Invasive Region Segmentation using Pre-trained UNet and Prognosis Analysis of Breast Cancer based on Tumor-Stroma Ratio

Subrata Bhattacharjee; Yeong Byn Hwang; Hee Cheol Kim; Heung Kook Choi; Dongmin Kim; Nam Hoon Cho

doi:10.1109/ICECET55527.2022.9872881

Invasive Region Segmentation using Pre-trained UNet and Prognosis Analysis of Breast Cancer based on Tumor-Stroma Ratio

Subrata Bhattacharjee, Yeong Byn Hwang, Hee Cheol Kim, Heung Kook Choi, Dongmin Kim, Nam Hoon Cho

Department of Pathology

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

1 Citation (Scopus)

Abstract

Breast cancer (BCa) is a type of disease that has multiple prognostic markers that differs from one cancer stage to another. Assessing the area and pattern of cancer regions is essential for pathological investigations. However, the main purpose of this study is to segment the regions of invasive carcinoma (i.e., non-tubular and tubular) in the histological sections of BCa. The segmentation was performed on hematoxylin and eosin (H&E)-stained tissue slides of 42 BCa patients from 5 different centers in Korea. The tumor-stroma ratio (TSR) is a promising prognostic parameter for BCa as well as in other epithelial cancer types estimating the area of stroma and tumor regions. Therefore, in this paper, we used the pre-trained convolutional neural network (CNN) models as a backbone of UNet, to precisely extract the tumor regions from the stroma tissue components for TSR analysis.

Original language	English
Title of host publication	International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665470872
DOIs	https://doi.org/10.1109/ICECET55527.2022.9872881
Publication status	Published - 2022
Event	2022 IEEE International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022 - Prague, Czech Republic Duration: 2022 Jul 20 → 2022 Jul 22

Publication series

Name	International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022

Conference

Conference	2022 IEEE International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022
Country/Territory	Czech Republic
City	Prague
Period	22/7/20 → 22/7/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Science Applications
Computer Vision and Pattern Recognition
Energy Engineering and Power Technology
Electrical and Electronic Engineering
Media Technology
Instrumentation

UN SDGs

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

Access to Document

10.1109/ICECET55527.2022.9872881

Cite this

Bhattacharjee, S., Hwang, Y. B., Kim, H. C., Choi, H. K., Kim, D., & Cho, N. H. (2022). Invasive Region Segmentation using Pre-trained UNet and Prognosis Analysis of Breast Cancer based on Tumor-Stroma Ratio. In International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022 (International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICECET55527.2022.9872881

Bhattacharjee, Subrata ; Hwang, Yeong Byn ; Kim, Hee Cheol et al. / Invasive Region Segmentation using Pre-trained UNet and Prognosis Analysis of Breast Cancer based on Tumor-Stroma Ratio. International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022).

@inproceedings{e76f137418dc453a8a585b6f1d718a08,

title = "Invasive Region Segmentation using Pre-trained UNet and Prognosis Analysis of Breast Cancer based on Tumor-Stroma Ratio",

abstract = "Breast cancer (BCa) is a type of disease that has multiple prognostic markers that differs from one cancer stage to another. Assessing the area and pattern of cancer regions is essential for pathological investigations. However, the main purpose of this study is to segment the regions of invasive carcinoma (i.e., non-tubular and tubular) in the histological sections of BCa. The segmentation was performed on hematoxylin and eosin (H&E)-stained tissue slides of 42 BCa patients from 5 different centers in Korea. The tumor-stroma ratio (TSR) is a promising prognostic parameter for BCa as well as in other epithelial cancer types estimating the area of stroma and tumor regions. Therefore, in this paper, we used the pre-trained convolutional neural network (CNN) models as a backbone of UNet, to precisely extract the tumor regions from the stroma tissue components for TSR analysis.",

