PHOC Descriptor Applied for Mammography Classification

Gilmário Barbosa Santos

doi:10.22456/2175-2745.89115

Authors

Gilmário Barbosa Santos UDESC

DOI:

https://doi.org/10.22456/2175-2745.89115

Abstract

This paper describes experiments with PHOC (Pyramid Histogram of Color) features descriptor in terms of capacity for representing features presented in breast radiograph (also known as mammography). Patches were taken from regions in digital mammographies, representing benign, cancerous, normal tissues and image’s background. The motivation is to evaluate the proposal in perspective of using it for execution in an inexpensive ordinary desktop computer in places located far from medical experts. The images were obtained from DDSM database and processed producing the feature-dataset used for training an Artificial Neural Network, the results were evaluated by analysis of the learning rate curve and ROC curves, besides these graphical analytical tools the confusion matrix and other quantitative metrics (TPR, FPR and Accuracy) were also extracted and analyzed. The average accuracy ≈ 0.8 and the other metrics extracted from results demonstrate that the proposal presents potential for further developments. At the best effort, PHOC was not found in literature for applications in mammographies such as it is proposed here.

Downloads

Download data is not yet available.

References

WHO-GENEVE-SWITZERLAND. Breast Can- cer. [S.l.], 2019. Availabel at ⟨http://www.who.int/ cancer/prevention/diagnosis-screening/breast-cancer/en/⟩. Dispon ́ıvel em: ⟨http://www.who.int/cancer/prevention/ diagnosis-screening/breast-cancer/en/⟩.

SUNZ.ZHAO,Z.Y.F.X.H.L.Z.Z.W.S.J.J.P.Y.H.Z. Y. Risk factors and preventions of breast cancer. International journal of biological sciences, v. 13, n. 11, p. 1387–1397, 2017.

INCA. INCA - Instituto Nacional de Caˆncer - Jose ́ A. G. da Silva. Detecc ̧a ̃o Precoce. [S.l.], 2018. Available at ⟨http://www2.inca.gov.br/wps/wcm/connect/tiposdecancer/ site/home/mama/deteccao precoce⟩.

ACS. American Cancer Society Recommendations for the Early Detection of Breast Cancer. [S.l.], 2019. Available at ⟨http://www.cancer.org/cancer/breast-cancer/ screening-tests-and-early-detection.html⟩.

CHAN, H. P. et al. Improvement in radiologist’s detec- tion of clustered microcalcifications on mammograms - the potential of computer aided-diagnosis. Invest. Radiol., v. 25, n. 10, p. 1102–1110, 1990.

AMARASINGHE, D. et al. Segmentation and sklearn numerical analysis of microcalcifications on mammograms using mathematical morphology. The British Journal of Radi- ology, v. 70, n. 837, 1997.

CHAN, H. P. et al. Image feature analysis and computer- aided diagnosis in digital radiography. i. automated detection of microcalcications in mammography. Medical Physics, v. 14, n. 4, 1987.

SUCKLING, J. et al. The mammographic image anal- ysis society digital mammogram database. Exerpta Medica. International Congress Series, p. 375–378, 1994.

YAGHJYAN, L. et al. Tissue-based associations of mam- mographic breast density with breast stem cell markers. Breast Cancer Research, v. 19, p. 100–, 2017.

TITUS-ERNSTOFF, L. et al. Breast cancer risk factors in relation to breast density (united states). Cancer Causes Control, v. 17, p. 1281–1290, 2006.

MENCATTINI, A. et al. Mammographic images en- hancement and denoising for breast cancer detection using dyadic wavelet processing. IEEE Transactions on Instrumen- tation and Measurement, v. 57, n. 7, p. 1422–1430, July 2008.

DDSM. DDSM: Digital Database for Screening Mam- mography. 2019. Available at ⟨http://www.eng.usf.edu/cvprg/ Mammography/Database.html⟩.

ZENG, X. et al. Automated diabetic retinopathy detec- tion based on binocular siamese-like convolutional neural network. IEEE Access, v. 7, p. 30744–30753, 2019.

Zhang, X. et al. Whole mammogram image classification with convolutional neural networks. In: 2017 IEEE Interna- tional Conference on Bioinformatics and Biomedicine (BIBM). [S.l.: s.n.], 2017. p. 700–704.

