IRUM: An Image Representation and Unified Learning Method for Breast Cancer Diagnosis from Multi-View Ultrasound Images

Haoyuan Chen; Yonghao Li; Jiadong Zhang; Qi Xu; Meiyu Li; Zhenhui Li; Xuejun Qian; Dinggang Shen

doi:10.1007/978-3-031-73284-3_3

IRUM: An Image Representation and Unified Learning Method for Breast Cancer Diagnosis from Multi-View Ultrasound Images

Haoyuan Chen
, Yonghao Li
, Jiadong Zhang
, Qi Xu
, Meiyu Li
, Zhenhui Li
, Xuejun Qian
, Dinggang Shen^*

^*Corresponding author for this work

Department of Biomedical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Multi-view breast ultrasound imaging has been routinely performed in clinical settings to ensure comprehensive disease evaluation. Recently, artificial intelligence (AI) has been developed to interpret medical images; however, most of the current AI models are restricted to single-view images, resulting in weak representation of breast 3D tissues. Here, we develop an Image Representation and Unified learning Method (IRUM) on a dataset comprising 3800 ultrasound images from 1900 patients with an accuracy of 86.8%. Owing to the design of four distinct learning modules, the proposed IRUM is not only able to predict breast cancer risk using multi-view inputs, but also compatible with single-view input (a commonly encountered situation in clinical practice). We demonstrate that the IRUM achieves superior performance to conventional single-view and multi-view approaches to a certain degree. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Original language	English
Title of host publication	Machine Learning in Medical Imaging
Subtitle of host publication	15th International Workshop, MLMI 2024, Held in Conjunction with MICCAI 2024, Marrakesh, Morocco, October 6, 2024, Proceedings, Part I
Editors	Xuanang Xu, Zhiming Cui, Islem Rekik, Xi Ouyang, Kaicong Sun
Place of Publication	Cham
Publisher	Springer
Pages	22-30
ISBN (Electronic)	978-3-031-73284-3
ISBN (Print)	9783031732836
DOIs	https://doi.org/10.1007/978-3-031-73284-3_3
Publication status	Published - 2025
Event	15th International Workshop on Machine Learning in Medical Imaging (MLMI 2024) - Palmeraie Palace, Marrakesh, Morocco Duration: 6 Oct 2024 → 6 Oct 2024 https://conferences.miccai.org/2024/en/ https://sites.google.com/view/mlmi2024

Publication series

Name	Lecture Notes in Computer Science
Volume	15241
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	15th International Workshop on Machine Learning in Medical Imaging (MLMI 2024)
Place	Morocco
City	Marrakesh
Period	6/10/24 → 6/10/24
Internet address	https://conferences.miccai.org/2024/en/ https://sites.google.com/view/mlmi2024

UN SDGs

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

SDG 3 Good Health and Well-being

Research Keywords

Breast cancer
Consistency learning
Image representation
Multi-view diagnosis
Ultrasound

Access Output

10.1007/978-3-031-73284-3_3

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Chen, H., Li, Y., Zhang, J., Xu, Q., Li, M., Li, Z., Qian, X., & Shen, D. (2025). IRUM: An Image Representation and Unified Learning Method for Breast Cancer Diagnosis from Multi-View Ultrasound Images. In X. Xu, Z. Cui, I. Rekik, X. Ouyang, & K. Sun (Eds.), Machine Learning in Medical Imaging: 15th International Workshop, MLMI 2024, Held in Conjunction with MICCAI 2024, Marrakesh, Morocco, October 6, 2024, Proceedings, Part I (pp. 22-30). (Lecture Notes in Computer Science; Vol. 15241). Springer . https://doi.org/10.1007/978-3-031-73284-3_3

Chen, Haoyuan ; Li, Yonghao ; Zhang, Jiadong et al. / IRUM : An Image Representation and Unified Learning Method for Breast Cancer Diagnosis from Multi-View Ultrasound Images. Machine Learning in Medical Imaging: 15th International Workshop, MLMI 2024, Held in Conjunction with MICCAI 2024, Marrakesh, Morocco, October 6, 2024, Proceedings, Part I. editor / Xuanang Xu ; Zhiming Cui ; Islem Rekik ; Xi Ouyang ; Kaicong Sun. Cham : Springer , 2025. pp. 22-30 (Lecture Notes in Computer Science).

@inproceedings{ba5b5ee5946f4778bf57b4230e22f6bd,

title = "IRUM: An Image Representation and Unified Learning Method for Breast Cancer Diagnosis from Multi-View Ultrasound Images",

abstract = "Multi-view breast ultrasound imaging has been routinely performed in clinical settings to ensure comprehensive disease evaluation. Recently, artificial intelligence (AI) has been developed to interpret medical images; however, most of the current AI models are restricted to single-view images, resulting in weak representation of breast 3D tissues. Here, we develop an Image Representation and Unified learning Method (IRUM) on a dataset comprising 3800 ultrasound images from 1900 patients with an accuracy of 86.8\%. Owing to the design of four distinct learning modules, the proposed IRUM is not only able to predict breast cancer risk using multi-view inputs, but also compatible with single-view input (a commonly encountered situation in clinical practice). We demonstrate that the IRUM achieves superior performance to conventional single-view and multi-view approaches to a certain degree. {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.",

keywords = "Breast cancer, Consistency learning, Image representation, Multi-view diagnosis, Ultrasound",

author = "Haoyuan Chen and Yonghao Li and Jiadong Zhang and Qi Xu and Meiyu Li and Zhenhui Li and Xuejun Qian and Dinggang Shen",

year = "2025",

doi = "10.1007/978-3-031-73284-3\_3",

language = "English",

isbn = "9783031732836",

series = "Lecture Notes in Computer Science",

publisher = "Springer ",

pages = "22--30",

editor = "Xuanang Xu and Zhiming Cui and Islem Rekik and Xi Ouyang and Kaicong Sun",

booktitle = "Machine Learning in Medical Imaging",

note = "15th International Workshop on Machine Learning in Medical Imaging (MLMI 2024) ; Conference date: 06-10-2024 Through 06-10-2024",

url = "https://conferences.miccai.org/2024/en/, https://sites.google.com/view/mlmi2024",

}

Chen, H, Li, Y, Zhang, J, Xu, Q, Li, M, Li, Z, Qian, X & Shen, D 2025, IRUM: An Image Representation and Unified Learning Method for Breast Cancer Diagnosis from Multi-View Ultrasound Images. in X Xu, Z Cui, I Rekik, X Ouyang & K Sun (eds), Machine Learning in Medical Imaging: 15th International Workshop, MLMI 2024, Held in Conjunction with MICCAI 2024, Marrakesh, Morocco, October 6, 2024, Proceedings, Part I. Lecture Notes in Computer Science, vol. 15241, Springer , Cham, pp. 22-30, 15th International Workshop on Machine Learning in Medical Imaging (MLMI 2024), Marrakesh, Morocco, 6/10/24. https://doi.org/10.1007/978-3-031-73284-3_3

IRUM: An Image Representation and Unified Learning Method for Breast Cancer Diagnosis from Multi-View Ultrasound Images. / Chen, Haoyuan; Li, Yonghao; Zhang, Jiadong et al.
Machine Learning in Medical Imaging: 15th International Workshop, MLMI 2024, Held in Conjunction with MICCAI 2024, Marrakesh, Morocco, October 6, 2024, Proceedings, Part I. ed. / Xuanang Xu; Zhiming Cui; Islem Rekik; Xi Ouyang; Kaicong Sun. Cham: Springer , 2025. p. 22-30 (Lecture Notes in Computer Science; Vol. 15241).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - IRUM

T2 - 15th International Workshop on Machine Learning in Medical Imaging (MLMI 2024)

AU - Chen, Haoyuan

AU - Li, Yonghao

AU - Zhang, Jiadong

AU - Xu, Qi

AU - Li, Meiyu

AU - Li, Zhenhui

AU - Qian, Xuejun

AU - Shen, Dinggang

PY - 2025

Y1 - 2025

N2 - Multi-view breast ultrasound imaging has been routinely performed in clinical settings to ensure comprehensive disease evaluation. Recently, artificial intelligence (AI) has been developed to interpret medical images; however, most of the current AI models are restricted to single-view images, resulting in weak representation of breast 3D tissues. Here, we develop an Image Representation and Unified learning Method (IRUM) on a dataset comprising 3800 ultrasound images from 1900 patients with an accuracy of 86.8%. Owing to the design of four distinct learning modules, the proposed IRUM is not only able to predict breast cancer risk using multi-view inputs, but also compatible with single-view input (a commonly encountered situation in clinical practice). We demonstrate that the IRUM achieves superior performance to conventional single-view and multi-view approaches to a certain degree. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

AB - Multi-view breast ultrasound imaging has been routinely performed in clinical settings to ensure comprehensive disease evaluation. Recently, artificial intelligence (AI) has been developed to interpret medical images; however, most of the current AI models are restricted to single-view images, resulting in weak representation of breast 3D tissues. Here, we develop an Image Representation and Unified learning Method (IRUM) on a dataset comprising 3800 ultrasound images from 1900 patients with an accuracy of 86.8%. Owing to the design of four distinct learning modules, the proposed IRUM is not only able to predict breast cancer risk using multi-view inputs, but also compatible with single-view input (a commonly encountered situation in clinical practice). We demonstrate that the IRUM achieves superior performance to conventional single-view and multi-view approaches to a certain degree. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

KW - Breast cancer

KW - Consistency learning

KW - Image representation

KW - Multi-view diagnosis

KW - Ultrasound

UR - https://www.scopus.com/pages/publications/85208231601

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85208231601&origin=recordpage

U2 - 10.1007/978-3-031-73284-3_3

DO - 10.1007/978-3-031-73284-3_3

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9783031732836

T3 - Lecture Notes in Computer Science

SP - 22

EP - 30

BT - Machine Learning in Medical Imaging

A2 - Xu, Xuanang

A2 - Cui, Zhiming

A2 - Rekik, Islem

A2 - Ouyang, Xi

A2 - Sun, Kaicong

PB - Springer

CY - Cham

Y2 - 6 October 2024 through 6 October 2024

ER -

Chen H, Li Y, Zhang J, Xu Q, Li M, Li Z et al. IRUM: An Image Representation and Unified Learning Method for Breast Cancer Diagnosis from Multi-View Ultrasound Images. In Xu X, Cui Z, Rekik I, Ouyang X, Sun K, editors, Machine Learning in Medical Imaging: 15th International Workshop, MLMI 2024, Held in Conjunction with MICCAI 2024, Marrakesh, Morocco, October 6, 2024, Proceedings, Part I. Cham: Springer . 2025. p. 22-30. (Lecture Notes in Computer Science). Epub 2024 Oct 23. doi: 10.1007/978-3-031-73284-3_3

IRUM: An Image Representation and Unified Learning Method for Breast Cancer Diagnosis from Multi-View Ultrasound Images

Abstract

Publication series

Conference

UN SDGs

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this