MRes-CNN: a multi-branch residual CNN for colorectal histopathological image classification

Lingling Yuan; Md Mamunur Rahaman; Hongzan Sun; Xiaoyan Li; Marcin Grzegorzek; Ning Xu; Chen Li

doi:10.1007/978-981-96-0840-9_9

MRes-CNN: a multi-branch residual CNN for colorectal histopathological image classification

Lingling Yuan, Md Mamunur Rahaman, Hongzan Sun, Xiaoyan Li, Marcin Grzegorzek, Ning Xu, Chen Li

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

Abstract

This research introduces the Multi-branch Residual Convolutional Neural Network (MRes-CNN) to enhance the accuracy of colorectal histopathological image classification. MRes-CNN incorporates MRes Blocks and Attention Module, optimizing efficiency in analyzing images. Employing the open-sourced Enteroscope Biopsy Histopathological Hematoxylin and Eosin Image Dataset (EBHI) for empirical validation, MRes-CNN achieves an impressive average accuracy of 92.44% across three experiments, significantly outperforming 21 existing deep learning (DL) models. Ablation studies confirm the crucial roles of MRes Blocks and Attention Module in enhancing model performance. These findings underscore the potential of MRes-CNN to transform colorectal histopathological image classification, promising substantial benefits for clinical practice and medical research.

Original language	English
Title of host publication	Advanced Data Mining and Applications
Subtitle of host publication	20th International Conference, ADMA 2024. Proceedings, Part IV
Editors	Quan Z. Sheng, Gill Dobbie, Jing Jiang, Xuyun Zhang, Wei Emma Zhang, Yannis Manolopoulos, Jia Wu, Wathiq Mansoor, Congbo Ma
Place of Publication	Singapore
Publisher	Springer, Springer Nature
Pages	125-139
Number of pages	15
ISBN (Electronic)	9789819608409
ISBN (Print)	9789819608393
DOIs	https://doi.org/10.1007/978-981-96-0840-9_9
Publication status	Published - 2025
Externally published	Yes
Event	20th International Conference on Advanced Data Mining Applications, ADMA 2024 - Sydney, Australia Duration: 3 Dec 2024 → 5 Dec 2024

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	15390
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	20th International Conference on Advanced Data Mining Applications, ADMA 2024
Country/Territory	Australia
City	Sydney
Period	3/12/24 → 5/12/24

Keywords

Multi-branch Residual model
Convolution Neural Network
Colorectal histopathology
Five-class image classification

Access to Document

10.1007/978-981-96-0840-9_9

Cite this

Yuan, L., Rahaman, M. M., Sun, H., Li, X., Grzegorzek, M., Xu, N., & Li, C. (2025). MRes-CNN: a multi-branch residual CNN for colorectal histopathological image classification. In Q. Z. Sheng, G. Dobbie, J. Jiang, X. Zhang, W. E. Zhang, Y. Manolopoulos, J. Wu, W. Mansoor, & C. Ma (Eds.), Advanced Data Mining and Applications: 20th International Conference, ADMA 2024. Proceedings, Part IV (pp. 125-139). (Lecture Notes in Computer Science; Vol. 15390). Springer, Springer Nature. https://doi.org/10.1007/978-981-96-0840-9_9

Yuan, Lingling ; Rahaman, Md Mamunur ; Sun, Hongzan et al. / MRes-CNN : a multi-branch residual CNN for colorectal histopathological image classification. Advanced Data Mining and Applications: 20th International Conference, ADMA 2024. Proceedings, Part IV. editor / Quan Z. Sheng ; Gill Dobbie ; Jing Jiang ; Xuyun Zhang ; Wei Emma Zhang ; Yannis Manolopoulos ; Jia Wu ; Wathiq Mansoor ; Congbo Ma. Singapore : Springer, Springer Nature, 2025. pp. 125-139 (Lecture Notes in Computer Science).

@inproceedings{757dc08550fa4a0f9d9f6cfcb3330c69,

title = "MRes-CNN: a multi-branch residual CNN for colorectal histopathological image classification",

abstract = "This research introduces the Multi-branch Residual Convolutional Neural Network (MRes-CNN) to enhance the accuracy of colorectal histopathological image classification. MRes-CNN incorporates MRes Blocks and Attention Module, optimizing efficiency in analyzing images. Employing the open-sourced Enteroscope Biopsy Histopathological Hematoxylin and Eosin Image Dataset (EBHI) for empirical validation, MRes-CNN achieves an impressive average accuracy of 92.44\% across three experiments, significantly outperforming 21 existing deep learning (DL) models. Ablation studies confirm the crucial roles of MRes Blocks and Attention Module in enhancing model performance. These findings underscore the potential of MRes-CNN to transform colorectal histopathological image classification, promising substantial benefits for clinical practice and medical research. ",

keywords = "Multi-branch Residual model, Convolution Neural Network, Colorectal histopathology, Five-class image classification",

author = "Lingling Yuan and Rahaman, \{Md Mamunur\} and Hongzan Sun and Xiaoyan Li and Marcin Grzegorzek and Ning Xu and Chen Li",

year = "2025",

doi = "10.1007/978-981-96-0840-9\_9",

language = "English",

isbn = "9789819608393",

series = "Lecture Notes in Computer Science",

publisher = "Springer, Springer Nature",

pages = "125--139",

editor = "Sheng, \{Quan Z.\} and Gill Dobbie and Jing Jiang and Xuyun Zhang and Zhang, \{Wei Emma\} and Yannis Manolopoulos and Jia Wu and Wathiq Mansoor and Congbo Ma",

booktitle = "Advanced Data Mining and Applications",

address = "United States",

note = "20th International Conference on Advanced Data Mining Applications, ADMA 2024 ; Conference date: 03-12-2024 Through 05-12-2024",

