Classifying Prostate Histological Images Using Deep Gaussian Processes on a New Optical Density Granulometry-Based Descriptor
The increasing use of whole slide digital scanners has led to an enormous interest in the application of machine learning techniques to detect prostate cancer using eosin and hematoxylin stained histopathological images. In this work the above problem is approached as follows: the optical density of each whole slide image is calculated and its eosin and hematoxylin concentration components estimated. Then, hand-crafted features, which are expected to capture the expertise of pathologists, are extracted from patches of these two concentration components. Finally, patches are classified using a Deep Gaussian Process on the extracted features. The new approach outperforms current state of the art shallow as well as deep classifiers like InceptionV3, Xception and VGG19 with an AUC value higher than 0.98.
KeywordsProstate cancer Optical Density Texture features Morphological features Deep Gaussian Processes
- 2.Kandemir, M., Zhang, C., Hamprecht, F.A.: Empowering multiple instance histopathology cancer diagnosis by cell graphs. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8674, pp. 228–235. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10470-6_29CrossRefGoogle Scholar
- 6.Ruifrok, A.C., Johnston, D.A.: Quantification of histochemical staining by color deconvolution. Anal. Quant. Cytol. Histol. 23(4), 291–299 (2001)Google Scholar
- 7.Salimbeni, H., Deisenroth, M.: Doubly stochastic variational inference for deep Gaussian processes. In: NIPS, pp. 4591–4602 (2017)Google Scholar