Evaluation of feature descriptors for cancerous tissue recognition

Panagiotis Stanitsas, Anoop Cherian, Xinyan Li, Alexander Truskinovsky, Vassilios Morellas, Nikolaos P Papanikolopoulos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Computer-Aided Diagnosis (CAD) has witnessed a rapid growth over the past decade, providing a variety of automated tools for the analysis of medical images. In surgical pathology, such tools enhance the diagnosing capabilities of pathologists by allowing them to review and diagnose a larger number of cases daily. Geared towards developing such tools, the main goal of this paper is to identify useful computer vision based feature descriptors for recognizing cancerous tissues in histopathologic images. To this end, we use images of Hematoxylin & Eosin-stained microscopic sections of breast and prostate carcinomas, and myometrial leiomyosarcomas, and provide an exhaustive evaluation of several state of the art feature representations for this task. Among the various image descriptors that we chose to compare, including representations based on convolutional neural networks, Fisher vectors, and sparse codes, we found that working with covariance based descriptors shows superior performance on all three types of cancer considered. While covariance descriptors are known to be effective for texture recognition, it is the first time that they are demonstrated to be useful for the proposed task and evaluated against deep learning models. Capitalizing on Region Covariance Descriptors (RCDs), we derive a powerful image descriptor for cancerous tissue recognition termed, Covariance Kernel Descriptor (CKD), which consistently outperformed all the considered image representations. Our experiments show that using CKD lead to 92.83%, 91.51%, and 98.10% classification accuracy for the recognition of breast carcinomas, prostate carcinomas, and myometrial leiomyosarcomas, respectively.

Original languageEnglish (US)
Title of host publication2016 23rd International Conference on Pattern Recognition, ICPR 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1490-1495
Number of pages6
ISBN (Electronic)9781509048472
DOIs
StatePublished - Apr 13 2017
Event23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, Mexico
Duration: Dec 4 2016Dec 8 2016

Other

Other23rd International Conference on Pattern Recognition, ICPR 2016
CountryMexico
CityCancun
Period12/4/1612/8/16

Fingerprint

Tissue
Pathology
Computer vision
Textures
Neural networks
Experiments
Deep learning

Cite this

Stanitsas, P., Cherian, A., Li, X., Truskinovsky, A., Morellas, V., & Papanikolopoulos, N. P. (2017). Evaluation of feature descriptors for cancerous tissue recognition. In 2016 23rd International Conference on Pattern Recognition, ICPR 2016 (pp. 1490-1495). [7899848] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2016.7899848

Evaluation of feature descriptors for cancerous tissue recognition. / Stanitsas, Panagiotis; Cherian, Anoop; Li, Xinyan; Truskinovsky, Alexander; Morellas, Vassilios; Papanikolopoulos, Nikolaos P.

2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1490-1495 7899848.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Stanitsas, P, Cherian, A, Li, X, Truskinovsky, A, Morellas, V & Papanikolopoulos, NP 2017, Evaluation of feature descriptors for cancerous tissue recognition. in 2016 23rd International Conference on Pattern Recognition, ICPR 2016., 7899848, Institute of Electrical and Electronics Engineers Inc., pp. 1490-1495, 23rd International Conference on Pattern Recognition, ICPR 2016, Cancun, Mexico, 12/4/16. https://doi.org/10.1109/ICPR.2016.7899848
Stanitsas P, Cherian A, Li X, Truskinovsky A, Morellas V, Papanikolopoulos NP. Evaluation of feature descriptors for cancerous tissue recognition. In 2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1490-1495. 7899848 https://doi.org/10.1109/ICPR.2016.7899848
Stanitsas, Panagiotis ; Cherian, Anoop ; Li, Xinyan ; Truskinovsky, Alexander ; Morellas, Vassilios ; Papanikolopoulos, Nikolaos P. / Evaluation of feature descriptors for cancerous tissue recognition. 2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1490-1495
@inproceedings{5f1b52692c9e4314a57d67e8f29e52ea,
title = "Evaluation of feature descriptors for cancerous tissue recognition",
abstract = "Computer-Aided Diagnosis (CAD) has witnessed a rapid growth over the past decade, providing a variety of automated tools for the analysis of medical images. In surgical pathology, such tools enhance the diagnosing capabilities of pathologists by allowing them to review and diagnose a larger number of cases daily. Geared towards developing such tools, the main goal of this paper is to identify useful computer vision based feature descriptors for recognizing cancerous tissues in histopathologic images. To this end, we use images of Hematoxylin & Eosin-stained microscopic sections of breast and prostate carcinomas, and myometrial leiomyosarcomas, and provide an exhaustive evaluation of several state of the art feature representations for this task. Among the various image descriptors that we chose to compare, including representations based on convolutional neural networks, Fisher vectors, and sparse codes, we found that working with covariance based descriptors shows superior performance on all three types of cancer considered. While covariance descriptors are known to be effective for texture recognition, it is the first time that they are demonstrated to be useful for the proposed task and evaluated against deep learning models. Capitalizing on Region Covariance Descriptors (RCDs), we derive a powerful image descriptor for cancerous tissue recognition termed, Covariance Kernel Descriptor (CKD), which consistently outperformed all the considered image representations. Our experiments show that using CKD lead to 92.83{\%}, 91.51{\%}, and 98.10{\%} classification accuracy for the recognition of breast carcinomas, prostate carcinomas, and myometrial leiomyosarcomas, respectively.",
author = "Panagiotis Stanitsas and Anoop Cherian and Xinyan Li and Alexander Truskinovsky and Vassilios Morellas and Papanikolopoulos, {Nikolaos P}",
year = "2017",
month = "4",
day = "13",
doi = "10.1109/ICPR.2016.7899848",
language = "English (US)",
pages = "1490--1495",
booktitle = "2016 23rd International Conference on Pattern Recognition, ICPR 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Evaluation of feature descriptors for cancerous tissue recognition

