Deep Cascade Classifiers to Detect Clusters of Microcalcifications

详细信息    查看全文

• 关键词：Computer aided detection ; Mammography ; Clusters of microcalcifications ; Cascade of classifiers
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9699
• 期：1
• 页码：415-422
• 全文大小：982 KB
• 参考文献：1.Kopans, D.B.: Breast Imaging. Lippincott Williams & Wilkins, Hagerstown (2007)
  2.Eadie, L.H., Taylor, P., Gibson, A.P.: A systematic review of computer-assisted diagnosis in diagnostic cancer imaging. Eur. J. Radiol. 81(1), e70–e76 (2012)CrossRef
  3.El Naqa, I., Yang, Y., Wernick, M.N., Galatsanos, N.P., Nishikawa, R.M.: A support vector machine approach for detection of microcalcifications. IEEE Trans. Med. Imaging 21(12), 1552–1563 (2002)CrossRef
  4.Wei, L., Yang, Y., Nishikawa, R.M., Wernick, M.N., Edwards, A.: Relevance vector machine for automatic detection of clustered microcalcifications. IEEE Trans. Med. Imaging 24(10), 1278–1285 (2005)CrossRef
  5.Marrocco, C., Molinara, M., D’Elia, C., Tortorella, F.: A computer-aided detection system for clustered microcalcifications. Artif. Intell. Med. 50(1), 23–32 (2010)CrossRef
  6.Oliver, A., Torrent, A., Tortajada, M., Lladó, X., Peracaula, M., Tortajada, L., Sentís, M., Freixenet, J.: A boosting based approach for automatic micro-calcification detection. In: Martí, J., Oliver, A., Freixenet, J., Martí, R. (eds.) IWDM 2010. LNCS, vol. 6136, pp. 251–258. Springer, Heidelberg (2010)CrossRef
  7.Jing, H., Yang, Y., Nishikawa, R.M.: Detection of clustered microcalcifications using spatial point process modeling. Phys. Med. Biol. 56(1), 1–17 (2011)CrossRef
  8.Bria, A., Karssemeijer, N., Tortorella, F.: Learning from unbalanced data: a cascade-based approach for detecting clustered microcalcifications. Med. Image Anal. 18(2), 241–252 (2014)CrossRef
  9.Viola, P., Jones, M.: Robust real-time object detection. Int. J. Comput. Vis. 57(2), 137–154 (2001)CrossRef
  10.Bria, A., Marrocco, C., Molinara, M., Tortorella, F.: An effective learning strategy for cascaded object detection. Inf. Sci. 340–341, 17–26 (2016)MathSciNet CrossRef
  11.Yousef, W.A.: Assessing classifiers in terms of the partial area under the ROC curve. Comput. Stat. Data Anal. 64, 51–70 (2013)MathSciNet CrossRef
  12.Samuelson, F.W., Petrick, N.: Comparing image detection algorithms using resampling. In: IEEE International Symposium on Biomedical Imaging, pp. 1312–1315 (2006)
  13.Samuelson, F.W., Petrick, N., Paquerault, S.: Advantages and examples of resampling for CAD evaluation. In: IEEE International Symposium on Biomedical Imaging, pp. 492–495 (2007)
  
• 作者单位：Alessandro Bria (16)
  Claudio Marrocco (16)
  Nico Karssemeijer (17)
  Mario Molinara (16)
  Francesco Tortorella (16)
  
  16. DIEI, University of Cassino and Southern Latium, Cassino, FR, Italy
  17. DIAG, Radboud University Nijmegen Medical Centre, Nijmegen, The Netherlands
  
• 丛书名：Breast Imaging
• ISBN：978-3-319-41546-8
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9699

文摘

Recent advances in Computer-Aided Detection (CADe) for the automatic detection of clustered microcalcifications on mammograms show that cascade classifiers can compete with high-end commercial systems. In this paper, we introduce a deep cascade detector where the learning algorithm of each binary pixel classifier has been redesigned in the early stopping mechanism conventionally used to avoid overfitting to the training data. In this way, we strongly increase the number of features considered in each stage of the cascade (hence the term “deep”), yet we still benefit from the cascade framework by obtaining a very fast processing of mammograms (less than one second per image). We evaluated the proposed approach on a database of full-field digital mammograms; the experiments revealed a statistically significant improvement of deep cascade with respect to the traditional cascade framework. We also obtained statistically significantly higher performance than one of the most widespread commercial CADe systems, the Hologic R2CAD ImageChecker. Specifically, at the same number of false positives per image of R2CAD (0.21), the deep cascade detected 96 % of true lesions against the 90 % of R2CAD, whereas at the same lesion sensitivity of R2CAD (90 %), we obtained 0.05 false positives per image for the deep cascade against the 0.21 of R2CAD.