Radiomics-based malignancy prediction of parotid gland tumor

H. Kamezawa, Hidetaka Arimura, Ryuji Yasumatsu, K. Ninomiya, S. Haseai

研究成果: 著書/レポートタイプへの貢献会議での発言

抄録

We have investigated an approach for prediction of parotid gland tumor (PGT) malignancy on preoperative magnetic resonance (MR) images. The PGT regions were segmented on the MR images of 42 patients. A total of 972 radiomic features were extracted from tumor regions in T1- and T2-weighted MR images. Five features were selected as a radiomic biomarker from the 972 features by using a least absolute shrinkage and selection operator (LASSO). Malignancies of PGTs (high grade versus intermediate and low grades) were predicted by using random forest (RF) and k-nearest neighbors (k-NN) with the radiomic biomarker. The proposed approach was evaluated using the accuracy and the mean area under the receiver operating characteristic curve (AUC) based on a leave-one-out cross validation test. The accuracy and AUC of the malignancy prediction of PGTs were 73.8% and 0.88 for the RF and 88.1% and 0.95 for the k-NN, respectively. Our results suggested that the radiomics-based k-NN approach using preoperative MR images could be feasible to predict the malignancy of PGT.

元の言語英語
ホスト出版物のタイトルInternational Forum on Medical Imaging in Asia 2019
編集者Hiroshi Fujita, Jong Hyo Kim, Feng Lin
出版者SPIE
ISBN(電子版)9781510627758
DOI
出版物ステータス出版済み - 1 1 2019
イベントInternational Forum on Medical Imaging in Asia 2019 - Singapore, シンガポール
継続期間: 1 7 20191 9 2019

出版物シリーズ

名前Proceedings of SPIE - The International Society for Optical Engineering
11050
ISSN(印刷物)0277-786X
ISSN(電子版)1996-756X

会議

会議International Forum on Medical Imaging in Asia 2019
シンガポール
Singapore
期間1/7/191/9/19

Fingerprint

salivary glands
Magnetic Resonance Image
Magnetic resonance
magnetic resonance
Tumors
Tumor
tumors
Nearest Neighbor
Random Forest
biomarkers
Prediction
Biomarkers
predictions
grade
Receiver Operating Characteristic Curve
Shrinkage
shrinkage
Cross-validation
receivers
operators

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

これを引用

Kamezawa, H., Arimura, H., Yasumatsu, R., Ninomiya, K., & Haseai, S. (2019). Radiomics-based malignancy prediction of parotid gland tumor. : H. Fujita, J. H. Kim, & F. Lin (版), International Forum on Medical Imaging in Asia 2019 [1105019] (Proceedings of SPIE - The International Society for Optical Engineering; 巻数 11050). SPIE. https://doi.org/10.1117/12.2521362

Radiomics-based malignancy prediction of parotid gland tumor. / Kamezawa, H.; Arimura, Hidetaka; Yasumatsu, Ryuji; Ninomiya, K.; Haseai, S.

International Forum on Medical Imaging in Asia 2019. 版 / Hiroshi Fujita; Jong Hyo Kim; Feng Lin. SPIE, 2019. 1105019 (Proceedings of SPIE - The International Society for Optical Engineering; 巻 11050).

