COMPUTATIONAL ANALYSIS BASED ON ARTIFICIAL NEURAL NETWORKS FOR AIDING IN DIAGNOSING OSTEOARTHRITIS OF THE LUMBAR SPINE.

Autor:	Veronezi CC; Undergraduate Student in Medicine - Universidade do Extremo Sul Catarinense (UNESC), SC, Brazil., de Azevedo Simões PW; PhD Student in Health Sciences - Universidade do Extremo Sul Catarinense (UNESC), Master's Degree in Computer Science - Universidade Federal de Santa Catarina (UFSC), Professor in Medical Informatics at the Universidade do Extremo Sul Catarinense (UNESC), SC, Brazil., Dos Santos RL; Specialist in Orthopedics and Traumatology- Hospital Regional de São José, Specialist in Surgery of the Hand and Microsurgery at the Universidade de São Paulo (USP), Professor of Orthopedics at the Universidade do Extremo Sul Catarinense (UNESC), SC, Brazil., da Rocha EL; Master's Degree in Electrical Engineering - Universidade Federal de Santa Catarina, Bachelor's Degree in Computer Science - Universidade do Extremo Sul Catarinense (UNESC), SC, Brazil., Meláo S; Undergraduate Student in Medicine - Universidade do Extremo Sul Catarinense (UNESC)., de Mattos MC; PhD Student in Biomedical Engineering - Federal University of Santa Catarina (UFSC), Master's Degree in Computer Science - Federal University of Santa Catarina (UFSC), Professor of Artificial Intelligence at the Universidade do Extremo Sul Catarinense (UNESC), SC, Brazil., Cechinel C; PhD Student in Information, Documentation and Knowledge - Universidade de Alcalá (UAH) - Spain; Master's Degree in Computer Sciences - Universidade Federal de Santa Catarina (UFSC), SC, Brazil.
Jazyk:	angličtina
Zdroj:	Revista brasileira de ortopedia [Rev Bras Ortop] 2015 Dec 06; Vol. 46 (2), pp. 195-9. Date of Electronic Publication: 2015 Dec 06 (Print Publication: 2011).
DOI:	10.1016/S2255-4971(15)30239-1
Abstrakt:	Objective: To ascertain the advantages of applying artificial neural networks to recognize patterns on lumbar spine radiographies in order to aid in the process of diagnosing primary osteoarthritis. Methods: This was a cross-sectional descriptive analytical study with a quantitative approach and an emphasis on diagnosis. The training set was composed of images collected between January and July 2009 from patients who had undergone lateral-view digital radiographies of the lumbar spine, which were provided by a radiology clinic located in the municipality of Criciúma (SC). Out of the total of 260 images gathered, those with distortions, those presenting pathological conditions that altered the architecture of the lumbar spine and those with patterns that were difficult to characterize were discarded, resulting in 206 images. The image data base (n = 206) was then subdivided, resulting in 68 radiographies for the training stage, 68 images for tests and 70 for validation. A hybrid neural network based on Kohonen self-organizing maps and on Multilayer Perceptron networks was used. Results: After 90 cycles, the validation was carried out on the best results, achieving accuracy of 62.85%, sensitivity of 65.71% and specificity of 60%. Conclusions: Even though the effectiveness shown was moderate, this study is still innovative. The values show that the technique used has a promising future, pointing towards further studies on image and cycle processing methodology with a larger quantity of radiographies.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu