Impact of JPEG 2000 compression on deep convolutional neural networks for metastatic cancer detection in histopathological images

Farhad Ghazvinian Zanjani (Corresponding author), Svitlana Zinger, Bastian Piepers, Saeed Mahmoudpour, Peter Schelkens, Peter de With

Research output: Contribution to journalArticleAcademicpeer-review

21 Downloads (Pure)

Abstract

The availability of massive amounts of data in histopathological whole-slide images (WSIs) has enabled the application of deep learning models and especially convolutional neural networks (CNNs), which have shown a high potential for improvement in cancer diagnosis. However, storage and transmission of large amounts of data such as gigapixel histopathological WSIs are challenging. Exploiting lossy compression algorithms for medical images is controversial but, as long as the clinical diagnosis is not affected, is acceptable. We study the impact of JPEG 2000 compression on our proposed CNN-based algorithm, which has produced performance comparable to that of pathologists and which was ranked second place in the CAMELYON17 challenge. Detecting tumor metastases in hematoxylin and eosin-stained tissue sections of breast lymph nodes is evaluated and compared with the pathologists’ diagnoses in three different experimental setups. Our experiments show that the CNN model is robust against compression ratios up to 24:1 when it is trained on uncompressed high-quality images. We demonstrate that a model trained on lower quality images—i.e., lossy compressed images—depicts a classification performance that is significantly improved for the corresponding compression ratio. Moreover, it is also observed that the model performs equally well on all higher-quality images. These properties will help to design cloud-based computer-aided diagnosis (CAD) systems, e.g., telemedicine that employ deep CNN models that are more robust to image quality variations due to compression required to address data storage and transmission constraints. However, the results presented are specific to the CAD system and application described, and further work is needed to examine whether they generalize to other systems and applications.
Original languageEnglish
Article number027501
Number of pages9
JournalJournal of Medical Imaging
Volume6
Issue number2
DOIs
Publication statusPublished - 1 Apr 2019

Fingerprint

Neural Networks (Computer)
Neoplasms
Telemedicine
Information Storage and Retrieval
Hematoxylin
Eosine Yellowish-(YS)
Breast
Lymph Nodes
Learning
Neoplasm Metastasis
Pathologists

Keywords

  • convolutional neural networks
  • digital pathology
  • image quality
  • JPEG 2000 compression
  • tumor detection

Cite this

@article{8fc07c0481d54e9fb4d8df34b6c2e3cb,
title = "Impact of JPEG 2000 compression on deep convolutional neural networks for metastatic cancer detection in histopathological images",
abstract = "The availability of massive amounts of data in histopathological whole-slide images (WSIs) has enabled the application of deep learning models and especially convolutional neural networks (CNNs), which have shown a high potential for improvement in cancer diagnosis. However, storage and transmission of large amounts of data such as gigapixel histopathological WSIs are challenging. Exploiting lossy compression algorithms for medical images is controversial but, as long as the clinical diagnosis is not affected, is acceptable. We study the impact of JPEG 2000 compression on our proposed CNN-based algorithm, which has produced performance comparable to that of pathologists and which was ranked second place in the CAMELYON17 challenge. Detecting tumor metastases in hematoxylin and eosin-stained tissue sections of breast lymph nodes is evaluated and compared with the pathologists’ diagnoses in three different experimental setups. Our experiments show that the CNN model is robust against compression ratios up to 24:1 when it is trained on uncompressed high-quality images. We demonstrate that a model trained on lower quality images—i.e., lossy compressed images—depicts a classification performance that is significantly improved for the corresponding compression ratio. Moreover, it is also observed that the model performs equally well on all higher-quality images. These properties will help to design cloud-based computer-aided diagnosis (CAD) systems, e.g., telemedicine that employ deep CNN models that are more robust to image quality variations due to compression required to address data storage and transmission constraints. However, the results presented are specific to the CAD system and application described, and further work is needed to examine whether they generalize to other systems and applications.",
keywords = "convolutional neural networks, digital pathology, image quality, JPEG 2000 compression, tumor detection",
author = "{Ghazvinian Zanjani}, Farhad and Svitlana Zinger and Bastian Piepers and Saeed Mahmoudpour and Peter Schelkens and {de With}, Peter",
year = "2019",
month = "4",
day = "1",
doi = "10.1117/1.JMI.6.2.027501",
language = "English",
volume = "6",
journal = "Journal of Medical Imaging",
issn = "2329-4302",
publisher = "SPIE",
number = "2",

}

Impact of JPEG 2000 compression on deep convolutional neural networks for metastatic cancer detection in histopathological images. / Ghazvinian Zanjani, Farhad (Corresponding author); Zinger, Svitlana; Piepers, Bastian ; Mahmoudpour, Saeed; Schelkens, Peter; de With, Peter.