研究成果: 著書/レポートタイプへの貢献会議での発言

Kamezawa, H, Arimura, H, Yasumatsu, R, Ninomiya, K & Haseai, S 2019, Radiomics-based malignancy prediction of parotid gland tumor. : H Fujita, JH Kim & F Lin (版), International Forum on Medical Imaging in Asia 2019., 1105019, Proceedings of SPIE - The International Society for Optical Engineering, 巻. 11050, SPIE, International Forum on Medical Imaging in Asia 2019, Singapore, シンガポール, 1/7/19. https://doi.org/10.1117/12.2521362
Kamezawa H, Arimura H, Yasumatsu R, Ninomiya K, Haseai S. Radiomics-based malignancy prediction of parotid gland tumor. : Fujita H, Kim JH, Lin F, 編集者, International Forum on Medical Imaging in Asia 2019. SPIE. 2019. 1105019. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2521362
Kamezawa, H. ; Arimura, Hidetaka ; Yasumatsu, Ryuji ; Ninomiya, K. ; Haseai, S. / Radiomics-based malignancy prediction of parotid gland tumor. International Forum on Medical Imaging in Asia 2019. 編集者 / Hiroshi Fujita ; Jong Hyo Kim ; Feng Lin. SPIE, 2019. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{7a7abcf568dd49bbae397fb78893a9d7,
title = "Radiomics-based malignancy prediction of parotid gland tumor",
abstract = "We have investigated an approach for prediction of parotid gland tumor (PGT) malignancy on preoperative magnetic resonance (MR) images. The PGT regions were segmented on the MR images of 42 patients. A total of 972 radiomic features were extracted from tumor regions in T1- and T2-weighted MR images. Five features were selected as a radiomic biomarker from the 972 features by using a least absolute shrinkage and selection operator (LASSO). Malignancies of PGTs (high grade versus intermediate and low grades) were predicted by using random forest (RF) and k-nearest neighbors (k-NN) with the radiomic biomarker. The proposed approach was evaluated using the accuracy and the mean area under the receiver operating characteristic curve (AUC) based on a leave-one-out cross validation test. The accuracy and AUC of the malignancy prediction of PGTs were 73.8{\%} and 0.88 for the RF and 88.1{\%} and 0.95 for the k-NN, respectively. Our results suggested that the radiomics-based k-NN approach using preoperative MR images could be feasible to predict the malignancy of PGT.",
author = "H. Kamezawa and Hidetaka Arimura and Ryuji Yasumatsu and K. Ninomiya and S. Haseai",
year = "2019",
month = "1",
day = "1",
doi = "10.1117/12.2521362",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Hiroshi Fujita and Kim, {Jong Hyo} and Feng Lin",
booktitle = "International Forum on Medical Imaging in Asia 2019",
address = "United States",

}

TY - GEN

T1 - Radiomics-based malignancy prediction of parotid gland tumor

AU - Kamezawa, H.

AU - Arimura, Hidetaka

AU - Yasumatsu, Ryuji

AU - Ninomiya, K.

AU - Haseai, S.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We have investigated an approach for prediction of parotid gland tumor (PGT) malignancy on preoperative magnetic resonance (MR) images. The PGT regions were segmented on the MR images of 42 patients. A total of 972 radiomic features were extracted from tumor regions in T1- and T2-weighted MR images. Five features were selected as a radiomic biomarker from the 972 features by using a least absolute shrinkage and selection operator (LASSO). Malignancies of PGTs (high grade versus intermediate and low grades) were predicted by using random forest (RF) and k-nearest neighbors (k-NN) with the radiomic biomarker. The proposed approach was evaluated using the accuracy and the mean area under the receiver operating characteristic curve (AUC) based on a leave-one-out cross validation test. The accuracy and AUC of the malignancy prediction of PGTs were 73.8% and 0.88 for the RF and 88.1% and 0.95 for the k-NN, respectively. Our results suggested that the radiomics-based k-NN approach using preoperative MR images could be feasible to predict the malignancy of PGT.

AB - We have investigated an approach for prediction of parotid gland tumor (PGT) malignancy on preoperative magnetic resonance (MR) images. The PGT regions were segmented on the MR images of 42 patients. A total of 972 radiomic features were extracted from tumor regions in T1- and T2-weighted MR images. Five features were selected as a radiomic biomarker from the 972 features by using a least absolute shrinkage and selection operator (LASSO). Malignancies of PGTs (high grade versus intermediate and low grades) were predicted by using random forest (RF) and k-nearest neighbors (k-NN) with the radiomic biomarker. The proposed approach was evaluated using the accuracy and the mean area under the receiver operating characteristic curve (AUC) based on a leave-one-out cross validation test. The accuracy and AUC of the malignancy prediction of PGTs were 73.8% and 0.88 for the RF and 88.1% and 0.95 for the k-NN, respectively. Our results suggested that the radiomics-based k-NN approach using preoperative MR images could be feasible to predict the malignancy of PGT.

UR - http://www.scopus.com/inward/record.url?scp=85063862623&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063862623&partnerID=8YFLogxK

U2 - 10.1117/12.2521362

DO - 10.1117/12.2521362

M3 - Conference contribution

AN - SCOPUS:85063862623

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - International Forum on Medical Imaging in Asia 2019

A2 - Fujita, Hiroshi

A2 - Kim, Jong Hyo

A2 - Lin, Feng

PB - SPIE

ER -