Abstract
Computer aided diagnosis (CAD) of cancerous anatomical structures via 3D medical images has emerged as an intensively studied research area. In this paper, we present a principled three-tiered image feature learning approach to capture task specific and data-driven class discriminative statistics from an annotated image database. It integrates voxel-, instance-, and database-level feature learning, aggregation and parsing. The initial segmentation is proceeded as robust voxel labeling and thresholding. After instance-level spatial aggregation, extracted features can also be flexibly tuned for classifying lesions, or discriminating different subcategories of lesions. We demonstrate the effectiveness in the lung nodule detection task which handles all types of solid, partial-solid, and ground-glass nodules using the same set of learned features. Our hierarchical feature learning framework, which was extensively trained and validated on large-scale multiple site datasets of \(879\) CT volumes (510 training and 369 validation), achieves superior performance than other state-of-the-art CAD systems. The proposed method is also shown to be applicable for colonic polyp detection, including all polyp morphological subcategories, via 770 tagged-prep CT scans from multiple medical sites (358 training and 412 validation).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
PBT is a powerful two-class and multiclass discriminative learning framework [20]. Random Forests or Ferns [21, 22] are also applicable for training voxel-level labeler. Our empirical experience shows that PBT can learn very similar or slightly better ROC curves with much simpler model complexity, i.e., one tree versus multiple trees per model/classifier.
References
Dehmeshki, J., Amin, H., Valdivieso, M., Ye, X.: Segmentation of pulmonary nodules in thoracic CT scans: a region growing approach. IEEE Trans. Med. Imag. 27, 467–480 (2008)
Ye, X., Lin, X., Dehmeshki, J., Slabaugh, G., Beddoe, G.: Shape based computer-aided detection of lung nodules in thoracic CT images. IEEE Trans. Biomed. Eng. 56(7), 1810–1820 (2009)
Kubota, T., Jerebko, A., Dewan, M., Salganicoff, M., Krishnan, A.: Segmentation of pulmonary nodules of various densities with morphological approaches and convexity models. Med. Image Anal. 15(1), 133–154 (2011)
El-Baz, A., Gimel’farb, G.: Robust medical images segmentation using learned shape and appearance models. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009, Part I. LNCS, vol. 5761, pp. 281–288. Springer, Heidelberg (2009)
Mendonça, P.R.S., Bhotika, R., Zhao, F., Miller, J.V.: Lung nodule detection via bayesian voxel labeling. In: Karssemeijer, N., Lelieveldt, B. (eds.) IPMI 2007. LNCS, vol. 4584, pp. 134–146. Springer, Heidelberg (2007)
Wu, D., Lu, L., Bi, J., Shinagawa, Y., Boyer, K., Krishnan, A., Salganicoff, M.: Stratified learning of local anatomical context for lung nodules in CT images. In: IEEE CVPR (2010)
Lo, P., Sporring, J., Ashraf, H., Pedersen, J., de Bruijne, M.: Vessel-guided airway tree segmentation: a voxel classification approach. Med. Image Anal. 14, 527–538 (2010)
Jacobs, C., Sánchez, C.I., Saur, S.C., Twellmann, T., de Jong, P.A., van Ginneken, B.: Computer-aided detection of ground glass nodules in thoracic CT images using shape, intensity and context features. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011, Part III. LNCS, vol. 6893, pp. 207–214. Springer, Heidelberg (2011)
Shotton, J., Winn, J., Rother, C., Criminisi, A.: Textonboost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context. IJCV 81(1), 1:2–1:23 (2009)
Raykar, V., Krishnapuram, B., Bi, J., Dundar, M., Rao, R.: Bayesian multiple instance learning: automatic feature selection and inductive transfer. In: ICML, pp. 808–815 (2008)
Jerebko, A.K., Lakare, S., Cathier, P., Periaswamy, S., Bogoni, L.: Symmetric curvature patterns for colonic polyp detection. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4191, pp. 169–176. Springer, Heidelberg (2006)