keywords = "breast cancer, histopathological, invasive carcinoma, segmentation",

author = "Subrata Bhattacharjee and Hwang, {Yeong Byn} and Kim, {Hee Cheol} and Choi, {Heung Kook} and Dongmin Kim and Cho, {Nam Hoon}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022 ; Conference date: 20-07-2022 Through 22-07-2022",

year = "2022",

doi = "10.1109/ICECET55527.2022.9872881",

language = "English",

series = "International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022",

address = "United States",

}

Bhattacharjee, S, Hwang, YB, Kim, HC, Choi, HK, Kim, D & Cho, NH 2022, Invasive Region Segmentation using Pre-trained UNet and Prognosis Analysis of Breast Cancer based on Tumor-Stroma Ratio. in International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022. International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022, Institute of Electrical and Electronics Engineers Inc., 2022 IEEE International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022, Prague, Czech Republic, 22/7/20. https://doi.org/10.1109/ICECET55527.2022.9872881

Invasive Region Segmentation using Pre-trained UNet and Prognosis Analysis of Breast Cancer based on Tumor-Stroma Ratio. / Bhattacharjee, Subrata; Hwang, Yeong Byn; Kim, Hee Cheol et al.
International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022).

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

TY - GEN

T1 - Invasive Region Segmentation using Pre-trained UNet and Prognosis Analysis of Breast Cancer based on Tumor-Stroma Ratio

AU - Bhattacharjee, Subrata

AU - Hwang, Yeong Byn

AU - Kim, Hee Cheol

AU - Choi, Heung Kook

AU - Kim, Dongmin

AU - Cho, Nam Hoon

PY - 2022

Y1 - 2022

N2 - Breast cancer (BCa) is a type of disease that has multiple prognostic markers that differs from one cancer stage to another. Assessing the area and pattern of cancer regions is essential for pathological investigations. However, the main purpose of this study is to segment the regions of invasive carcinoma (i.e., non-tubular and tubular) in the histological sections of BCa. The segmentation was performed on hematoxylin and eosin (H&E)-stained tissue slides of 42 BCa patients from 5 different centers in Korea. The tumor-stroma ratio (TSR) is a promising prognostic parameter for BCa as well as in other epithelial cancer types estimating the area of stroma and tumor regions. Therefore, in this paper, we used the pre-trained convolutional neural network (CNN) models as a backbone of UNet, to precisely extract the tumor regions from the stroma tissue components for TSR analysis.

AB - Breast cancer (BCa) is a type of disease that has multiple prognostic markers that differs from one cancer stage to another. Assessing the area and pattern of cancer regions is essential for pathological investigations. However, the main purpose of this study is to segment the regions of invasive carcinoma (i.e., non-tubular and tubular) in the histological sections of BCa. The segmentation was performed on hematoxylin and eosin (H&E)-stained tissue slides of 42 BCa patients from 5 different centers in Korea. The tumor-stroma ratio (TSR) is a promising prognostic parameter for BCa as well as in other epithelial cancer types estimating the area of stroma and tumor regions. Therefore, in this paper, we used the pre-trained convolutional neural network (CNN) models as a backbone of UNet, to precisely extract the tumor regions from the stroma tissue components for TSR analysis.

KW - breast cancer

KW - histopathological

KW - invasive carcinoma

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=85138859966&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85138859966&partnerID=8YFLogxK

U2 - 10.1109/ICECET55527.2022.9872881

DO - 10.1109/ICECET55527.2022.9872881

M3 - Conference contribution

AN - SCOPUS:85138859966

T3 - International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022

BT - International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022

Y2 - 20 July 2022 through 22 July 2022

ER -

Bhattacharjee S, Hwang YB, Kim HC, Choi HK, Kim D, Cho NH. Invasive Region Segmentation using Pre-trained UNet and Prognosis Analysis of Breast Cancer based on Tumor-Stroma Ratio. In International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022). doi: 10.1109/ICECET55527.2022.9872881

Invasive Region Segmentation using Pre-trained UNet and Prognosis Analysis of Breast Cancer based on Tumor-Stroma Ratio

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this