An AI-based method to retrieve hematoxylin and eosin breast histology images using mammograms

Azam Hamidinekoo; Erika Denton; Kate Honnor; Reyer Zwiggelaar

doi:10.1117/12.2564298

An AI-based method to retrieve hematoxylin and eosin breast histology images using mammograms

Azam Hamidinekoo
, Erika Denton
, Kate Honnor
, Reyer Zwiggelaar

Department of Computer Science

Norfolk and Norwich University Hospitals NHS Foundation Trust

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (ISBN)

1 Citation (Scopus)

Abstract

Early diagnosis of breast cancer can increase survival rate. The assessment process for breast screening follows a triple assessment model: appropriate imaging, clinical assessment and biopsy. Retrieving prior cases with similar cancer symptoms could be used to circumvent incompatibilities in breast cancer grading. Abnormal mass lesions in breast are often co-located with normal tissue, which makes it difficult to describe the whole image with a single binary code. Therefore, we propose an AI-based method to describe mass lesions in semantic abstracts/codes. These codes are used in a searching based method to retrieve similar cases in the archive. This simple and effective network is used for unifying classification and retrieval in a single learning process, while enforcing similar lesion types to have similar semantic codes in a compact form. An advantage of this approach is its scalability to large-scale image retrievals.

Original language	English
Title of host publication	15th International Workshop on Breast Imaging, IWBI 2020
Editors	Hilde Bosmans, Nicholas Marshall, Chantal Van Ongeval
Publisher	SPIE
ISBN (Electronic)	9781510638310
DOIs	https://doi.org/10.1117/12.2564298
Publication status	Published - 22 May 2020
Event	15th International Workshop on Breast Imaging, IWBI 2020 - Leuven, Belgium Duration: 25 May 2020 → 27 May 2020

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	11513
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	15th International Workshop on Breast Imaging, IWBI 2020
Country/Territory	Belgium
City	Leuven
Period	25 May 2020 → 27 May 2020

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Deep Learning
Hematoxylin &Eosin (H&E)
Histology
Image Retrieval
Mammography

Access to Document

10.1117/12.2564298

Permanent link

Persistent link

Cite this

Hamidinekoo, A., Denton, E., Honnor, K., & Zwiggelaar, R. (2020). An AI-based method to retrieve hematoxylin and eosin breast histology images using mammograms. In H. Bosmans, N. Marshall, & C. Van Ongeval (Eds.), 15th International Workshop on Breast Imaging, IWBI 2020 Article 1151319 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11513). SPIE. https://doi.org/10.1117/12.2564298

@inproceedings{ffb13979e64a48a196ff8d01ac787056,

title = "An AI-based method to retrieve hematoxylin and eosin breast histology images using mammograms",

abstract = "Early diagnosis of breast cancer can increase survival rate. The assessment process for breast screening follows a triple assessment model: appropriate imaging, clinical assessment and biopsy. Retrieving prior cases with similar cancer symptoms could be used to circumvent incompatibilities in breast cancer grading. Abnormal mass lesions in breast are often co-located with normal tissue, which makes it difficult to describe the whole image with a single binary code. Therefore, we propose an AI-based method to describe mass lesions in semantic abstracts/codes. These codes are used in a searching based method to retrieve similar cases in the archive. This simple and effective network is used for unifying classification and retrieval in a single learning process, while enforcing similar lesion types to have similar semantic codes in a compact form. An advantage of this approach is its scalability to large-scale image retrievals.",

keywords = "Deep Learning, Hematoxylin \&Eosin (H\&E), Histology, Image Retrieval, Mammography",

author = "Azam Hamidinekoo and Erika Denton and Kate Honnor and Reyer Zwiggelaar",

year = "2020",

month = may,

day = "22",

doi = "10.1117/12.2564298",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Hilde Bosmans and Nicholas Marshall and \{Van Ongeval\}, Chantal",

booktitle = "15th International Workshop on Breast Imaging, IWBI 2020",

address = "United States of America",

note = "15th International Workshop on Breast Imaging, IWBI 2020 ; Conference date: 25-05-2020 Through 27-05-2020",

}

Hamidinekoo, A, Denton, E, Honnor, K & Zwiggelaar, R 2020, An AI-based method to retrieve hematoxylin and eosin breast histology images using mammograms. in H Bosmans, N Marshall & C Van Ongeval (eds), 15th International Workshop on Breast Imaging, IWBI 2020., 1151319, Proceedings of SPIE - The International Society for Optical Engineering, vol. 11513, SPIE, 15th International Workshop on Breast Imaging, IWBI 2020, Leuven, Belgium, 25 May 2020. https://doi.org/10.1117/12.2564298

An AI-based method to retrieve hematoxylin and eosin breast histology images using mammograms. / Hamidinekoo, Azam; Denton, Erika; Honnor, Kate et al.
15th International Workshop on Breast Imaging, IWBI 2020. ed. / Hilde Bosmans; Nicholas Marshall; Chantal Van Ongeval. SPIE, 2020. 1151319 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11513).

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (ISBN)

TY - GEN

T1 - An AI-based method to retrieve hematoxylin and eosin breast histology images using mammograms

AU - Hamidinekoo, Azam

AU - Denton, Erika

AU - Honnor, Kate

AU - Zwiggelaar, Reyer

PY - 2020/5/22

Y1 - 2020/5/22

N2 - Early diagnosis of breast cancer can increase survival rate. The assessment process for breast screening follows a triple assessment model: appropriate imaging, clinical assessment and biopsy. Retrieving prior cases with similar cancer symptoms could be used to circumvent incompatibilities in breast cancer grading. Abnormal mass lesions in breast are often co-located with normal tissue, which makes it difficult to describe the whole image with a single binary code. Therefore, we propose an AI-based method to describe mass lesions in semantic abstracts/codes. These codes are used in a searching based method to retrieve similar cases in the archive. This simple and effective network is used for unifying classification and retrieval in a single learning process, while enforcing similar lesion types to have similar semantic codes in a compact form. An advantage of this approach is its scalability to large-scale image retrievals.

AB - Early diagnosis of breast cancer can increase survival rate. The assessment process for breast screening follows a triple assessment model: appropriate imaging, clinical assessment and biopsy. Retrieving prior cases with similar cancer symptoms could be used to circumvent incompatibilities in breast cancer grading. Abnormal mass lesions in breast are often co-located with normal tissue, which makes it difficult to describe the whole image with a single binary code. Therefore, we propose an AI-based method to describe mass lesions in semantic abstracts/codes. These codes are used in a searching based method to retrieve similar cases in the archive. This simple and effective network is used for unifying classification and retrieval in a single learning process, while enforcing similar lesion types to have similar semantic codes in a compact form. An advantage of this approach is its scalability to large-scale image retrievals.

KW - Deep Learning

KW - Hematoxylin &Eosin (H&E)

KW - Histology

KW - Image Retrieval

KW - Mammography

UR - https://www.scopus.com/pages/publications/85086142352

U2 - 10.1117/12.2564298

DO - 10.1117/12.2564298

M3 - Conference Proceeding (ISBN)

AN - SCOPUS:85086142352

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - 15th International Workshop on Breast Imaging, IWBI 2020

A2 - Bosmans, Hilde

A2 - Marshall, Nicholas

A2 - Van Ongeval, Chantal

PB - SPIE

T2 - 15th International Workshop on Breast Imaging, IWBI 2020

Y2 - 25 May 2020 through 27 May 2020

ER -

Hamidinekoo A, Denton E, Honnor K, Zwiggelaar R. An AI-based method to retrieve hematoxylin and eosin breast histology images using mammograms. In Bosmans H, Marshall N, Van Ongeval C, editors, 15th International Workshop on Breast Imaging, IWBI 2020. SPIE. 2020. 1151319. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.2564298

An AI-based method to retrieve hematoxylin and eosin breast histology images using mammograms

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Permanent link

Other files and links

Fingerprint

Cite this