Multistage Segmentation of Prostate Cancer Tissues Using Sample Entropy Texture Analysis
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 sampl...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-12-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/22/12/1370 |
id |
doaj-fd4fedee45344e57b068e224017ccfee |
---|---|
record_format |
Article |
spelling |
doaj-fd4fedee45344e57b068e224017ccfee2020-12-05T00:02:10ZengMDPI AGEntropy1099-43002020-12-01221370137010.3390/e22121370Multistage Segmentation of Prostate Cancer Tissues Using Sample Entropy Texture AnalysisTariq Ali0Khalid Masood1Muhammad Irfan2Umar Draz3Arfan Ali Nagra4Muhammad Asif5Bandar M. Alshehri6Adam Glowacz7Ryszard Tadeusiewicz8Mater H. Mahnashi9Sana Yasin10Department of Computer Science, Sahiwal Campus, COMSATS University Islamabad, Sahiwal 57000, PakistanDepartment of Computer Science, Lahore Garrison University, Lahore 54792, PakistanElectrical Engineering Department, College of Engineering, Najran University, Najran 61441, Saudi ArabiaDepartment of Computer Science, University of Sahiwal, Sahiwal, Punjab 57000, PakistanDepartment of Computer Science, Lahore Garrison University, Lahore 54792, PakistanDepartment of Computer Science, Lahore Garrison University, Lahore 54792, PakistanDepartment of Clinical Laboratory, Faculty of applied Medical Sciences, Najran University, P.O. Box, Najran 1988, Saudi ArabiaDepartment of Automatic Control and Robotics, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Science and Technology, al. A. Mickiewicza 30, 30-059 Kraków, PolandDepartment of Biocybernetics and Biomedical Engineering, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Science and Technology, al. A. Mickiewicza 30, 30-059 Kraków, PolandDepartment of Medicinal Chemistry, Pharmacy School, Najran University, Najran 61441, Saudi ArabiaDepartment of Computer Science, University of Okara, Okara 56130, PakistanIn 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.https://www.mdpi.com/1099-4300/22/12/1370wavelet packetssample entropymean-shift segmentationdice coefficient |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tariq Ali Khalid Masood Muhammad Irfan Umar Draz Arfan Ali Nagra Muhammad Asif Bandar M. Alshehri Adam Glowacz Ryszard Tadeusiewicz Mater H. Mahnashi Sana Yasin |
spellingShingle |
Tariq Ali Khalid Masood Muhammad Irfan Umar Draz Arfan Ali Nagra Muhammad Asif Bandar M. Alshehri Adam Glowacz Ryszard Tadeusiewicz Mater H. Mahnashi Sana Yasin Multistage Segmentation of Prostate Cancer Tissues Using Sample Entropy Texture Analysis Entropy wavelet packets sample entropy mean-shift segmentation dice coefficient |
author_facet |
Tariq Ali Khalid Masood Muhammad Irfan Umar Draz Arfan Ali Nagra Muhammad Asif Bandar M. Alshehri Adam Glowacz Ryszard Tadeusiewicz Mater H. Mahnashi Sana Yasin |
author_sort |
Tariq Ali |
title |
Multistage Segmentation of Prostate Cancer Tissues Using Sample Entropy Texture Analysis |
title_short |
Multistage Segmentation of Prostate Cancer Tissues Using Sample Entropy Texture Analysis |
title_full |
Multistage Segmentation of Prostate Cancer Tissues Using Sample Entropy Texture Analysis |
title_fullStr |
Multistage Segmentation of Prostate Cancer Tissues Using Sample Entropy Texture Analysis |
title_full_unstemmed |
Multistage Segmentation of Prostate Cancer Tissues Using Sample Entropy Texture Analysis |
title_sort |
multistage segmentation of prostate cancer tissues using sample entropy texture analysis |
publisher |
MDPI AG |
series |
Entropy |
issn |
1099-4300 |
publishDate |
2020-12-01 |
description |
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. |
topic |
wavelet packets sample entropy mean-shift segmentation dice coefficient |
url |
https://www.mdpi.com/1099-4300/22/12/1370 |
work_keys_str_mv |
AT tariqali multistagesegmentationofprostatecancertissuesusingsampleentropytextureanalysis AT khalidmasood multistagesegmentationofprostatecancertissuesusingsampleentropytextureanalysis AT muhammadirfan multistagesegmentationofprostatecancertissuesusingsampleentropytextureanalysis AT umardraz multistagesegmentationofprostatecancertissuesusingsampleentropytextureanalysis AT arfanalinagra multistagesegmentationofprostatecancertissuesusingsampleentropytextureanalysis AT muhammadasif multistagesegmentationofprostatecancertissuesusingsampleentropytextureanalysis AT bandarmalshehri multistagesegmentationofprostatecancertissuesusingsampleentropytextureanalysis AT adamglowacz multistagesegmentationofprostatecancertissuesusingsampleentropytextureanalysis AT ryszardtadeusiewicz multistagesegmentationofprostatecancertissuesusingsampleentropytextureanalysis AT materhmahnashi multistagesegmentationofprostatecancertissuesusingsampleentropytextureanalysis AT sanayasin multistagesegmentationofprostatecancertissuesusingsampleentropytextureanalysis |
_version_ |
1724400262800474112 |