Ensemble Learning for Diabetic Foot Ulcer Segmentation based on DFUC2022 Dataset

Pin Xu; Xin Wu; Yanyi Li; Ejaz Ul Haq; Jianping Yin; Kuan Li

doi:10.1145/3573428.3573737

Ensemble Learning for Diabetic Foot Ulcer Segmentation based on DFUC2022 Dataset

Pin Xu
, Xin Wu
, Yanyi Li
, Ejaz Ul Haq
, Jianping Yin
, Kuan Li

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

4 Scopus citations

Abstract

In order to increase the segmentation impact of the Diabetic Foot Ulcer Challenge 2022 dataset, we train a selection of popular deep learning segmentation algorithms and improve training methods, such as adding Dice term to loss function, employing transfer learning and poly learning rate update strategy, etc., in this paper. Experiments show that our method is effective, we get a Dice score of 0.7045, which is better than the official baseline result of 0.6277. Moreover, we integrate the above segmentation models using four ensemble methods to evaluate segmentation performance, such as Averaging, Weighting, Voting, and Stacking. We observed that our proposed one-layer CNN stacking network exhibits superior segmentation performance (Dice score: 0.7142) compared to single CNN model and other three ensemble methods. Our performance surpasses the baseline result, placing us in the top 10 in the Diabetic Foot Ulcer Challenge 2022.

Original language	English
Title of host publication	Proceedings of 2022 6th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2022
Publisher	Association for Computing Machinery
Pages	1750-1754
Number of pages	5
ISBN (Electronic)	9781450397148
DOIs	https://doi.org/10.1145/3573428.3573737
State	Published - 21 Oct 2022
Externally published	Yes
Event	6th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2022 - Virtual, Online, China Duration: 21 Oct 2022 → 23 Oct 2022

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	6th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2022
Country/Territory	China
City	Virtual, Online
Period	21/10/22 → 23/10/22

Bibliographical note

Publisher Copyright:
© 2022 Association for Computing Machinery.

Keywords

DFUC2022
Deep learning
Diabetic foot ulcer
Ensemble learning
Image segmentation

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/3573428.3573737

Cite this

Xu, P., Wu, X., Li, Y., Haq, E. U., Yin, J., & Li, K. (2022). Ensemble Learning for Diabetic Foot Ulcer Segmentation based on DFUC2022 Dataset. In Proceedings of 2022 6th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2022 (pp. 1750-1754). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3573428.3573737

@inproceedings{5c68d1fe3d2246529a839a8a7bb4359b,

title = "Ensemble Learning for Diabetic Foot Ulcer Segmentation based on DFUC2022 Dataset",

abstract = "In order to increase the segmentation impact of the Diabetic Foot Ulcer Challenge 2022 dataset, we train a selection of popular deep learning segmentation algorithms and improve training methods, such as adding Dice term to loss function, employing transfer learning and poly learning rate update strategy, etc., in this paper. Experiments show that our method is effective, we get a Dice score of 0.7045, which is better than the official baseline result of 0.6277. Moreover, we integrate the above segmentation models using four ensemble methods to evaluate segmentation performance, such as Averaging, Weighting, Voting, and Stacking. We observed that our proposed one-layer CNN stacking network exhibits superior segmentation performance (Dice score: 0.7142) compared to single CNN model and other three ensemble methods. Our performance surpasses the baseline result, placing us in the top 10 in the Diabetic Foot Ulcer Challenge 2022.",

keywords = "DFUC2022, Deep learning, Diabetic foot ulcer, Ensemble learning, Image segmentation",

author = "Pin Xu and Xin Wu and Yanyi Li and Haq, \{Ejaz Ul\} and Jianping Yin and Kuan Li",

note = "Publisher Copyright: {\textcopyright} 2022 Association for Computing Machinery.; 6th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2022 ; Conference date: 21-10-2022 Through 23-10-2022",

year = "2022",

month = oct,

day = "21",

doi = "10.1145/3573428.3573737",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "1750--1754",

booktitle = "Proceedings of 2022 6th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2022",

}

Xu, P, Wu, X, Li, Y, Haq, EU, Yin, J & Li, K 2022, Ensemble Learning for Diabetic Foot Ulcer Segmentation based on DFUC2022 Dataset. in Proceedings of 2022 6th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2022. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 1750-1754, 6th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2022, Virtual, Online, China, 21/10/22. https://doi.org/10.1145/3573428.3573737

Ensemble Learning for Diabetic Foot Ulcer Segmentation based on DFUC2022 Dataset. / Xu, Pin; Wu, Xin; Li, Yanyi et al.
Proceedings of 2022 6th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2022. Association for Computing Machinery, 2022. p. 1750-1754 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Ensemble Learning for Diabetic Foot Ulcer Segmentation based on DFUC2022 Dataset

AU - Xu, Pin

AU - Wu, Xin

AU - Li, Yanyi

AU - Haq, Ejaz Ul

AU - Yin, Jianping

AU - Li, Kuan

PY - 2022/10/21

Y1 - 2022/10/21

N2 - In order to increase the segmentation impact of the Diabetic Foot Ulcer Challenge 2022 dataset, we train a selection of popular deep learning segmentation algorithms and improve training methods, such as adding Dice term to loss function, employing transfer learning and poly learning rate update strategy, etc., in this paper. Experiments show that our method is effective, we get a Dice score of 0.7045, which is better than the official baseline result of 0.6277. Moreover, we integrate the above segmentation models using four ensemble methods to evaluate segmentation performance, such as Averaging, Weighting, Voting, and Stacking. We observed that our proposed one-layer CNN stacking network exhibits superior segmentation performance (Dice score: 0.7142) compared to single CNN model and other three ensemble methods. Our performance surpasses the baseline result, placing us in the top 10 in the Diabetic Foot Ulcer Challenge 2022.

AB - In order to increase the segmentation impact of the Diabetic Foot Ulcer Challenge 2022 dataset, we train a selection of popular deep learning segmentation algorithms and improve training methods, such as adding Dice term to loss function, employing transfer learning and poly learning rate update strategy, etc., in this paper. Experiments show that our method is effective, we get a Dice score of 0.7045, which is better than the official baseline result of 0.6277. Moreover, we integrate the above segmentation models using four ensemble methods to evaluate segmentation performance, such as Averaging, Weighting, Voting, and Stacking. We observed that our proposed one-layer CNN stacking network exhibits superior segmentation performance (Dice score: 0.7142) compared to single CNN model and other three ensemble methods. Our performance surpasses the baseline result, placing us in the top 10 in the Diabetic Foot Ulcer Challenge 2022.

KW - DFUC2022

KW - Deep learning

KW - Diabetic foot ulcer

KW - Ensemble learning

KW - Image segmentation

UR - https://www.scopus.com/pages/publications/85150486156

U2 - 10.1145/3573428.3573737

DO - 10.1145/3573428.3573737

M3 - Conference contribution

AN - SCOPUS:85150486156

T3 - ACM International Conference Proceeding Series

SP - 1750

EP - 1754

BT - Proceedings of 2022 6th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2022

PB - Association for Computing Machinery

T2 - 6th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2022

Y2 - 21 October 2022 through 23 October 2022

ER -

Xu P, Wu X, Li Y, Haq EU, Yin J, Li K. Ensemble Learning for Diabetic Foot Ulcer Segmentation based on DFUC2022 Dataset. In Proceedings of 2022 6th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2022. Association for Computing Machinery. 2022. p. 1750-1754. (ACM International Conference Proceeding Series). doi: 10.1145/3573428.3573737

Ensemble Learning for Diabetic Foot Ulcer Segmentation based on DFUC2022 Dataset

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this