Mandibular segmentation on panoramic radiographs with CNN Transfer Learning

Nur Nafiiyah; Chastine Fatichah; Darlis Herumurti; Eha Renwi Astuti; Ramadhan Hardani Putra; Esa Prakasa

doi:10.1109/COMNETSAT56033.2022.9994407

Mandibular segmentation on panoramic radiographs with CNN Transfer Learning

Nur Nafiiyah, Chastine Fatichah, Darlis Herumurti, Eha Renwi Astuti, Ramadhan Hardani Putra, Esa Prakasa

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

1 Citation (Scopus)

Abstract

Gender identification and age estimation can use the mandible bone on panoramic radiographs. The identification process using the system requires a segmentation stage. Mandibular segmentation is research that has been done a lot to get an accurate object result. The purpose of this study was to segment the mandible on a panoramic radiograph using transfer learning CNN (MobileNetV2, ResNet18, ResNet50). The CNN method has been done before, so we tried to use the CNN method to produce clear and complete mandibular segmentation results on panoramic radiographs. The dataset used to train the model was taken from the Dental Hospital, Airlangga University, Surabaya. There are thousands of datasets, and based on the criteria of a radiologist, the data used are 38 images. The best result of mandibular segmentation on panoramic radiographs is the MobileNetV2 method because the highest Jaccard mean value is 0.9522.

Original language	English
Title of host publication	Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	190-194
Number of pages	5
ISBN (Electronic)	9781665460309
DOIs	https://doi.org/10.1109/COMNETSAT56033.2022.9994407
Publication status	Published - 2022
Event	11th IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022 - Solo, Indonesia Duration: 3 Nov 2022 → 5 Nov 2022

Publication series

Name	Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022

Conference

Conference	11th IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022
Country/Territory	Indonesia
City	Solo
Period	3/11/22 → 5/11/22

Keywords

MobileNetV2
ResNet18
ResNet50
mandibular segmentation
panoramic radiograph

Access to Document

10.1109/COMNETSAT56033.2022.9994407

Cite this

Nafiiyah, N., Fatichah, C., Herumurti, D., Astuti, E. R., Putra, R. H., & Prakasa, E. (2022). Mandibular segmentation on panoramic radiographs with CNN Transfer Learning. In Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022 (pp. 190-194). (Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/COMNETSAT56033.2022.9994407

Nafiiyah, Nur ; Fatichah, Chastine ; Herumurti, Darlis et al. / Mandibular segmentation on panoramic radiographs with CNN Transfer Learning. Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 190-194 (Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022).

@inproceedings{69b1aec981c643688b1a2d687b7140b0,

title = "Mandibular segmentation on panoramic radiographs with CNN Transfer Learning",

abstract = "Gender identification and age estimation can use the mandible bone on panoramic radiographs. The identification process using the system requires a segmentation stage. Mandibular segmentation is research that has been done a lot to get an accurate object result. The purpose of this study was to segment the mandible on a panoramic radiograph using transfer learning CNN (MobileNetV2, ResNet18, ResNet50). The CNN method has been done before, so we tried to use the CNN method to produce clear and complete mandibular segmentation results on panoramic radiographs. The dataset used to train the model was taken from the Dental Hospital, Airlangga University, Surabaya. There are thousands of datasets, and based on the criteria of a radiologist, the data used are 38 images. The best result of mandibular segmentation on panoramic radiographs is the MobileNetV2 method because the highest Jaccard mean value is 0.9522.",

keywords = "MobileNetV2, ResNet18, ResNet50, mandibular segmentation, panoramic radiograph",

author = "Nur Nafiiyah and Chastine Fatichah and Darlis Herumurti and Astuti, {Eha Renwi} and Putra, {Ramadhan Hardani} and Esa Prakasa",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 11th IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022 ; Conference date: 03-11-2022 Through 05-11-2022",

year = "2022",

doi = "10.1109/COMNETSAT56033.2022.9994407",

language = "English",

series = "Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022",

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

pages = "190--194",

booktitle = "Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022",

address = "United States",

}

Nafiiyah, N, Fatichah, C , Herumurti, D, Astuti, ER, Putra, RH & Prakasa, E 2022, Mandibular segmentation on panoramic radiographs with CNN Transfer Learning. in Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022. Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022, Institute of Electrical and Electronics Engineers Inc., pp. 190-194, 11th IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022, Solo, Indonesia, 3/11/22. https://doi.org/10.1109/COMNETSAT56033.2022.9994407

Mandibular segmentation on panoramic radiographs with CNN Transfer Learning. / Nafiiyah, Nur; Fatichah, Chastine ; Herumurti, Darlis et al.
Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 190-194 (Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022).

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

TY - GEN

T1 - Mandibular segmentation on panoramic radiographs with CNN Transfer Learning

AU - Nafiiyah, Nur

AU - Fatichah, Chastine

AU - Herumurti, Darlis

AU - Astuti, Eha Renwi

AU - Putra, Ramadhan Hardani

AU - Prakasa, Esa

PY - 2022

Y1 - 2022

N2 - Gender identification and age estimation can use the mandible bone on panoramic radiographs. The identification process using the system requires a segmentation stage. Mandibular segmentation is research that has been done a lot to get an accurate object result. The purpose of this study was to segment the mandible on a panoramic radiograph using transfer learning CNN (MobileNetV2, ResNet18, ResNet50). The CNN method has been done before, so we tried to use the CNN method to produce clear and complete mandibular segmentation results on panoramic radiographs. The dataset used to train the model was taken from the Dental Hospital, Airlangga University, Surabaya. There are thousands of datasets, and based on the criteria of a radiologist, the data used are 38 images. The best result of mandibular segmentation on panoramic radiographs is the MobileNetV2 method because the highest Jaccard mean value is 0.9522.

AB - Gender identification and age estimation can use the mandible bone on panoramic radiographs. The identification process using the system requires a segmentation stage. Mandibular segmentation is research that has been done a lot to get an accurate object result. The purpose of this study was to segment the mandible on a panoramic radiograph using transfer learning CNN (MobileNetV2, ResNet18, ResNet50). The CNN method has been done before, so we tried to use the CNN method to produce clear and complete mandibular segmentation results on panoramic radiographs. The dataset used to train the model was taken from the Dental Hospital, Airlangga University, Surabaya. There are thousands of datasets, and based on the criteria of a radiologist, the data used are 38 images. The best result of mandibular segmentation on panoramic radiographs is the MobileNetV2 method because the highest Jaccard mean value is 0.9522.

KW - MobileNetV2

KW - ResNet18

KW - ResNet50

KW - mandibular segmentation

KW - panoramic radiograph

UR - http://www.scopus.com/inward/record.url?scp=85146726495&partnerID=8YFLogxK

U2 - 10.1109/COMNETSAT56033.2022.9994407

DO - 10.1109/COMNETSAT56033.2022.9994407

M3 - Conference contribution

AN - SCOPUS:85146726495

T3 - Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022

SP - 190

EP - 194

BT - Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022

Y2 - 3 November 2022 through 5 November 2022

ER -

Nafiiyah N, Fatichah C , Herumurti D, Astuti ER, Putra RH, Prakasa E. Mandibular segmentation on panoramic radiographs with CNN Transfer Learning. In Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 190-194. (Proceeding - IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022). doi: 10.1109/COMNETSAT56033.2022.9994407

Mandibular segmentation on panoramic radiographs with CNN Transfer Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this