Feasibility of Prediction Model for Internal Tumor Target Volume from 4-D Computed Tomography of Lung cancer

Utumporn Puangragsa; Pitchayakorn Lomvisai; Pattarapong Phasukkit; Sarut Puangragsa; Jiraporn Setakornnukul; Nongluck Houngkamhang; Petchanon Thongserm; Pittaya Dankulchai

doi:10.1109/iSAI-NLP54397.2021.9678177

Feasibility of Prediction Model for Internal Tumor Target Volume from 4-D Computed Tomography of Lung cancer

Utumporn Puangragsa
, Pitchayakorn Lomvisai
, Pattarapong Phasukkit
, Sarut Puangragsa
, Jiraporn Setakornnukul
, Nongluck Houngkamhang
, Petchanon Thongserm
, Pittaya Dankulchai

Department of Radiology

Siriraj Hospital
King Mongkut's Institute of Technology Ladkrabang

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

Abstract

4-Dimensional computed tomography (4DCT) is the most common technique to determine organ movement due to breathing motion. However, the ability of 4DCT to acquire CT images as a function of the respiratory phase increases higher radiation dose. To reduce the patient's radiation dose, this study created lung motion prediction models used to estimate tumor target movement in ten respiratory phases by detecting only external organ movement during a complete respiration cycle without radiation with Kinect. The average overall amplitude difference between RPM and Kinect signals in the phantom experiment was 0.02 ± 0.1 mm. F1 score of 100% for all most all classifications except classification 2,3,6,7 and 8 of 85%,83%,90%, 84%,85% where irregular breathing pattern. Essentially, the proposed tumor movement scheme's total accuracy (average of F1 scores) is 92.7 %.

Original language	English
Title of host publication	16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665409476
DOIs	https://doi.org/10.1109/iSAI-NLP54397.2021.9678177
Publication status	Published - 2021
Event	16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021 - Virtual, Online, Thailand Duration: 21 Dec 2021 → 23 Dec 2021

Publication series

Name	16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021

Conference

Conference	16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021
Country/Territory	Thailand
City	Virtual, Online
Period	21/12/21 → 23/12/21

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

4-dimension computed tomography (4D-CT)
Prediction internal organ
deep learning

Access to Document

10.1109/iSAI-NLP54397.2021.9678177

Cite this

Puangragsa, U., Lomvisai, P., Phasukkit, P., Puangragsa, S., Setakornnukul, J., Houngkamhang, N., Thongserm, P., & Dankulchai, P. (2021). Feasibility of Prediction Model for Internal Tumor Target Volume from 4-D Computed Tomography of Lung cancer. In 16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021 (16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/iSAI-NLP54397.2021.9678177

Puangragsa, Utumporn ; Lomvisai, Pitchayakorn ; Phasukkit, Pattarapong et al. / Feasibility of Prediction Model for Internal Tumor Target Volume from 4-D Computed Tomography of Lung cancer. 16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021).

@inproceedings{722e5aca63754cdea0d6a08b4407c839,

title = "Feasibility of Prediction Model for Internal Tumor Target Volume from 4-D Computed Tomography of Lung cancer",

abstract = "4-Dimensional computed tomography (4DCT) is the most common technique to determine organ movement due to breathing motion. However, the ability of 4DCT to acquire CT images as a function of the respiratory phase increases higher radiation dose. To reduce the patient's radiation dose, this study created lung motion prediction models used to estimate tumor target movement in ten respiratory phases by detecting only external organ movement during a complete respiration cycle without radiation with Kinect. The average overall amplitude difference between RPM and Kinect signals in the phantom experiment was 0.02 ± 0.1 mm. F1 score of 100\% for all most all classifications except classification 2,3,6,7 and 8 of 85\%,83\%,90\%, 84\%,85\% where irregular breathing pattern. Essentially, the proposed tumor movement scheme's total accuracy (average of F1 scores) is 92.7 \%.",

keywords = "4-dimension computed tomography (4D-CT), Prediction internal organ, deep learning",

