilty, Precision Agriculture, and Interactive Systems.

References

ORGANIZATION, W. H. et al. Chest radiography in tuberculosis detection: summary of current WHO recommendations and guidance on programmatic approaches. [S.l.], 2016.

NEFOUSSI, S.; AMAMRA, A.; AMAROUCHE, I. A. A comparative study of chest x-ray image enhancement techniques for pneumonia recognition. In: SPRINGER. Advances in Computing Systems and Applications: Proceedings of the 4th Conference on Computing Systems and Applications. [S.l.], 2021. p. 276–288.

FONSECA, A. U. et al. X-ray image enhancement: A technique combination approach. In: 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI). [S.l.: s.n.], 2019. p. 1686–1690.

RUI, W.; GUOYU, W. Medical x-ray image enhancement method based on tv-homomorphic filter. In: IEEE. 2017 2nd International Conference on Image, Vision and Computing (ICIVC). [S.l.], 2017. p. 315–318.

ROY, S.; SANTOSH, K. Analyzing overlaid foreign objects in chest x-rays—clinical significance and artificial intelligence tools. In: MULTIDISCIPLINARY DIGITAL PUBLISHING INSTITUTE. Healthcare. [S.l.], 2023. v. 11, n. 3, p. 308.

MEYER, T. J. et al. Systematic analysis of button batteries’, euro coins’, and disk magnets’ radiographic characteristics and the implications for the differential diagnosis of round radiopaque foreign bodies in the esophagus. International Journal of Pediatric Otorhinolaryngology, v. 132, p. 109917, 2020.

FONSECA, A. U. et al. Foreign artifacts detection on pediatric chest x-ray. In: IEEE. 2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE). [S.l.], 2020. p. 1–4.

FONSECA, A. et al. Automatic orientation identification of pediatric chest x-rays. In: 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC). [S.l.: s.n.], 2020. p. 1449–1454.

Reza, S.; Amin, O. B.; Hashem, M. M. A. A novel feature extraction and selection technique for chest x-ray image view classification. In: 2019 5th International Conference on Advances in Electrical Engineering (ICAEE). [S.l.: s.n.], 2019. p. 189–194.

SANTOSH, K.; WENDLING, L. Angular relational signature-based chest radiograph image view classification. Medical & biological engineering & computing, Springer, v. 56, n. 8, p. 1447–1458, 2018.

SHI, F. et al. Review of artificial intelligence techniques in imaging data acquisition, segmentation, and diagnosis for covid-19. IEEE Reviews in Biomedical Engineering, v. 14, p. 4–15, 2021. ISSN 1941-1189.

FAN, D.-P. et al. Inf-net: Automatic covid-19 lung infection segmentation from ct images. IEEE Transactions on Medical Imaging, v. 39, n. 8, p. 2626–2637, Aug 2020. ISSN 1558-254X.

FONSECA, A. U.; FELIX, J. P.; SOARES, F. Segmentação da regi ̃ao pulmonar em radiografias pediátricas de tórax. In: SBC. Anais da X Escola Regional de Informática de Goías. [S.l.], 2022. p. 48–59.

TEIXEIRA, L. O. et al. Impact of lung segmentation on the diagnosis and explanation of covid-19 in chest x-ray images. arXiv preprint arXiv:2009.09780, 2020.

GONZALEZ, R. C.; WOODS, R. E. Processamento digital de imagens. 3. ed. [S.l.]: Pearson Prentice Hall, São Paulo, 2010.

TAHERI, M.; RASTGARPOUR, M.; KOOCHARI, A. A novel method for medical image segmentation based on convolutional neural networks with sgd optimization. Journal of Electrical and Computer Engineering Innovations (JECEI), Shahid Rajaee Teacher Training University, v. 9, n. 1, p. 37–46, 2021.

CLARKE, L. et al. MRI segmentation: methods and applications. Magnetic resonance imaging, Elsevier, v. 13, n. 3, p. 343–368, 1995.

CHEN, J. et al. Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306, 2021.

HESAMIAN, M. H. et al. Deep learning techniques for medical image segmentation: achievements and challenges. Journal of digital imaging, Springer, v. 32, n. 4, p. 582–596, 2019.

ZHOU, Z. et al. Unet++: A nested u-net architecture for medical image segmentation. In: Deep learning in medical image analysis and multimodal learning for clinical decision support. [S.l.]: Springer, 2018. p. 3–11.

MAHMOOD, F. et al. Deep adversarial training for multi-organ nuclei segmentation in histopathology images. IEEE Transactions on Medical Imaging, v. 39, n. 11, p. 3257–3267, Nov 2020. ISSN 1558-254X.

GU, Z. et al. Ce-net: Context encoder network for 2d medical image segmentation. IEEE Transactions on Medical Imaging, v. 38, n. 10, p. 2281–2292, Oct 2019. ISSN 1558-254X.

RONNEBERGER, O.; FISCHER, P.; BROX, T. U-net: Convolutional networks for biomedical image segmentation. In: SPRINGER. International Conference on Medical image computing and computer-assisted intervention. [S.l.], 2015. p. 234–241.

OH, Y.; PARK, S.; YE, J. C. Deep learning covid-19 features on cxr using limited training data sets. IEEE transactions on medical imaging, IEEE, v. 39, n. 8, p. 2688–2700, 2020.

GORDIENKO, Y. et al. Deep learning with lung segmentation and bone shadow exclusion techniques for chest x-ray analysis of lung cancer. In: SPRINGER. International Conference on Computer Science, Engineering and Education Applications. [S.l.], 2018. p. 638–647.

LI, X. et al. Automatic lung field segmentation in x-ray radiographs using statistical shape and appearance models. Journal of Medical Imaging and Health Informatics, v. 6, n. 2, p. 338–348, 2016. ISSN 21567018.

GINNEKEN, B. V. Computer-aided diagnosis in chest radiography. Tese (Doutorado) — University Medical Center Utrecht, 6 2001.

PENG, T. et al. Hybrid automatic lung segmentation on chest ct scans. IEEE Access, IEEE, v. 8, p. 73293–73306, 2020.

CANDEMIR, S.; ANTANI, S. A review on lung boundary detection in chest x-rays. International journal of computer assisted radiology and surgery, Springer, v. 14, n. 4, p. 563–576, 2019.

CANDEMIR, S.; JAEGER, S. et al. Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE Transactions on Medical Imaging, v. 33, n. 2, p. 577–590, 2014. ISSN 02780062.

JAEGER, S. et al. Automatic screening for tuberculosis in chest radiographs: a survey. Quantitative imaging in medicine and surgery, v. 3, n. 2, p. 89–99, 2013. ISSN 2223-4292.

XUE, Z. et al. Foreign object detection in chest x-rays. In: IEEE. Bioinformatics and Biomedicine (BIBM), 2015 IEEE International Conference on. [S.l.], 2015. p. 956–961.

HOGEWEG, L. et al. Clavicle segmentation in chest radiographs. Medical Image Analysis, Elsevier B.V., v. 16, n. 8, p. 1490–1502, 2012. ISSN 13618415. Disponível em: ⟨http://dx.doi.org/10.1016/j.media.2012.06.009⟩.

SCHALEKAMP, S. et al. The effect of supplementary bone-suppressed chest radiographs on the assessment of a variety of common pulmonary abnormalities: Results of an observer study. Journal of thoracic imaging, LWW, v. 31, n. 2, p. 119–125, 2016.

HOGEWEG, L.; SANCHEZ, C. I.; Van Ginneken, B. Suppression of translucent elongated structures: Applications in chest radiography. IEEE Transactions on Medical Imaging, v. 32, n. 11, p. 2099–2113, 2013. ISSN 02780062.

PATIL, S.; UDUPI, D. V. Preprocessing to be considered for mr and ct images containing tumors. IOSR Journal Electrical and Electronics Engineering, v. 1, n. 4, p. 54–57, 2012.

IAKOVIDIS, D. K.; SAVELONAS, M. A.; PAPAMICHALIS, G. Robust model-based detection of the lung field boundaries in portable chest radiographs supported by selective thresholding. Measurement Science and Technology, v. 20, n. 10, p. 104019, 2009. ISSN 0957-0233.

TSEVAS, S.; IAKOVIDIS, D. K. Measuring the relative extent of pulmonary infiltrates by hierarchical classification of patient-specific image features. Measurement Science and Technology, v. 22, n. 11, p. 114017, 2011. ISSN 09570233.

ANDRADE, A. L. S. S. de et al. Effectiveness of haemophilus influenzae b conjugate vaccine on childhood pneumonia: a case-control study in brazil. International journal of epidemiology, Oxford University Press, v. 33, n. 1, p. 173–181, 2004.

FONSECA, A. U.; OLIVEIRA, L. L. G.; SOARES, F. A. A. M. N. Detecção de artefatos estranhos em radiografias de tórax. In: XV CBIS- Congresso Brasileiro de Informática em Saúde. Goiânia, Brasil: [s.n.], 2016. p. 721–730.

CANDEMIR, S.; ANTANI, S. et al. Lung boundary detection in pediatric chest x-rays. In: Proc. SPIE, Medical Imaging 2015: PACS and Imaging Informatics: Next Generation and Innovations. [S.l.: s.n.], 2015. v. 9418, p. 94180Q–94180Q–6.

REINKE, A. et al. Understanding metric-related pitfalls in image analysis validation. arXiv preprint arXiv:2302.01790, 2023.

VIDAL, P. L. et al. Multi-stage transfer learning for lung segmentation using portable x-ray devices for patients with covid-19. Expert Systems with Applications, Elsevier, v. 173, p. 114677, 2021.

HUYNH, H. T.; ANH, V. N. N. A deep learning method for lung segmentation on large size chest x-ray image. In: 2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF). [S.l.: s.n.], 2019. p. 1–5.

AL-EIADEH, M. R. Automatic lung field segmentation using robust deep learning criteria. International Journal of Hybrid Innovation Technologies, v. 1, n. 1, p. 69–82, 2021.

CAO, F.; ZHAO, H. Automatic lung segmentation algorithm on chest x-ray images based on fusion variational auto-encoder and three-terminal attention mechanism. Symmetry, MDPI, v. 13, n. 5, p. 814, 2021.

CHAVAN, M. et al. Deep neural network for lung image segmentation on chest x-ray. Technologies, MDPI, v. 10, n. 5, p. 105, 2022.

RAJARAMAN, S. et al. Comparing deep learning models for population screening using chest radiography. In: SPIE. Medical Imaging 2018: Computer-Aided Diagnosis. [S.l.], 2018. v. 10575, p. 322–332.

SRIMATHI, D. H.; ROSE, D. P. et al. A Comparative Study On Performance Of Pre-Trained Convolutional Neural Networks In Tuberculosis Detection. European Journal of Molecular & Clinical Medicine, v. 7, n. 3, p. 4852–4858, 2020.

RAJARAMAN, S. et al. Improved semantic segmentation of tuberculosis—Consistent findings in chest x-rays using augmented training of modality-specific U-Net models with weak localizations. Diagnostics, Multidisciplinary Digital Publishing Institute, v. 11, n. 4, p. 616, 2021.