Efficient processing of deep neural networks: A tutorial and survey., v. 105, n. 12. 2295–2329 p.

STOUTCHININ, A.; CONTI, F.; BENINI, L. Optimally scheduling cnn convolutions for efficient memory access. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, v. 38, n. 6, p. 1095–1108, 2019.

LAZEBNIK, S.; SCHMID, C.; PONCE, J. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the IEEE conference on computer vision and pattern recognition. [S.l.: s.n.], 2006. p. 2169–2178.

BOSCH, A.; ZISSERMAN, A.; MUNOZ, X. Represent- ing shape with a spatial pyramid kernel. In: Proceedings of the 6th ACM international conference on Image and video retrieval. [S.l.: s.n.], 2007. p. 401–408.

BOSCH, A.; ZISSERMAN, A.; MUNOZ, X. Image classification using random forests and ferns. In: ICCV. [S.l.: s.n.], 2007.

BOSCH, A.; ZISSERMAN, A.; MUNOZ, X. Scene clas- sification using a hybrid generative/discriminative approach. IEEE - PAMI, v. 30, n. 4, p. 712–727, 2008.

GAO, H.; CHEN, W.; DOU, L. Image classification based on support vector machine and the fusion of comple- mentary features. [S.l.]. Availabel at ⟨http://arxiv.org/abs/1511. 01706⟩. Dispon ́ıvel em: ⟨http://arxiv.org/abs/1511.01706⟩.

K.P.SOMAN; RAMASHANDRAN, K.; RESMI, N. In- sight into Wavelets - from Theory to Pratice. 3rd. ed. [S.l.]: PHI, 2010.

GARGOUR, C. et al. A short introduction to wavelets and their applications. IEEE Circuits and Systems Magazine, v. 9, n. 2, p. 57–68, 2009.

KOCUR, C. M. et al. Using neural networks to select wavelet features for breast cancer diagnosis. IEEE ENGI- NEERING IN MEDICINE AND BIOLOGY, v. 15, n. 3, p. 95–102, 1996.

DHEEBA, J.; SINGH, N. A.; SELVI, S. T. Computer- aided detection of breast cancer on mammograms: A swarm intelligence optimized wavelet neural network approach. Jour- nal of Biomedical Informatics, v. 49, p. 45–52, 2014.

MEHDY, M. M. et al. Survey: Artificial neural networks in image processing for early detection of breast cancer. Hin- dawi Computational and Mathematical Methods in Medicine, v. 2017, 2017.

GARDEZI A. ELAZAB, B. L. T. W. S. Breast cancer de- tection and diagnosis using mammographic data: Systematic review. J Med Internet Res, v. 21, n. 7, 2019.

CARNEIRO, P. C. et al. Breast density pattern charac- terization by histogram features and texture descriptors. RE-

SEARCH ON BIOMEDICAL ENGINEERING, v. 33, n. 1, p. 69–77, 2017.

ZHOU, C. et al. Computerized image analysis: Estima- tion of breast density on mammograms. Med. Phys., v. 28, n. 6, p. 1056–1069, 2001.

GERON, A. Hands-On Machine Learning with Scikit- Learn and TensorFlow, Concepts, Tools, and Techniques to Build Intelligent Systems. [S.l.]: O’Reilly Media, 2017.

BUDUMA, N.; LOCASCIO, N. Fundamentals of deep learning: designing next-generation machine intelligence al- gorithms. [S.l.]: O’Reilly Media, 2017.

SHARMA, A. DDSM Utility. [S.l.]: GitHub, 2015. ⟨https://github.com/trane293/DDSMUtility⟩.

BEALE, M. H.; HAGAN, M. T.; DEMUTH, H. B. Neural network toolbox: users guide. [S.l.]. Available at ⟨https://www.mathworks.com/help/pdf doc/nnet/nnet ug. pdf⟩. Dispon ́ıvel em: ⟨https://www.mathworks.com/help/ pdf doc/nnet/nnet ug.pdf⟩.

KUMAR, R.; ANTONY, G. A review of methods and ap- plications of the roc curve in clinical trials. Drug Information Journal, v. 44, n. 6, p. 659–671, 2010.

PRATI, R.; BATISTA, G.; MONARD, M. A survey on graphical methods for classification predictive performance evaluation. IEEE Transactions on Knowledge and Data Engi- neering, v. 23, n. 11, p. 1601–1618, 2011.