Automatic Detection of Oral Lesion Measurement Ruler Toward Computer-Aided Image-Based Oral Cancer Screening

Zhiyun Xue; Kelly Yu; Paul C. Pearlman; Anabik Pal; Tseng Cheng Chen; Chun Hung Hua; Chung Jan Kang; Chih Yen Chien; Ming Hsui Tsai; Cheng Ping Wang; Anil K. Chaturvedi; Sameer Antani

doi:10.1109/EMBC48229.2022.9871610

Automatic Detection of Oral Lesion Measurement Ruler Toward Computer-Aided Image-Based Oral Cancer Screening

Zhiyun Xue^*, Kelly Yu, Paul C. Pearlman, Anabik Pal, Tseng Cheng Chen, Chun Hung Hua, Chung Jan Kang, Chih Yen Chien, Ming Hsui Tsai, Cheng Ping Wang, Anil K. Chaturvedi, Sameer Antani

^*Corresponding author for this work

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

6 Scopus citations

Abstract

Intelligent computer-aided algorithms analyzing photographs of various mouth regions can help in reducing the high subjectivity in human assessment of oral lesions. Very often, in the images, a ruler is placed near a suspected lesion to indicate its location and as a physical size reference. In this paper, we compared two deep-learning networks: ResNeSt and ViT, to automatically identify ruler images. Even though the ImageN et 1K dataset contains a 'ruler' class label, the pre-trained models showed low sensitivity. After fine-tuning with our data, the two networks achieved high performance on our test set as well as a hold-out test set from a different provider. Heatmaps generated using three saliency methods: GradCam and XRAI for ResNeSt model, and Attention Rollout for ViT model, demonstrate the effectiveness of our technique.

Original language	English
Title of host publication	44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3218-3221
Number of pages	4
ISBN (Electronic)	9781728127828
DOIs	https://doi.org/10.1109/EMBC48229.2022.9871610
State	Published - 2022
Externally published	Yes
Event	44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022 - Glasgow, United Kingdom Duration: 11 07 2022 → 15 07 2022

Publication series

Name	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Volume	2022-July
ISSN (Print)	1557-170X

Conference

Conference	44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
Country/Territory	United Kingdom
City	Glasgow
Period	11/07/22 → 15/07/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Access to Document

10.1109/EMBC48229.2022.9871610

Cite this

Xue, Z., Yu, K., Pearlman, P. C., Pal, A., Chen, T. C., Hua, C. H., Kang, C. J., Chien, C. Y., Tsai, M. H., Wang, C. P., Chaturvedi, A. K., & Antani, S. (2022). Automatic Detection of Oral Lesion Measurement Ruler Toward Computer-Aided Image-Based Oral Cancer Screening. In 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022 (pp. 3218-3221). (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2022-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC48229.2022.9871610

Xue, Zhiyun ; Yu, Kelly ; Pearlman, Paul C. et al. / Automatic Detection of Oral Lesion Measurement Ruler Toward Computer-Aided Image-Based Oral Cancer Screening. 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 3218-3221 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

@inproceedings{2649a6d1797b424d82e5628bea8414cc,

title = "Automatic Detection of Oral Lesion Measurement Ruler Toward Computer-Aided Image-Based Oral Cancer Screening",

abstract = "Intelligent computer-aided algorithms analyzing photographs of various mouth regions can help in reducing the high subjectivity in human assessment of oral lesions. Very often, in the images, a ruler is placed near a suspected lesion to indicate its location and as a physical size reference. In this paper, we compared two deep-learning networks: ResNeSt and ViT, to automatically identify ruler images. Even though the ImageN et 1K dataset contains a 'ruler' class label, the pre-trained models showed low sensitivity. After fine-tuning with our data, the two networks achieved high performance on our test set as well as a hold-out test set from a different provider. Heatmaps generated using three saliency methods: GradCam and XRAI for ResNeSt model, and Attention Rollout for ViT model, demonstrate the effectiveness of our technique.",