van Wijk, C., van Ravesteijn, V., Vos, F., van Vliet, L.J.: Detection and segmentation of colonic polyps on implicit isosurfaces by second principal curvature flow. IEEE Trans. Med. Imag. 29(3), 688–698 (2010)
Melonakos, J., Mendonça, P.R.S., Bhotka, R., Sirohey, S.A.: A probabilistic model for haustral curvatures with applications to colon CAD. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part II. LNCS, vol. 4792, pp. 420–427. Springer, Heidelberg (2007)
Slabaugh, G., Yang, X., Ye, X., Boyes, R., Beddoe, G.: A robust and fast system for ctc computer-aided detection of colorectal lesions. Algorithms 3(1), 21–43 (2010)
Mendonça, P.R.S., Bhotika, R., Sirohey, S.A., Turner, W.D., Miller, J.V., Avila, R.S.: Model-based analysis of local shape for lesion detection in CT scans. In: Duncan, J.S., Gerig, G. (eds.) MICCAI 2005. LNCS, vol. 3749, pp. 688–695. Springer, Heidelberg (2005)
Paik, D., et al.: Surface normal overlap: a computer-aided detection algorithm with application to colonic polyps and lung nodules in helical CT. IEEE Trans. Med. Imag. 23(6), 661–675 (2004)
Lu, L., Barbu, A., Wolf, M., Liang, J., Bogoni, L., Salganicoff, M., Comaniciu, D.: Accurate polyp segmentation for 3D CT colonography using multi-staged probabilistic binary learning and compositional model. In: IEEE CVPR (2008)
Lorensen, W., Cline, H.: Marching cubes: a high resolution 3D surface construction algorithm. ACM SIGGRAPH Comput. Graph. 21(4), 163–169 (1987)
Lu, L., Barbu, A., Wolf, M., Liang, J., Bogoni, L., Salganicoff, M., Comaniciu, D.: Simultaneous detection and registration for ileo-cecal valve detection in 3D CT colonography. In: European Conference on Computer Vision, vol. 4, pp. 10–15 (2008)
Tu, Z.: Probabilistic boosting-tree: Learning discriminative models for classification, recognition, and clustering. In: ICCV, pp. 1589–1596 (2005)
Bosch, A., Zisserman, A., Munoz, X.: Image classification using random forests and ferns. In: ICCV, pp. 1–8 (2007)
Schwing, A., Zach, C., Zheng, Y., Pollefeys, M.: Adaptive random forest-how many experts to ask before making a decision? In: CVPR, pp. 1377–1384 (2011)
Farag, A., Graham, J., Farag, A., Falk, R.: Lung nodule modeling - a data-driven approach. In: Bebis, G. (ed.) ISVC 2009. LNCS, vol. 5875, pp. 347–356. Springer, Heidelberg (2009)
Lu, L., Bi, J., Wolf, M., Salganicoff, M.: Effective 3D object detection and regression using probabilistic segmentation features in CT images. In: IEEE Computer Vision and Pattern Recognition, pp. 1–8 (2011)
Gorelick, L., Blank, M., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. IEEE Trans. Pattern Anal. Mach. Intell. 29, 2247–2253 (2007)
Toews, M., Wells, W.M.: Efficient and robust model-to-image alignment using 3D scale-invariant features. Med. Image Anal. 17(3), 271–282 (2013)
Smith, K., Carleton, A., Lepetit, V.: Fast ray features for learning irregular shapes. In: ICCV (2009)
Tu, Z., Zhou, X., Bogoni, L., Barbu, A., Comaniciu, D.: Probabilistic 3D polyp detection in CT images: the role of sample alignment. In: CVPR, pp. 1544–1551 (2006)
Yao, J., Miller, M., Franaszek, M., Summers, R.: Colonic polyp segmentation in CT colongraphy-based on fuzzy clustering and deformable models. IEEE Trans. Med. Imag. 23(11), 1344–1352 (2004)
van Ravesteijn, V., van Wijk, C., Vos, F., Truyen, R., Peters, J., Stoker, J., van Vliet, L.: Computer aided detection of polyps in CT colonography using logistic regression. IEEE Trans. Med. Imag. 29(11), 1907–1917 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Lu, L., Devarakota, P., Vikal, S., Wu, D., Zheng, Y., Wolf, M. (2014). Computer Aided Diagnosis Using Multilevel Image Features on Large-Scale Evaluation. In: Menze, B., Langs, G., Montillo, A., Kelm, M., Müller, H., Tu, Z. (eds) Medical Computer Vision. Large Data in Medical Imaging. MCV 2013. Lecture Notes in Computer Science(), vol 8331. Springer, Cham. https://doi.org/10.1007/978-3-319-05530-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-05530-5_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-05529-9
Online ISBN: 978-3-319-05530-5
eBook Packages: Computer ScienceComputer Science (R0)