Selective Labeling: Identifying Representative Sub-volumes for Interactive Segmentation

详细信息    查看全文

• 关键词：Unsupervised ; Sub ; volume proposals ; Interactive segmentation ; Active learning ; Affinity clustering ; Supervoxels
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9993
• 期：1
• 页码：17-24
• 全文大小：3,235 KB
• 参考文献：1.Karasev, P., Kolesov, I., Fritscher, K., Vela, P., Mitchell, P., Tannenbaum, A.: Interactive medical image segmentation using PDE control of active contours. IEEE Trans. Med. Imaging 32, 2127–2139 (2013)CrossRef
  2.Beichel, R., et al.: Liver segmentation in CT data: a segmentation refinement approach. In: Proceedings of 3D Segmentation in the Clinic: A Grand Challenge, pp. 235–245 (2007)
  3.Uijlings, J.R.R., van de Sande, K.E.A., Gevers, T., Smeulders, A.W.M.: Selective search for object recognition. IJCV 104, 154–171 (2013)CrossRef
  4.Top, A., Hamarneh, G., Abugharbieh, R.: Active learning for interactive 3D image segmentation. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011. LNCS, vol. 6893, pp. 603–610. Springer, Heidelberg (2011). doi:10.​1007/​978-3-642-23626-6_​74 CrossRef
  5.Top, A., Hamarneh, G., Abugharbieh, R.: Spotlight: automated confidence-based user guidance for increasing efficiency in interactive 3D image segmentation. In: Menze, B., Langs, G., Tu, Z., Criminisi, A. (eds.) MICCAI 2010. LNCS, vol. 6533, pp. 204–213. Springer, Heidelberg (2011)
  6.Lucchi, A., et al.: Supervoxel-based segmentation of mitochondria in EM image stacks with learned shape features. IEEE Trans. Med. Imaging 31(2), 474–486 (2012)CrossRef
  7.Hong, X., Chang, H., Shan, S., Chen, X., Gao, W.: Sigma set: a small second order statistical region descriptor. In: CVPR 2009 (2009)
  8.Luengo, I., Basham, M., French, A.P.: Fast global interactive volume segmentation with regional supervoxel descriptors. In: SPIE Medical Imaging, pp. 97842D–97842D. International Society for Optics and Photonics (2016)
  9.Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Mach. Learn. 63(1), 3–42 (2006)CrossRef MATH
  10.Frey, B.J., Dueck, D.: Clustering by passing messages between data points. Science 315(5814), 972–976 (2007)MathSciNet CrossRef MATH
  
• 作者单位：Imanol Luengo (18) (19)
  Mark Basham (19)
  Andrew P. French (18)
  
  18. School of Computer Science, University of Nottingham, Nottingham, NG8 1BB, UK
  19. Diamond Light Source Ltd, Harwell Science & Innovation Campus, Didcot, OX11 0DE, UK
  
• 丛书名：Patch-Based Techniques in Medical Imaging
• ISBN：978-3-319-47118-1
• 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：9993

文摘

Automatic segmentation of challenging biomedical volumes with multiple objects is still an open research field. Automatic approaches usually require a large amount of training data to be able to model the complex and often noisy appearance and structure of biological organelles and their boundaries. However, due to the variety of different biological specimens and the large volume sizes of the datasets, training data is costly to produce, error prone and sparsely available. Here, we propose a novel Selective Labeling algorithm to overcome these challenges; an unsupervised sub-volume proposal method that identifies the most representative regions of a volume. This massively-reduced subset of regions are then manually labeled and combined with an active learning procedure to fully segment the volume. Results on a publicly available EM dataset demonstrate the quality of our approach by achieving equivalent segmentation accuracy with only 5 % of the training data.