author = "Zhiyun Xue and Kelly Yu and Pearlman, {Paul C.} and Anabik Pal and Chen, {Tseng Cheng} and Hua, {Chun Hung} and Kang, {Chung Jan} and Chien, {Chih Yen} and Tsai, {Ming Hsui} and Wang, {Cheng Ping} and Chaturvedi, {Anil K.} and Sameer Antani",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022 ; Conference date: 11-07-2022 Through 15-07-2022",

year = "2022",

doi = "10.1109/EMBC48229.2022.9871610",

language = "英语",

series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

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

pages = "3218--3221",

booktitle = "44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022",

address = "美国",

}

Xue, Z, Yu, K, Pearlman, PC, Pal, A, Chen, TC, Hua, CH, Kang, CJ, Chien, CY, Tsai, MH, Wang, CP, Chaturvedi, AK & Antani, S 2022, Automatic Detection of Oral Lesion Measurement Ruler Toward Computer-Aided Image-Based Oral Cancer Screening. in 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, vol. 2022-July, Institute of Electrical and Electronics Engineers Inc., pp. 3218-3221, 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022, Glasgow, United Kingdom, 11/07/22. https://doi.org/10.1109/EMBC48229.2022.9871610

Automatic Detection of Oral Lesion Measurement Ruler Toward Computer-Aided Image-Based Oral Cancer Screening. / Xue, Zhiyun; Yu, Kelly; Pearlman, Paul C. et al.
44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 3218-3221 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2022-July).

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

TY - GEN

T1 - Automatic Detection of Oral Lesion Measurement Ruler Toward Computer-Aided Image-Based Oral Cancer Screening

AU - Xue, Zhiyun

AU - Yu, Kelly

AU - Pearlman, Paul C.

AU - Pal, Anabik

AU - Chen, Tseng Cheng

AU - Hua, Chun Hung

AU - Kang, Chung Jan

AU - Chien, Chih Yen

AU - Tsai, Ming Hsui

AU - Wang, Cheng Ping

AU - Chaturvedi, Anil K.

AU - Antani, Sameer

PY - 2022

Y1 - 2022

N2 - Intelligent computer-aided algorithms analyzing photographs of various mouth regions can help in reducing the high subjectivity in human assessment of oral lesions. Very often, in the images, a ruler is placed near a suspected lesion to indicate its location and as a physical size reference. In this paper, we compared two deep-learning networks: ResNeSt and ViT, to automatically identify ruler images. Even though the ImageN et 1K dataset contains a 'ruler' class label, the pre-trained models showed low sensitivity. After fine-tuning with our data, the two networks achieved high performance on our test set as well as a hold-out test set from a different provider. Heatmaps generated using three saliency methods: GradCam and XRAI for ResNeSt model, and Attention Rollout for ViT model, demonstrate the effectiveness of our technique.

AB - Intelligent computer-aided algorithms analyzing photographs of various mouth regions can help in reducing the high subjectivity in human assessment of oral lesions. Very often, in the images, a ruler is placed near a suspected lesion to indicate its location and as a physical size reference. In this paper, we compared two deep-learning networks: ResNeSt and ViT, to automatically identify ruler images. Even though the ImageN et 1K dataset contains a 'ruler' class label, the pre-trained models showed low sensitivity. After fine-tuning with our data, the two networks achieved high performance on our test set as well as a hold-out test set from a different provider. Heatmaps generated using three saliency methods: GradCam and XRAI for ResNeSt model, and Attention Rollout for ViT model, demonstrate the effectiveness of our technique.

UR - http://www.scopus.com/inward/record.url?scp=85138128083&partnerID=8YFLogxK

U2 - 10.1109/EMBC48229.2022.9871610

DO - 10.1109/EMBC48229.2022.9871610

M3 - 会议稿件

C2 - 36086542

AN - SCOPUS:85138128083

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 3218

EP - 3221

BT - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022

Y2 - 11 July 2022 through 15 July 2022

ER -

Xue Z, Yu K, Pearlman PC, Pal A, Chen TC, Hua CH et al. Automatic Detection of Oral Lesion Measurement Ruler Toward Computer-Aided Image-Based Oral Cancer Screening. In 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 3218-3221. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). doi: 10.1109/EMBC48229.2022.9871610

Automatic Detection of Oral Lesion Measurement Ruler Toward Computer-Aided Image-Based Oral Cancer Screening

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this