A Method for Phantom Image Correction and Classification of Their Structures of Interest
Abstract
To execute the quality control of mammographic systems, the Brazilian Health Ministry demands the use of breast phantoms. Aiming to reduce the subjectivity present in the evaluation of phantom images through human visual inspection, a computerized system has been developed that uses a correction method in its digitised images, associated with the classification of its structures of interest by the visibility criterion. Comparing the results of the classification using the J48 algorithm of the WEKA package with and without image correction, this method presented a significant improvement in the effectiveness for determining structures of the phantom.References
Barufaldi B. et al. (2009) “Sistema para o Controle de Qualidade de Mamógrafos e Geração Automática de Laudos Através da Análise de Imagens de Fantoma”, V Workshop de Visão Computacional, São Paulo.
Cinti, M. N. et al. (2004) “Custom Breast Phantom for an Accurate Tumor SNR Analysis”, IEEE Transactions on Nuclear Science, vol. 51(1) 198-204.
Gonzales R.C. and Woods R.E. (2002) “Digital Image Processing”, 2nd ed. Prentice Hall.
González-Lopez, A. (2007) “Useful optical density range in film dosimetry: Limitations due to noise and saturation” Phys. Med. Biol. 52, p.321-327.
Hogge J. et al. (1999) “Quality Assurance in Mammography: Artifact Analysis”, RadioGraphics, vol. 19 503-522.
INCA – Instituto Nacional do Câncer (2009) “Estimativa 2010: incidência de câncer no Brasil / Instituto Nacional de Câncer”, ISBN 978-85-7318-161-6 (98).
Medeiros R. B. , Alves F.F.R., Ruberti E. M and Ferreira D.F.P (2002) “Influência das condições de processamento no desempenho de dois sistemas tela/filme utilizados na mamografia”, Revista Brasileira de Engenharia Biomédica, vol. 18 (2) 57-63.
Tiezzi D.G. (2010) “Câncer de mama: um futuro desafio para o sistema de saúde nos países em desenvolvimento”` Rev. Bras. Ginecol. Obstet. 32(6).
Witten I. H. and Frank, E. (2005) “Data Mining – Practical Machine Learning Tools and Techniques”. San Francisco, Elsevier, 2nd Edition.
Cinti, M. N. et al. (2004) “Custom Breast Phantom for an Accurate Tumor SNR Analysis”, IEEE Transactions on Nuclear Science, vol. 51(1) 198-204.
Gonzales R.C. and Woods R.E. (2002) “Digital Image Processing”, 2nd ed. Prentice Hall.
González-Lopez, A. (2007) “Useful optical density range in film dosimetry: Limitations due to noise and saturation” Phys. Med. Biol. 52, p.321-327.
Hogge J. et al. (1999) “Quality Assurance in Mammography: Artifact Analysis”, RadioGraphics, vol. 19 503-522.
INCA – Instituto Nacional do Câncer (2009) “Estimativa 2010: incidência de câncer no Brasil / Instituto Nacional de Câncer”, ISBN 978-85-7318-161-6 (98).
Medeiros R. B. , Alves F.F.R., Ruberti E. M and Ferreira D.F.P (2002) “Influência das condições de processamento no desempenho de dois sistemas tela/filme utilizados na mamografia”, Revista Brasileira de Engenharia Biomédica, vol. 18 (2) 57-63.
Tiezzi D.G. (2010) “Câncer de mama: um futuro desafio para o sistema de saúde nos países em desenvolvimento”` Rev. Bras. Ginecol. Obstet. 32(6).
Witten I. H. and Frank, E. (2005) “Data Mining – Practical Machine Learning Tools and Techniques”. San Francisco, Elsevier, 2nd Edition.
Published
2011-07-19
How to Cite
BARUFALDI, Bruno; CAVALCANTI, Amanda B.; BATISTA, Leonardo V.; GÓIS, Renata F.; SCHIABEL, Homero; CARVALHO, José F. G..
A Method for Phantom Image Correction and Classification of Their Structures of Interest. In: BRAZILIAN SYMPOSIUM ON COMPUTING APPLIED TO HEALTH (SBCAS), 11. , 2011, Natal/RN.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2011
.
p. 1746-1755.
ISSN 2763-8952.
