Multistage Segmentation of Prostate Cancer Tissues Using Sample Entropy Texture Analysis

Abstract

In this study, a multistage segmentation technique is proposed that identifies cancerous cells in prostate tissue samples. The benign areas of the tissue are distinguished from the cancerous regions using the texture of glands. The texture is modeled based on wavelet packet features along with sample entropy values. In a multistage segmentation process, the mean-shift algorithm is applied on the pre-processed images to perform a coarse segmentation of the tissue. Wavelet packets are employed in the second stage to obtain fine details of the structured shape of glands. Finally, the texture of the gland is modeled by the sample entropy values, which identifies epithelial regions from stroma patches. Although there are three stages of the proposed algorithm, the computation is fast as wavelet packet features and sample entropy values perform robust modeling for the required regions of interest. A comparative analysis with other state-of-the-art texture segmentation techniques is presented and dice ratios are computed for the comparison. It has been observed that our algorithm not only outperforms other techniques, but, by introducing sample entropy features, identification of cancerous regions of tissues is achieved with 90% classification accuracy, which shows the robustness of the proposed algorithm.

Keywords: dice coefficient; mean-shift segmentation; sample entropy; wavelet packets.

Figure 1

A microscopic tissue component showing various gland regions such as EN (epithelial nuclei), SN (stroma nuclei), EC (epithelial cytoplasm), SC (stroma Cytoplasm) and lumen.

Figure 2

The proposed framework.

Figure 3

Mean shift segmentation for benign circular glands.

Figure 4

Mean shift segmentation for benign elliptical glands.

Figure 5

Comparison of the Gland segmentation by the proposed algorithm (yellow boundary line) and Gaussian filtering algorithm (GFT) by [39] (blue boundary lines).

Figure 6

Dice similarity coefficient (DSC) for the proposed algorithm (TPA) and Gaussian filtering technique (GFT) in [39] for the first 24 samples in our dataset. The average DSC for our technique is 0.91, whereas for GFT, it is 0.79.