author = "Utumporn Puangragsa and Pitchayakorn Lomvisai and Pattarapong Phasukkit and Sarut Puangragsa and Jiraporn Setakornnukul and Nongluck Houngkamhang and Petchanon Thongserm and Pittaya Dankulchai",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021 ; Conference date: 21-12-2021 Through 23-12-2021",

year = "2021",

doi = "10.1109/iSAI-NLP54397.2021.9678177",

language = "English",

series = "16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021",

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

booktitle = "16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021",

}

Puangragsa, U, Lomvisai, P, Phasukkit, P, Puangragsa, S, Setakornnukul, J, Houngkamhang, N, Thongserm, P & Dankulchai, P 2021, Feasibility of Prediction Model for Internal Tumor Target Volume from 4-D Computed Tomography of Lung cancer. in 16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021. 16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021, Institute of Electrical and Electronics Engineers Inc., 16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021, Virtual, Online, Thailand, 21/12/21. https://doi.org/10.1109/iSAI-NLP54397.2021.9678177

Feasibility of Prediction Model for Internal Tumor Target Volume from 4-D Computed Tomography of Lung cancer. / Puangragsa, Utumporn; Lomvisai, Pitchayakorn; Phasukkit, Pattarapong et al.
16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021).

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

TY - GEN

T1 - Feasibility of Prediction Model for Internal Tumor Target Volume from 4-D Computed Tomography of Lung cancer

AU - Puangragsa, Utumporn

AU - Lomvisai, Pitchayakorn

AU - Phasukkit, Pattarapong

AU - Puangragsa, Sarut

AU - Setakornnukul, Jiraporn

AU - Houngkamhang, Nongluck

AU - Thongserm, Petchanon

AU - Dankulchai, Pittaya

PY - 2021

Y1 - 2021

N2 - 4-Dimensional computed tomography (4DCT) is the most common technique to determine organ movement due to breathing motion. However, the ability of 4DCT to acquire CT images as a function of the respiratory phase increases higher radiation dose. To reduce the patient's radiation dose, this study created lung motion prediction models used to estimate tumor target movement in ten respiratory phases by detecting only external organ movement during a complete respiration cycle without radiation with Kinect. The average overall amplitude difference between RPM and Kinect signals in the phantom experiment was 0.02 ± 0.1 mm. F1 score of 100% for all most all classifications except classification 2,3,6,7 and 8 of 85%,83%,90%, 84%,85% where irregular breathing pattern. Essentially, the proposed tumor movement scheme's total accuracy (average of F1 scores) is 92.7 %.

AB - 4-Dimensional computed tomography (4DCT) is the most common technique to determine organ movement due to breathing motion. However, the ability of 4DCT to acquire CT images as a function of the respiratory phase increases higher radiation dose. To reduce the patient's radiation dose, this study created lung motion prediction models used to estimate tumor target movement in ten respiratory phases by detecting only external organ movement during a complete respiration cycle without radiation with Kinect. The average overall amplitude difference between RPM and Kinect signals in the phantom experiment was 0.02 ± 0.1 mm. F1 score of 100% for all most all classifications except classification 2,3,6,7 and 8 of 85%,83%,90%, 84%,85% where irregular breathing pattern. Essentially, the proposed tumor movement scheme's total accuracy (average of F1 scores) is 92.7 %.

KW - 4-dimension computed tomography (4D-CT)

KW - Prediction internal organ

KW - deep learning

UR - https://www.scopus.com/pages/publications/85125344420

U2 - 10.1109/iSAI-NLP54397.2021.9678177

DO - 10.1109/iSAI-NLP54397.2021.9678177

M3 - Conference contribution

AN - SCOPUS:85125344420

T3 - 16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021

BT - 16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021

Y2 - 21 December 2021 through 23 December 2021

ER -

Puangragsa U, Lomvisai P, Phasukkit P, Puangragsa S, Setakornnukul J, Houngkamhang N et al. Feasibility of Prediction Model for Internal Tumor Target Volume from 4-D Computed Tomography of Lung cancer. In 16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021. Institute of Electrical and Electronics Engineers Inc. 2021. (16th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2021). doi: 10.1109/iSAI-NLP54397.2021.9678177

Feasibility of Prediction Model for Internal Tumor Target Volume from 4-D Computed Tomography of Lung cancer

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this