Classification and Retrieval of Digital Pathology Scans: A New Dataset

Morteza Babaie; Shivam Kalra; Aditya Sriram; Christopher Mitcheltree; Shujin Zhu; Amin Khatami; Shahryar Rahnamayan; Hamid R. Tizhoosh

doi:10.1109/CVPRW.2017.106

Classification and Retrieval of Digital Pathology Scans: A New Dataset

Morteza Babaie, Shivam Kalra, Aditya Sriram, Christopher Mitcheltree, Shujin Zhu, Amin Khatami, Shahryar Rahnamayan, Hamid R. Tizhoosh

Artificial Intelligence and Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we introduce a new dataset, Kimia Path24, for image classification and retrieval in digital pathology. We use the whole scan images of 24 different tissue textures to generate 1,325 test patches of size 1000x1000 (0.5mm x 0.5mm). Training data can be generated according to preferences of algorithm designer and can range from approximately 27,000 to over 50,000 patches if the preset parameters are adopted. We propose a compound patch-and-scan accuracy measurement that makes achieving high accuracies quite challenging. In addition, we set the benchmarking line by applying LBP, dictionary approach and convolutional neural nets (CNNs) and report their results. The highest accuracy was 41.80% for CNN.

Original language	English (US)
Title of host publication	Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Publisher	IEEE Computer Society
Pages	760-768
Number of pages	9
ISBN (Electronic)	9781538607336
DOIs	https://doi.org/10.1109/CVPRW.2017.106
State	Published - Aug 22 2017
Event	30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 - Honolulu, United States Duration: Jul 21 2017 → Jul 26 2017

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2017-July
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Country/Territory	United States
City	Honolulu
Period	7/21/17 → 7/26/17

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/CVPRW.2017.106

Cite this

Babaie, M., Kalra, S., Sriram, A., Mitcheltree, C., Zhu, S., Khatami, A., Rahnamayan, S., & Tizhoosh, H. R. (2017). Classification and Retrieval of Digital Pathology Scans: A New Dataset. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 (pp. 760-768). Article 8014840 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2017-July). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2017.106

Classification and Retrieval of Digital Pathology Scans: A New Dataset. / Babaie, Morteza; Kalra, Shivam; Sriram, Aditya et al.
Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. IEEE Computer Society, 2017. p. 760-768 8014840 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2017-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Babaie, M, Kalra, S, Sriram, A, Mitcheltree, C, Zhu, S, Khatami, A, Rahnamayan, S & Tizhoosh, HR 2017, Classification and Retrieval of Digital Pathology Scans: A New Dataset. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017., 8014840, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2017-July, IEEE Computer Society, pp. 760-768, 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017, Honolulu, United States, 7/21/17. https://doi.org/10.1109/CVPRW.2017.106

Babaie M, Kalra S, Sriram A, Mitcheltree C, Zhu S, Khatami A et al. Classification and Retrieval of Digital Pathology Scans: A New Dataset. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. IEEE Computer Society. 2017. p. 760-768. 8014840. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW.2017.106

@inproceedings{fb87880e3fca417fb101b093d297c9a7,

title = "Classification and Retrieval of Digital Pathology Scans: A New Dataset",

abstract = "In this paper, we introduce a new dataset, Kimia Path24, for image classification and retrieval in digital pathology. We use the whole scan images of 24 different tissue textures to generate 1,325 test patches of size 1000x1000 (0.5mm x 0.5mm). Training data can be generated according to preferences of algorithm designer and can range from approximately 27,000 to over 50,000 patches if the preset parameters are adopted. We propose a compound patch-and-scan accuracy measurement that makes achieving high accuracies quite challenging. In addition, we set the benchmarking line by applying LBP, dictionary approach and convolutional neural nets (CNNs) and report their results. The highest accuracy was 41.80% for CNN.",

author = "Morteza Babaie and Shivam Kalra and Aditya Sriram and Christopher Mitcheltree and Shujin Zhu and Amin Khatami and Shahryar Rahnamayan and Tizhoosh, {Hamid R.}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 ; Conference date: 21-07-2017 Through 26-07-2017",

year = "2017",

month = aug,

day = "22",

doi = "10.1109/CVPRW.2017.106",

language = "English (US)",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "760--768",

booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017",

}

TY - GEN

T1 - Classification and Retrieval of Digital Pathology Scans

T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017

AU - Babaie, Morteza

AU - Kalra, Shivam

AU - Sriram, Aditya

AU - Mitcheltree, Christopher

AU - Zhu, Shujin

AU - Khatami, Amin

AU - Rahnamayan, Shahryar

AU - Tizhoosh, Hamid R.

PY - 2017/8/22

Y1 - 2017/8/22

N2 - In this paper, we introduce a new dataset, Kimia Path24, for image classification and retrieval in digital pathology. We use the whole scan images of 24 different tissue textures to generate 1,325 test patches of size 1000x1000 (0.5mm x 0.5mm). Training data can be generated according to preferences of algorithm designer and can range from approximately 27,000 to over 50,000 patches if the preset parameters are adopted. We propose a compound patch-and-scan accuracy measurement that makes achieving high accuracies quite challenging. In addition, we set the benchmarking line by applying LBP, dictionary approach and convolutional neural nets (CNNs) and report their results. The highest accuracy was 41.80% for CNN.

AB - In this paper, we introduce a new dataset, Kimia Path24, for image classification and retrieval in digital pathology. We use the whole scan images of 24 different tissue textures to generate 1,325 test patches of size 1000x1000 (0.5mm x 0.5mm). Training data can be generated according to preferences of algorithm designer and can range from approximately 27,000 to over 50,000 patches if the preset parameters are adopted. We propose a compound patch-and-scan accuracy measurement that makes achieving high accuracies quite challenging. In addition, we set the benchmarking line by applying LBP, dictionary approach and convolutional neural nets (CNNs) and report their results. The highest accuracy was 41.80% for CNN.

UR - http://www.scopus.com/inward/record.url?scp=85030229949&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030229949&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2017.106

DO - 10.1109/CVPRW.2017.106

M3 - Conference contribution

AN - SCOPUS:85030229949

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 760

EP - 768

BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017

PB - IEEE Computer Society

Y2 - 21 July 2017 through 26 July 2017

ER -

Classification and Retrieval of Digital Pathology Scans: A New Dataset

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this