AU - Stanitsas, Panagiotis

AU - Cherian, Anoop

AU - Li, Xinyan

AU - Truskinovsky, Alexander

AU - Morellas, Vassilios

AU - Papanikolopoulos, Nikolaos P

PY - 2017/4/13

Y1 - 2017/4/13

N2 - Computer-Aided Diagnosis (CAD) has witnessed a rapid growth over the past decade, providing a variety of automated tools for the analysis of medical images. In surgical pathology, such tools enhance the diagnosing capabilities of pathologists by allowing them to review and diagnose a larger number of cases daily. Geared towards developing such tools, the main goal of this paper is to identify useful computer vision based feature descriptors for recognizing cancerous tissues in histopathologic images. To this end, we use images of Hematoxylin & Eosin-stained microscopic sections of breast and prostate carcinomas, and myometrial leiomyosarcomas, and provide an exhaustive evaluation of several state of the art feature representations for this task. Among the various image descriptors that we chose to compare, including representations based on convolutional neural networks, Fisher vectors, and sparse codes, we found that working with covariance based descriptors shows superior performance on all three types of cancer considered. While covariance descriptors are known to be effective for texture recognition, it is the first time that they are demonstrated to be useful for the proposed task and evaluated against deep learning models. Capitalizing on Region Covariance Descriptors (RCDs), we derive a powerful image descriptor for cancerous tissue recognition termed, Covariance Kernel Descriptor (CKD), which consistently outperformed all the considered image representations. Our experiments show that using CKD lead to 92.83%, 91.51%, and 98.10% classification accuracy for the recognition of breast carcinomas, prostate carcinomas, and myometrial leiomyosarcomas, respectively.

AB - Computer-Aided Diagnosis (CAD) has witnessed a rapid growth over the past decade, providing a variety of automated tools for the analysis of medical images. In surgical pathology, such tools enhance the diagnosing capabilities of pathologists by allowing them to review and diagnose a larger number of cases daily. Geared towards developing such tools, the main goal of this paper is to identify useful computer vision based feature descriptors for recognizing cancerous tissues in histopathologic images. To this end, we use images of Hematoxylin & Eosin-stained microscopic sections of breast and prostate carcinomas, and myometrial leiomyosarcomas, and provide an exhaustive evaluation of several state of the art feature representations for this task. Among the various image descriptors that we chose to compare, including representations based on convolutional neural networks, Fisher vectors, and sparse codes, we found that working with covariance based descriptors shows superior performance on all three types of cancer considered. While covariance descriptors are known to be effective for texture recognition, it is the first time that they are demonstrated to be useful for the proposed task and evaluated against deep learning models. Capitalizing on Region Covariance Descriptors (RCDs), we derive a powerful image descriptor for cancerous tissue recognition termed, Covariance Kernel Descriptor (CKD), which consistently outperformed all the considered image representations. Our experiments show that using CKD lead to 92.83%, 91.51%, and 98.10% classification accuracy for the recognition of breast carcinomas, prostate carcinomas, and myometrial leiomyosarcomas, respectively.

UR - http://www.scopus.com/inward/record.url?scp=85019127456&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019127456&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2016.7899848

DO - 10.1109/ICPR.2016.7899848

M3 - Conference contribution

SP - 1490

EP - 1495

BT - 2016 23rd International Conference on Pattern Recognition, ICPR 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -