Abstract
A novel gland segmentation and classification scheme applied to an H&E histology image of the prostate tissue is proposed. For gland segmentation, we associate appropriate nuclei objects with each lumen object to create a gland segment. We further extract 22 features to describe the structural information and contextual information for each segment. These features are used to classify a gland segment into one of the three classes: artifact, normal gland and cancer gland. On a dataset of 48 images at 5× magnification (which includes 525 artifacts, 931 normal glands and 1,375 cancer glands), we achieved the following classification accuracies: 93% for artifacts v. true glands; 79% for normal v. cancer glands, and 77% for discriminating all three classes. The proposed method outperforms state of the art methods in terms of segmentation and classification accuracies and computational efficiency.
Keywords
- Contextual Information
- Segmentation Result
- Jaccard Index
- Median Absolute Deviation
- Prostate Cancer Detection
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
www.cse.msu.edu/~nguye231/GlandSegClass.html
Description: The code for gland segmentation and feature extraction, the details of the experiments (PPMM-SF method, PPMM-SCF method, three methods to estimate p(y|x) mentioned in the paper)
Download conference paper PDF
References
Kumar, V., Abbas, A., Fausto, N.: Robbins and Cotran Pathologic Basis of Disease. Saunders (2004)
Monaco, J., Tomaszewski, J., Feldman, M., Hagemann, I., Moradi, et al.: High-throughput detection of prostate cancer in histological sections using probabilistic pairwise markov models. Medical Image Analysis 14, 617–629 (2010)
Nguyen, K., Jain, A., Sabata, B.: Prostate cancer detection: Fusion of cytological and textural features. Journal of Pathology Informatics 2, 2–3 (2011)
Doyle, S., Feldman, M., Tomaszewski, J., Madabhushi, A.: A boosted Bayesian multi-resolution classifier for prostate cancer detection from digitized needle biopsies. IEEE Trans. Biomed. Eng. 59, 1205–1218 (2012)
Peng, Y., Jiang, Y., Eisengart, L., et al.: Segmentation of prostatic glands in histology images. In: IEEE Int. Symp. on Biomedical Imaging, pp. 2091–2094 (2011)
Naik, S., Doyle, S., Madabhushi, A., Tomaszewski, J., et al.: Automated gland segmentation and Gleason grading of prostate histology by integrating low-, high-level and domain specific information. In: MIAAB Workshop, Piscataway, NJ (2007)
Yoon, H.J., Li, C.C., Christudass, C., Veltri, R., et al.: Cardinal multiridgelet-based prostate cancer histological image classification for Gleason grading. In: IEEE Int. Conf. Bioinformatics and Biomedicine, pp. 315–320 (2011)
Khouzani, K.J., Zadeh, H.S.: Multiwavelet grading of pathological images of prostate. IEEE Trans. Biomed. Eng. 50, 697–704 (2003)
Tabesh, A., Teverovskiy, M., et al.: Multifeature prostate cancer diagnosis and gleason grading of histological images. IEEE Trans. Med. Img. 26, 1366–1378 (2007)
Haralick, R., Shapiro, L.: Computer and robot vision, vol. 2, pp. 28–48. Addison-Wesley (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nguyen, K., Sarkar, A., Jain, A.K. (2012). Structure and Context in Prostatic Gland Segmentation and Classification. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012. MICCAI 2012. Lecture Notes in Computer Science, vol 7510. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33415-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-33415-3_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33414-6
Online ISBN: 978-3-642-33415-3
eBook Packages: Computer ScienceComputer Science (R0)