}

Yuan, L, Rahaman, MM, Sun, H, Li, X, Grzegorzek, M, Xu, N & Li, C 2025, MRes-CNN: a multi-branch residual CNN for colorectal histopathological image classification. in QZ Sheng, G Dobbie, J Jiang, X Zhang, WE Zhang, Y Manolopoulos, J Wu, W Mansoor & C Ma (eds), Advanced Data Mining and Applications: 20th International Conference, ADMA 2024. Proceedings, Part IV. Lecture Notes in Computer Science, vol. 15390, Springer, Springer Nature, Singapore, pp. 125-139, 20th International Conference on Advanced Data Mining Applications, ADMA 2024, Sydney, Australia, 3/12/24. https://doi.org/10.1007/978-981-96-0840-9_9

MRes-CNN: a multi-branch residual CNN for colorectal histopathological image classification. / Yuan, Lingling; Rahaman, Md Mamunur; Sun, Hongzan et al.
Advanced Data Mining and Applications: 20th International Conference, ADMA 2024. Proceedings, Part IV. ed. / Quan Z. Sheng; Gill Dobbie; Jing Jiang; Xuyun Zhang; Wei Emma Zhang; Yannis Manolopoulos; Jia Wu; Wathiq Mansoor; Congbo Ma. Singapore: Springer, Springer Nature, 2025. p. 125-139 (Lecture Notes in Computer Science; Vol. 15390).

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

TY - GEN

T1 - MRes-CNN

T2 - 20th International Conference on Advanced Data Mining Applications, ADMA 2024

AU - Yuan, Lingling

AU - Rahaman, Md Mamunur

AU - Sun, Hongzan

AU - Li, Xiaoyan

AU - Grzegorzek, Marcin

AU - Xu, Ning

AU - Li, Chen

PY - 2025

Y1 - 2025

N2 - This research introduces the Multi-branch Residual Convolutional Neural Network (MRes-CNN) to enhance the accuracy of colorectal histopathological image classification. MRes-CNN incorporates MRes Blocks and Attention Module, optimizing efficiency in analyzing images. Employing the open-sourced Enteroscope Biopsy Histopathological Hematoxylin and Eosin Image Dataset (EBHI) for empirical validation, MRes-CNN achieves an impressive average accuracy of 92.44% across three experiments, significantly outperforming 21 existing deep learning (DL) models. Ablation studies confirm the crucial roles of MRes Blocks and Attention Module in enhancing model performance. These findings underscore the potential of MRes-CNN to transform colorectal histopathological image classification, promising substantial benefits for clinical practice and medical research.

AB - This research introduces the Multi-branch Residual Convolutional Neural Network (MRes-CNN) to enhance the accuracy of colorectal histopathological image classification. MRes-CNN incorporates MRes Blocks and Attention Module, optimizing efficiency in analyzing images. Employing the open-sourced Enteroscope Biopsy Histopathological Hematoxylin and Eosin Image Dataset (EBHI) for empirical validation, MRes-CNN achieves an impressive average accuracy of 92.44% across three experiments, significantly outperforming 21 existing deep learning (DL) models. Ablation studies confirm the crucial roles of MRes Blocks and Attention Module in enhancing model performance. These findings underscore the potential of MRes-CNN to transform colorectal histopathological image classification, promising substantial benefits for clinical practice and medical research.

KW - Multi-branch Residual model

KW - Convolution Neural Network

KW - Colorectal histopathology

KW - Five-class image classification

UR - https://www.scopus.com/pages/publications/85213364059

U2 - 10.1007/978-981-96-0840-9_9

DO - 10.1007/978-981-96-0840-9_9

M3 - Conference proceeding contribution

SN - 9789819608393

T3 - Lecture Notes in Computer Science

SP - 125

EP - 139

BT - Advanced Data Mining and Applications

A2 - Sheng, Quan Z.

A2 - Dobbie, Gill

A2 - Jiang, Jing

A2 - Zhang, Xuyun

A2 - Zhang, Wei Emma

A2 - Manolopoulos, Yannis

A2 - Wu, Jia

A2 - Mansoor, Wathiq

A2 - Ma, Congbo

PB - Springer, Springer Nature

CY - Singapore

Y2 - 3 December 2024 through 5 December 2024

ER -

Yuan L, Rahaman MM, Sun H, Li X, Grzegorzek M, Xu N et al. MRes-CNN: a multi-branch residual CNN for colorectal histopathological image classification. In Sheng QZ, Dobbie G, Jiang J, Zhang X, Zhang WE, Manolopoulos Y, Wu J, Mansoor W, Ma C, editors, Advanced Data Mining and Applications: 20th International Conference, ADMA 2024. Proceedings, Part IV. Singapore: Springer, Springer Nature. 2025. p. 125-139. (Lecture Notes in Computer Science). doi: 10.1007/978-981-96-0840-9_9