Segmentation of pectoral muscle using the adaptive gamma corrections
- 139 Downloads
Accurate segregation of pectoral muscles is very crucial in breast cancer detection. Pectoral segmentation is a challenging task due to heterogeneous tissues densities, neighborhood complexities and breast shape variabilities. This paper presents an adaptive gamma correction method for pectoral suppression in mammograms. The proposed algorithm is adaptive to variations in shape, density of tissues and the curvature of pectoral boundary i.e. straight line or curved pectoral boundary. The method utilizes the morphological information of mammograms to discriminate the breast parenchyma from the rest of breast region. The adaptive gamma corrections enhance the mammograms according to tissues densities and provide a separation boundary between breast region and pectoral parenchymal. The method is tested on three types of tissues densities present in MIAS dataset i.e. Fatty, Fatty-glandular and Dense tissues. The goodness of segmentation is measured using jaccard similarity index between the ground truth and segmented regions. The proposed methods successfully detected 98.45 % of the pectoral regions and have an overall 92.79 % jaccard similarity index with the ground truth. Moreover, evaluation by experts also confirms good performance of the proposed method.
KeywordsBreast cancer Pectoral suppression Edge detection Adaptive gamma correction Interpolation
The work is supported by URIF grant 0153AA-B52.
The authors are thankful to Virginie Briantais, Radiologist at Jean Villar Clinic, 33520 Bruges, France & Dr Fakhreddine Ababsa, image processing Expert, Evry University, 91020 Evry, France.
- 5.Dense B, Dense C (2013) Autodensity: an automated method to measure mammographic breast density that predicts breast cancer risk and screening outcomesGoogle Scholar
- 7.Duarte M, Alvarenga A, Azevedo C, Infantosi A, Pereira W (2012) Estimating the pectoral muscle and the nipple positions in mammographies using morphological filters. In: XXIII Congresso Brasileiro em Engenharia Biomédica, vol 52Google Scholar
- 10.Galdran A, Picón A, Garrote E, Pardo D (2015) Pectoral muscle segmentation in mammograms based on cartoon-texture decomposition. In: Pattern recognition and image analysis. Springer, pp 587–594Google Scholar
- 13.Hacking D, Pacifci S Craniocaudal view. https://radiopaedia.org/articles/craniocaudal-view. Accession date 15.11.2016
- 14.Hacking D, Pacifci S Mediolateral view. https://radiopaedia.org/articles/mediolateral-oblique-view. Accession date 15.11.2016
- 15.He W, Juette A, Denton ER, Oliver A, Martí R, Zwiggelaar R (2015) A review on automatic mammographic density and parenchymal segmentation. Int J Breast CancerGoogle Scholar
- 16.Keller B, Nathan D, Wang Y, Zheng Y, Gee J, Conant E, Kontos D (2011) Adaptive multi-cluster fuzzy c-means segmentation of breast parenchymal tissue in digital mammography. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 562–569Google Scholar
- 21.Matsubara T, Yamazaki D, Kato M, Hara T, Fujita H, Iwase T, Endo T (2001) An automated classification scheme for mammograms based on amount and distribution of fibroglandular breast tissue density. In: International congress series, vol 1230. Elsevier, pp 545–552Google Scholar
- 24.Olsén C, Mukhdoomi A (2007) Automatic segmentation of fibroglandular tissue. In: Image analysis. Springer, pp 679–688Google Scholar
- 25.Raba D, Oliver A, Martí J, Peracaula M, Espunya J (2005) Breast segmentation with pectoral muscle suppression on digital mammograms. In: Iberian conference on pattern recognition and image analysis. Springer, pp 471–478Google Scholar
- 26.Society AC (2015) Global cancer facts & figures, 3rd edn. http://www.cancer.org/acs/groups/content/research/documents/document/acspc-044738.pdf
- 28.Suckling J, Parker J, Dance D, Astley S, Hutt I, Boggis C, Ricketts I, Stamatakis E, Cerneaz N, Kok S et al (1994) The mammographic image analysis society digital mammogram database. In: Exerpta Medica. International congress series, vol 1069, pp 375–378Google Scholar
- 29.Wirth MA (2006) Performance evaluation of cade algorithms in mammography. Recent Adv Breast Imag Mammograph Comput-Aided Diag Breast Cancer:640–671Google Scholar
- 31.Zhang YD, Wang SH, Liu G, Yang J (2016) Computer-aided diagnosis of abnormal breasts in mammogram images by weighted-type fractional fourier transform. Adv Mech Eng 8(2):1687814016634,243Google Scholar