Multi-Task Learning with Context-Oriented Self-Attention for Breast Ultrasound Image Classification and Segmentation

Meng Xu; Kuan Huang; Xiaojun Qi

doi:10.1109/ISBI52829.2022.9761685

Multi-Task Learning with Context-Oriented Self-Attention for Breast Ultrasound Image Classification and Segmentation

Meng Xu
, Kuan Huang
, Xiaojun Qi

Utah State University

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

27 Scopus citations

Abstract

Breast cancer is a great threat to women's health. Automatic analysis of Breast UltraSound (BUS) images can help radiologists make more accurate and efficient diagnoses of breast cancer. We propose a Multi-Task Learning Network with Context-Oriented Self-Attention (MTL-COSA) module to automatically and simultaneously segment tumors and classify them as benign or malignant. The COSA module incorporates prior medical knowledge to guide the network to learn contextual relationships for better feature representations in BUS images. Extensive cross-validation experiments are conducted on two public datasets to evaluate the performance of MTL-COSA and several state-of-the-art methods. MTL-COSA achieves the best classification results and second-best segmentation results compared with deep learning-based methods (5 classification methods and 3 segmentation methods).

Original language	English
Title of host publication	IEEE ISBI 2022 Proceedings - 2022 IEEE International Symposium on Biomedical Imaging
Publisher	IEEE Computer Society
ISBN (Electronic)	9781665429238
DOIs	https://doi.org/10.1109/ISBI52829.2022.9761685
State	Published - 2022
Event	19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 - Hybrid, Kolkata, India Duration: 28 Mar 2022 → 31 Mar 2022

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2022-March
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	19th IEEE International Symposium on Biomedical Imaging, ISBI 2022
Country/Territory	India
City	Hybrid, Kolkata
Period	28/03/22 → 31/03/22

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

breast ultrasound
classification
context-oriented self-attention
multi-task learning
segmentation

Access to Document

10.1109/ISBI52829.2022.9761685

Cite this

Xu, M., Huang, K., & Qi, X. (2022). Multi-Task Learning with Context-Oriented Self-Attention for Breast Ultrasound Image Classification and Segmentation. In IEEE ISBI 2022 Proceedings - 2022 IEEE International Symposium on Biomedical Imaging (Proceedings - International Symposium on Biomedical Imaging; Vol. 2022-March). IEEE Computer Society. https://doi.org/10.1109/ISBI52829.2022.9761685

@inproceedings{36dad5ced3a84c9dbad9108d644d24d9,

title = "Multi-Task Learning with Context-Oriented Self-Attention for Breast Ultrasound Image Classification and Segmentation",

abstract = "Breast cancer is a great threat to women's health. Automatic analysis of Breast UltraSound (BUS) images can help radiologists make more accurate and efficient diagnoses of breast cancer. We propose a Multi-Task Learning Network with Context-Oriented Self-Attention (MTL-COSA) module to automatically and simultaneously segment tumors and classify them as benign or malignant. The COSA module incorporates prior medical knowledge to guide the network to learn contextual relationships for better feature representations in BUS images. Extensive cross-validation experiments are conducted on two public datasets to evaluate the performance of MTL-COSA and several state-of-the-art methods. MTL-COSA achieves the best classification results and second-best segmentation results compared with deep learning-based methods (5 classification methods and 3 segmentation methods).",

keywords = "breast ultrasound, classification, context-oriented self-attention, multi-task learning, segmentation",

author = "Meng Xu and Kuan Huang and Xiaojun Qi",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 ; Conference date: 28-03-2022 Through 31-03-2022",

year = "2022",

doi = "10.1109/ISBI52829.2022.9761685",

language = "English",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

booktitle = "IEEE ISBI 2022 Proceedings - 2022 IEEE International Symposium on Biomedical Imaging",

}

Xu, M , Huang, K & Qi, X 2022, Multi-Task Learning with Context-Oriented Self-Attention for Breast Ultrasound Image Classification and Segmentation. in IEEE ISBI 2022 Proceedings - 2022 IEEE International Symposium on Biomedical Imaging. Proceedings - International Symposium on Biomedical Imaging, vol. 2022-March, IEEE Computer Society, 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022, Hybrid, Kolkata, India, 28/03/22. https://doi.org/10.1109/ISBI52829.2022.9761685

Multi-Task Learning with Context-Oriented Self-Attention for Breast Ultrasound Image Classification and Segmentation. / Xu, Meng ; Huang, Kuan; Qi, Xiaojun.
IEEE ISBI 2022 Proceedings - 2022 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2022. (Proceedings - International Symposium on Biomedical Imaging; Vol. 2022-March).

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

TY - GEN

T1 - Multi-Task Learning with Context-Oriented Self-Attention for Breast Ultrasound Image Classification and Segmentation

AU - Xu, Meng

AU - Huang, Kuan

AU - Qi, Xiaojun

PY - 2022

Y1 - 2022

N2 - Breast cancer is a great threat to women's health. Automatic analysis of Breast UltraSound (BUS) images can help radiologists make more accurate and efficient diagnoses of breast cancer. We propose a Multi-Task Learning Network with Context-Oriented Self-Attention (MTL-COSA) module to automatically and simultaneously segment tumors and classify them as benign or malignant. The COSA module incorporates prior medical knowledge to guide the network to learn contextual relationships for better feature representations in BUS images. Extensive cross-validation experiments are conducted on two public datasets to evaluate the performance of MTL-COSA and several state-of-the-art methods. MTL-COSA achieves the best classification results and second-best segmentation results compared with deep learning-based methods (5 classification methods and 3 segmentation methods).

AB - Breast cancer is a great threat to women's health. Automatic analysis of Breast UltraSound (BUS) images can help radiologists make more accurate and efficient diagnoses of breast cancer. We propose a Multi-Task Learning Network with Context-Oriented Self-Attention (MTL-COSA) module to automatically and simultaneously segment tumors and classify them as benign or malignant. The COSA module incorporates prior medical knowledge to guide the network to learn contextual relationships for better feature representations in BUS images. Extensive cross-validation experiments are conducted on two public datasets to evaluate the performance of MTL-COSA and several state-of-the-art methods. MTL-COSA achieves the best classification results and second-best segmentation results compared with deep learning-based methods (5 classification methods and 3 segmentation methods).

KW - breast ultrasound

KW - classification

KW - context-oriented self-attention

KW - multi-task learning

KW - segmentation

UR - https://www.scopus.com/pages/publications/85129607838

U2 - 10.1109/ISBI52829.2022.9761685

DO - 10.1109/ISBI52829.2022.9761685

M3 - Conference contribution

AN - SCOPUS:85129607838

T3 - Proceedings - International Symposium on Biomedical Imaging

BT - IEEE ISBI 2022 Proceedings - 2022 IEEE International Symposium on Biomedical Imaging

PB - IEEE Computer Society

T2 - 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022

Y2 - 28 March 2022 through 31 March 2022

ER -

Multi-Task Learning with Context-Oriented Self-Attention for Breast Ultrasound Image Classification and Segmentation

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this