Analysis of Keypoint Detection Algorithms for Mass Candidates Selection in Mammography Images

  • Felipe Victor de Sá Oliveira UFRPE
  • Gersica Agripino Alencar UFRPE
  • Filipe Rolim Cordeiro UFRPE

Resumo

Breast cancer has been a growing problem for women around the world. The correct interpretation of mammographic images is important for the diagnosis of breast cancer. However, this is a difficult task even for a specialist. Image processing is used to make the diagnosis less susceptible to errors. Thus, the present work proposes a new method for the search of lesion candidates in mammographic images. To verify the efficiency of the approach, the behavior of the SURF, SIFT, BRISK and ORB algorithms were analyzed, as well as the Selective Search algorithm for candidate selection. A total of 1210 mammography images were used, from the CBIS-DDSM database. Results show that the SURF algorithm presented better performance, generating on average, for each image, 4.11 candidates considered in the internal area of the lesion, reducing exploratory space by 72%, whereas the ORB generated on average 1.6 candidates with a reduction rate of 96.30%.

Referências


Abbas, Q. (2016). Deepcad: A computer-aided diagnosis system for mammographic masses using deep invariant features. Computers, 5(4):28.

Bianco, S., Mazzini, D., Pau, D., and Schettini, R. (2015). Local detectors and compact descriptors for visual search: a quantitative comparison. Digital Signal Processing, 44:1–13.

Cordeiro, F. R., Santos, W. P. d., and Silva-Filho, A. G. (2017). Analysis of supervised and semi-supervised growcut applied to segmentation of masses in mammography images. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 5(4):297–315.

Deshmukh, J. and Bhosle, U. (2017). Surf features based classifiers for mammogram classification. In Wireless Communications, Signal Processing and Networking (WiSPNET), 2017 International Conference on, pages 134–139. IEEE.

Dhungel, N., Carneiro, G., and Bradley, A. P. (2017). A deep learning approach for the analysis of masses in mammograms with minimal user intervention. Medical image analysis, 37:114–128.

Evans, K. K., Birdwell, R. L., and Wolfe, J. M. (2013). If you don’t find it often, you often don’t find it: Why some cancers are missed in breast cancer screening. PloS one, 8(5):e64366.

INCA (2018). Estimativa 2018 - incidência de câncer no brasil.

Karami, E., Prasad, S., and Shehata, M. (2017). Image matching using sift, surf, brief and orb: Performance comparison for distorted images. arXiv preprint arXiv:1710.02726.

Leal, I., Aires, K., and Veras, R. (2017). Diagnóstico de benignidade e malignidade em imagens mamográficas utilizando aprendizado profundo para extração das regi˜oes de interesse e Índices de diversidade filogenéticas para classificação. Anais do XIV Encontro Nacional de Inteligência Artificial e Computacional, pages 250–261.

Leutenegger, S., Chli, M., and Siegwart, R. Y. (2011). Brisk: Binary robust invariant scalable keypoints. In Computer Vision (ICCV), 2011 IEEE International Conference on, pages 2548–2555. IEEE.

Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics, 9(1):62–66.

Rodrigues, L. A., Silva, F. A. d., Pereira, D. R., Artero, A. O., and Piteri, M. A. (2014). Detecção e reconhecimento de objetos em imagens utilizando algoritmos de extração de pontos chave. In Colloquium Exactarum. ISSN: 2178-8332, volume 6, pages 86–103.

Rosebrock, A. (2016). Intersection over union (iou) for object detection. Online] http://www.pyimagesearch. com/2016/11/07/intersection-overunion-iou-for-objectdetection.

Rublee, E., Rabaud, V., Konolige, K., and Bradski, G. (2011). Orb: An efficient alternative to sift or surf. In Computer Vision (ICCV), 2011 IEEE international conference on, pages 2564–2571. IEEE.

Salazar-Licea, L. A., Mendoza, C., Aceves, M., Pedraza, J., and Pastrana-Palma, A. (2014). Automatic segmentation of mammograms using a scale-invariant feature transform and k-means clustering algorithm. In Electrical Engineering, Computing Science and Automatic Control (CCE), 2014 11th International Conference on, pages 1–6. IEEE.

Tortora, G. J. and Derrickson, B. (2016). Corpo Humano-: Fundamentos de Anatomia e Fisiologia. Artmed Editora.

Uijlings, J. R., Van De Sande, K. E., Gevers, T., and Smeulders, A. W. (2013). Selective search for object recognition. International journal of computer vision, 104(2):154–171.

WHO et al. (2014). WHO position paper on mammography screening. World Health Organization.

Publicado
2018-10-22
Como Citar
OLIVEIRA, Felipe Victor de Sá; ALENCAR, Gersica Agripino; CORDEIRO, Filipe Rolim. Analysis of Keypoint Detection Algorithms for Mass Candidates Selection in Mammography Images. Anais do Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), [S.l.], p. 36-47, out. 2018. ISSN 2763-9061. Disponível em: <https://sol.sbc.org.br/index.php/eniac/article/view/4402>. Acesso em: 18 maio 2024. doi: https://doi.org/10.5753/eniac.2018.4402.