Mulet RA, Suárez CA, Noriega AM

Language: Spanish
References: 21
Page: 1-16
PDF size: 378.88 Kb.

ABSTRACT

Introduction: solitary pulmonary nodules are one of the most frequent problems in radiographic practice. They are a common incidental finding in chest studies conducted during routine clinical work.
Objective: implement a computer-assisted diagnostic system facilitating detection of solitary pulmonary nodules in multicut computerized tomography image series.
Methods: Matlab was used to develop and evaluate a set of algorithms constituting necessary components of a computer-assisted diagnostic system. The order was the following: an algorithm to extract regions of interest, another to extract characteristics, and another to detect solitary pulmonary nodules, for which several classifiers were tested. Evaluation of the algorithms was based on notes taken by specialists on the LIDC-IDRI (Lung Image Database Consortium) image collection.
Results: the segmentation method used for extraction of regions of interest made it possible to create a suitable division of the original images into significant regions. The algorithm used for detection found that the test set exhibited good accuracy (96.4%), a good sensitivity balance (91.5%), and a 0.84 rate of false positives per image.
Conclusions: the research and implementation work done is reflected in the construction of a Matlab graphic interface serving as a prototype for a computer-assisted diagnostic system which may facilitate detection of SPNs.

REFERENCES

1. Iglesias AA, Suárez A. Incidencia de cáncer: cifras alarmantes. Rev. Finlay. 2015 Mar [acceso: 25/09/2019]; 5(1): 1-3. Disponible en: http://scielo.sld.cu/scielo.php?script=sci_arttext&pid=S2221- 24342015000100001&lng=es

2. Awai K, Murao K, Ozawua A, Nakayama Y, Nakakura T, Liu D, et al. Pulmonary nodules: Estimation of malignancy at thin section helical CT –Effect of CAD on performance of radiologists. Radiology 2006; 239 (1): 276-284.

3. Mhetre RR, Sache RG. Detection of Lung Cancer Nodule on CT scan Images by using Region Growing Method. International Journal of Current Trends in Engineering & Research. 2016; 2(7):215-9.

4. Solano MJ. Nódulo Pulmonar Solitario. Rev Med Cos Cen 2016; 73 (619) 241-245.

5. Gabrielli N, Muñoz GS, Passalacqua H. Nódulo pulmonar solitario: Desafío diagnóstico y terapéutico. Cuadernos de Cirugía, 21(1), 65-74. https://doi.org/10.4206/cuad.cir.2007.v21n1-10

6. Rivero CA, Rivera Y, Borges G, Naranjo G. Algoritmo para la identificación de nódulos pulmonares solitarios en imágenes de tomografía de tórax. RCIM. 2015 Jun [acceso: 25/09/2019]; 7(1): 73-88. Disponible en: http://scielo.sld.cu/scielo.php?script=sci_arttext&pid=S1684- 18592015000100008&lng=es

7. Hua KL, Hsu CH, Hidayati SC, Cheng WH, Chen YJ. Computer-aided classification of lung nodules on computed tomography images via deep learning technique. Onco Targets Ther. 2015; 8: 2015–2022. https://doi.org/10.2147/OTT.S80733

8. Shen W, Zhou M, Yang F, Yang C, Tian J. Multi-scale Convolutional Neural Networks for Lung Nodule Classification. Ourselin S, Alexander D, Westin CF, Cardoso M, editors. Information Processing in Medical Imaging; 2015 Jun. Lecture Notes in Computer Science, 9123. Springer, Cham. https://doi.org/10.1007/978-3-319-19992-4_46

9. Souto M, Tahoces PG, Suárez JJ, et al. Detección automática de nódulos pulmonares en tomografía computarizada. Un estudio preliminar. Radiología, 50(5), 387-92. https://doi.org/10.1016/s0033-8338(08)76053-3

10. Campos V. Segmentación multicriterio para detección de nódulos pulmonares en imágenes de tomografía computarizada [PhD]. Pontifica Universidad Católica de Rio de Janeiro. Brasil. 2009: 0521380/CA.

11. Bhavanishankar K, Sudjamani MV. Techniques for detection of Solitary Pulmonary Nodules in human lung and their classification – A survey. International Journal on Cybernetics & Informatics (IJCI). 2015; 4 (1), 27-40. Doi: https://doi.org/10.5121/ijci.2015.4103

12. El-Regaily, Salsabil A, et al. Survey of Computer Aided Detection Systems for Lung Cancer in Computed Tomography. Current Medical Imaging 2018; 14(1):3-18. Doi: https://doi.org/10.2174/1573405613666170602123329

13. Bahadar K, Khaliq A, Shahid M. Correction. A Morphological Hessian Based Approach for Retinal Blood Vessels Segmentation and Denoising Using Region Based Otsu Thresholding. PLOS ONE 2016; 11(9): e0162581. https://doi.org/10.1371/journal.pone.0162581

14. Suárez JJ. Desarrollo de un sistema de diagnóstico asistido por computador para detección de nódulos pulmonares en tomografía computarizada multicorte. [PhD] Universidad de Santiago de Compostela: Servicio de Publicaciones e Intercambio Científico, 2009. Available at: http://hdl.handle.net/10347/2594

15. "Imadjust. Adjust image intensity values or colormap." 2019. Available at: https://www.mathworks.com/help/images/ref/imadjust.html.16

16. "Erode image - Matlab imerode - MathWork." 2019. Available at: https://la.mathworks.com/help/images/ref/imerode.html

17. "Morphological Reconstruction - Matlab & Simulink - MathWork." 2019. Available at: https://la.mathworks.com/help/images/understanding-morphological-reconstruction.html

18. Ammi RP, Venkata KR, Ramesh BI. Automated Pulmonary Lung Nodule Detection Using an Optimal Manifold Statistical Based Feature Descriptor and SVM Classifier. Journal of Biomedical Engineering and Medical Imaging, 2017; 4(4): 20-38. Doi: https://doi.org/10.14738/jbemi.44.3354

19. Bishop C. Pattern Recognition and Machine Learning. Springer Science+Business Media, LLC. NY 10013, USA 2006.

20. Armato III, Samuel G, McLennan, et al. Data From LIDC-IDRI. The Cancer Imaging Archive. Doi: https://doi.org/10.7937/K9/TCIA.2015.LO9QL9SX

21. Wang W, Luo J, Yang X, Lin H. Data Analysis of the Lung Imaging Database Consortium and Image Database Resource Initiative. Academic Radiology 2015; 22(4): 488-495. Doi: https://doi.org/10.1016/j.acra.2014.12.004