In: Journal of Medical Imaging, Vol. 6, No. 2, 027501, 01.04.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Impact of JPEG 2000 compression on deep convolutional neural networks for metastatic cancer detection in histopathological images

AU - Ghazvinian Zanjani, Farhad

AU - Zinger, Svitlana

AU - Piepers, Bastian

AU - Mahmoudpour, Saeed

AU - Schelkens, Peter

AU - de With, Peter

PY - 2019/4/1

Y1 - 2019/4/1

N2 - The availability of massive amounts of data in histopathological whole-slide images (WSIs) has enabled the application of deep learning models and especially convolutional neural networks (CNNs), which have shown a high potential for improvement in cancer diagnosis. However, storage and transmission of large amounts of data such as gigapixel histopathological WSIs are challenging. Exploiting lossy compression algorithms for medical images is controversial but, as long as the clinical diagnosis is not affected, is acceptable. We study the impact of JPEG 2000 compression on our proposed CNN-based algorithm, which has produced performance comparable to that of pathologists and which was ranked second place in the CAMELYON17 challenge. Detecting tumor metastases in hematoxylin and eosin-stained tissue sections of breast lymph nodes is evaluated and compared with the pathologists’ diagnoses in three different experimental setups. Our experiments show that the CNN model is robust against compression ratios up to 24:1 when it is trained on uncompressed high-quality images. We demonstrate that a model trained on lower quality images—i.e., lossy compressed images—depicts a classification performance that is significantly improved for the corresponding compression ratio. Moreover, it is also observed that the model performs equally well on all higher-quality images. These properties will help to design cloud-based computer-aided diagnosis (CAD) systems, e.g., telemedicine that employ deep CNN models that are more robust to image quality variations due to compression required to address data storage and transmission constraints. However, the results presented are specific to the CAD system and application described, and further work is needed to examine whether they generalize to other systems and applications.

AB - The availability of massive amounts of data in histopathological whole-slide images (WSIs) has enabled the application of deep learning models and especially convolutional neural networks (CNNs), which have shown a high potential for improvement in cancer diagnosis. However, storage and transmission of large amounts of data such as gigapixel histopathological WSIs are challenging. Exploiting lossy compression algorithms for medical images is controversial but, as long as the clinical diagnosis is not affected, is acceptable. We study the impact of JPEG 2000 compression on our proposed CNN-based algorithm, which has produced performance comparable to that of pathologists and which was ranked second place in the CAMELYON17 challenge. Detecting tumor metastases in hematoxylin and eosin-stained tissue sections of breast lymph nodes is evaluated and compared with the pathologists’ diagnoses in three different experimental setups. Our experiments show that the CNN model is robust against compression ratios up to 24:1 when it is trained on uncompressed high-quality images. We demonstrate that a model trained on lower quality images—i.e., lossy compressed images—depicts a classification performance that is significantly improved for the corresponding compression ratio. Moreover, it is also observed that the model performs equally well on all higher-quality images. These properties will help to design cloud-based computer-aided diagnosis (CAD) systems, e.g., telemedicine that employ deep CNN models that are more robust to image quality variations due to compression required to address data storage and transmission constraints. However, the results presented are specific to the CAD system and application described, and further work is needed to examine whether they generalize to other systems and applications.

KW - convolutional neural networks

KW - digital pathology

KW - image quality

KW - JPEG 2000 compression

KW - tumor detection

UR - http://www.scopus.com/inward/record.url?scp=85065464083&partnerID=8YFLogxK

U2 - 10.1117/1.JMI.6.2.027501

DO - 10.1117/1.JMI.6.2.027501

M3 - Article

C2 - 31037247

VL - 6

JO - Journal of Medical Imaging

JF - Journal of Medical Imaging

SN - 2329-4302

IS - 2

M1 - 027501

ER -