Estimación del Grado de Afectación Pulmonar por COVID-19 Mediante la Clasificación Supervisada de la Imagen de Rayos X

Eduardo  Garea Llano; Hector Adrian Castellanos Loaces; Eduardo Martínez Montes; Evelio González Dalmau

doi:10.5281/zenodo.5545908

Autores/as

Eduardo Garea Llano Centro de Neurociencias de Cuba
Hector Adrian Castellanos Loaces Centro de Neurociencias de Cuba
Eduardo Martínez Montes Centro de Neurociencias de Cuba
Evelio González Dalmau Centro de Neurociencias de Cuba

DOI:

https://doi.org/10.5281/zenodo.5545908

Palabras clave:

Aprendizaje automático; Clasificación supervisada; COVID-19; Imágenes de rayos x; Procesamiento digital de imágenes.

Resumen

El trabajo presenta la propuesta de un índice de afectación de los pulmones en imágenes de rayos x de tórax en pacientes diagnosticados con COVID-19 en estado grave de la enfermedad. El índice se obtiene a partir de un algoritmo que combina métodos de procesamiento digital de imágenes y aprendizaje automático para la segmentación de la región pulmonar, la evaluación de su calidad y la clasificación de la imagen segmentada de los pulmones.

Los resultados alcanzados en los experimentos realizados en imágenes de pacientes sanos y afectados por COVID-19 mostraron altos valores de sensibilidad y especificidad en la clasificación. Por otra parte, se estudió la variación de los valores del índice con respecto a variables clínicas en series de tiempo de imágenes de pacientes con COVID 19 ingresados en las unidades de terapia intensiva de hospitales de La Habana, Cuba. El comportamiento de la relación entre el índice y la evolución de la respuesta clínica de los pacientes, evidenció que pudiera ser utilizado como un indicador de la efectividad de los tratamientos y protocolos aplicados.

Citas

Baratella E, Crivelli P, Marrocchio C, Bozzato AM, De Vito A, Madeddu G (2020). Severity of lung involvement on chest X-rays in SARS-coronavirus-2 infected patients as a possible tool to predict clinical progression: an observational retrospective analysis of the relationship between radiological, clinical, and laboratory data. J Bras Pneumol. 2020; 46(5):20200226.

Batista. J.A, Araujo-Filho. M., Sawamura Y., Nathan-Costa A., Cerri G.G. , Higa-Nomura C (2020). COVID-19 pneumonia: what is the role of imaging in diagnosis?. J Bras Pneumol. 2020;46(2):e20200114. https://dx.doi.org/10.36416/1806-3756/e20200114.

Bishop C.M. (2006), Pattern Recognition and Machine Learning. Springer.2006.

Borghesi A., Zigliani A., Masciullo R., Golem S., Maculotti P., Farina D., and Maroldi R (2020) . Radiographic severity index in COVID-19 pneumonia: relationship to age and sex in 783 Italian patients. Radiol Med. 2020 May 1: 1–4.

Chen F., Pan J., Han Y. An Effective Image Quality Evaluation Method of X-Ray Imaging System. Journal of Computational Information Systems 7:4 (2011) 1278-1285.

Garea-Llano E, García-Vázquez M, Colores -Vargas JM, Zamudio-Fuentes LM, Ramírez-Acosta AA (2018). Optimized robust multi-sensor scheme for simultaneous video and image iris recognition. Pattern Recognition Letters 2018, 101: 44-45.

Gelbowitz A. (2021). Decision Trees and Random Forests Guide: An Overview Of Decision Trees And Random Forests: Machine Learning Design Patterns. Independently Published, 2021.

Gómez, O., Mesejo, P., Ibáñez, O. (2020). Deep architectures for high-resolution multi-organ chest X-ray image segmentation. Neural Comput & Applic 32, 15949–15963 (2020). https://doi.org/10.1007/s00521-019-04532-y

Gonzalez R.C., Woods R.E. (2018), Digital Image Processing, 4th edition, 2018, 8 Image Compression and Watermarking.

He L., Ren X., Gao Q., Zhao X., Yao B., Chao Y (2017)., The connected-component labeling problem: A review of state-of-the-art algorithms, Pattern Recognition, Volume 70, 2017, Pages 25-43, ISSN 0031-3203.

Huang C., Wang Y., Li X., Ren L., Zhao J., Hu Y., Zhang L., Fan G., Xu J., Gu X., Cheng Z., Yu T., Xia J., Wei Y., Wu W., Xie X., Yin W., Li H., Liu M., Xiao Y., Gao H., Guo L., Xie J., Wang G., Jiang R., Gao Z., Jin Q., Wang J., Cao B. (2020). Clinical features of patients infected with 2019 novel coronavirus in Wuhan, china. The Lancet, 395(10223), 2020. 1

Kanne J P., MD • Brent P. Little, MD • Jonathan H. Chung, MD • Brett M. Elicker, MD • Loren H. Ketai, MD (2020). Essentials for Radiologists on COVID-19: An Update-Radiology Scientific Expert Panel. Radiology Vol. 296, No. 2.

Koonsanit K., Thongvigitmanee S., Pongnapang N. and Thajchayapong P (2017)., "Image enhancement on digital x-ray images using N-CLAHE," 2017 10th Biomedical Engineering International Conference (BMEiCON), Hokkaido, Japan, 2017, pp. 1-4, doi: 10.1109/BMEiCON.2017.8229130.

Laghi, A. (2020). Cautions about radiologic diagnosis of COVID-19 infection driven by ar-tificial intelligence. The Lancet Digital Health, 2(5), e225. https://doi.org/10.1016/S2589-7500(20)30079-0

Liang W, Liang H, Ou L, Chen B, Chen A, Li C. (2020). Development and Validation of a Clinical Risk Score to Predict the Occurrence of Critical Illness in Hospitalized Patients With COVID-19. JAMA Intern Med. 2020; 180(8):1081-1089.https://doi.org/10.1001/jamainternmed.2020.2033

López-Cabrera, J. D., Portal Díaz, J. A., Orozco Morales, R., & Pérez Díaz, M. (2020). Revisión crítica sobre la identificación de COVID-19 a partir de imágenes de rayos x de tórax usando técnicas de inteligencia artificial. Revista Cubana De Transformación Digital, 1(3), 67–99. Recuperado a partir de https://rctd.uic.cu/rctd/article/view/103

Ming-Yen N., Lee Y. P. , Yang J., Yang F. , Li X. , Wang Hongx , Lui M.M. , Lo C. , Leung B. , Khong PL., Hui C. , Yuen K. , Kuo M.D. (2020) . Imaging profile of the COVID-19 infection: Radiologic findings and literature review. Radiology: Cardiothogracic Imaging, 2(1), 2020. 1

Monaco C.G., Zaottini F., Schiaffino S., Villa A., Della-Pepa G., Carbonaro L.A., Menicagli L., Cozzi A., Carriero S., Arpaia F., Di Leo G., Astengo D., Rosenberg I. and Sardanelli F.(2020). Chest x-ray severity score in COVID-19 patients on emergency department admission: a two-centre study. European Radiology Experimental (2020) 4:68 https://doi.org/10.1186/s41747-020-00195-w

Otsu N. (1979). A threshold selection method from gray-level histograms. IEEE Trans. Sys., Man., Cyber. 9: 62-66.

Samajdar T., Quraishi M.I. (2015) Analysis and Evaluation of Image Quality Metrics. In: Mandal J., Satapathy S., Kumar Sanyal M., Sarkar P., Mukhopadhyay A. (eds) Information Systems Design and Intelligent Applications. Advances in Intelligent Systems and Computing, vol 340. Springer, New Delhi. https://doi.org/10.1007/978-81-322-2247-7_38

Satendra P. S., Gaurav B., (2020). Chapter 1 - Perceptual hashing-based novel security framework for medical images, Editor(s): Amit Kumar Singh, Mohamed Elhoseny, In Intelligent Data-Centric Systems, Intelligent Data Security Solutions for e-Health Applications, Academic Press, 2020, Pages 1-20, ISBN 9780128195116,https://doi.org/10.1016/B978-0-12-819511-6.00001-7.

Schalekamp S, Huisman M, van Dijk RA, Boomsma MF, Freire Jorge PJ, de Boer WS (2020). Model-based Prediction of Critical Illness in Hospitalized Patients with COVID-19 [published online ahead of print, 2020 Aug 13]. Radiology. 2020; 202723.https://doi.org/10.1148/radiol.2020202723

Sprawls P.(13 de Abril de 2021) Image Characteristics and Quality. In Physical Principles of Medical Imaging. Online, Resources for Learning and Teaching http://www.sprawls.org/resources

Teixeira P.P, Loureiro-Irion K., Marchiori E. (2020). COVID-19: chest X-rays to predict clinical outcomes. Jornal Brasileiro de Pneumologia. vol.46 no.5 São Paulo, 2020. Epub Nov 02, 2020. http://dx.doi.org/10.36416/1806-3756/e20200464

Toriwaki J-I, Suenaga Y, Negoro T, Fukumura T (1973) Pattern recognition of chest X-ray images. Comput Vis Graph 2(3):252–271

Wechsler H, Sklansky J (1977) Finding the rib cage in chest radiographs. Pattern Recognition 9(1):21–30

Zhu J, Shen B, Abbasi A, Hoshmand-Kochi M, Li H, Duong TQ (2020). Deep transfer learning artificial intelligence accurately stages COVID-19 lung disease severity on portable chest radiographs. PLoS One. 2020; 15(7): e0236621. https://doi.org/10.1371/journal.pone.0236621

Zhu Y, Prummer S, Wang P, Chen T, Comaniciu D, Ostermeier M (2009). Dynamic layer separation for coronary DSA and enhancement in fluoroscopic sequences. In: MICCAI, pp 877–884

Zuiderveld K. (1994). “Graphics gems iv,” chapter Contrast Limited Adaptive Histogram Equalization, pp. 474–485. Academic Press Professional, Inc., San Diego, CA, USA, 1994.