Evaluation of classification strategies using quantitative ultrasound markers and a thyroid cancer rodent model

Maria Luisa Montero, Omar Zenteno, Benjamin Castaneda, Michael Oelze, Roberto Lavarello

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The incidence rate of diagnosed thyroid cancer has increased over the last decades. Although ultrasonic imaging has increased the malignancy detection rate, current ultrasonography markers do not provide a sufficient level of diagnostic accuracy to replace the fine needle aspiration biopsy. Recently, studies have reported that significant differences were observed in the values of quantitative ultrasound (QUS) parameters derived from a thyroid cancer rodent model between normal/benign and malignant tissues. In the present study, the performance of a multi-parametric classification for the differentiation of thyroid cancer in this rodent model has been evaluated. The experimental database consisted of 32 mice having different predispositions to developing thyroid abnormalities; 6 of them developed thyroid cancer papillary carcinoma (PTC), 5 follicular variant papillary thyroid carcinoma (FV-PTC), 6 developed benign tumors (c-cell adenoma) and 15 did not develop any thyroid abnormalities. Backscattered data was obtained from excised thyroid tissues using a 40 MHz, f/3 single element transducer. A total of five QUS parameters were derived from the ultrasound data: two from backscatter coefficients (i.e., the effective scatterer diameter (ESD) and effective acoustic concentration (EAC)), two from envelope statistics (i.e., the μ and k parameters), and one from ultrasound attenuation (i.e., attenuation coefficient slope). A two-class classification between normal/benign and malignant cases was performed using linear discriminant analysis with both one- and two-dimensional feature spaces. When using a two-dimensional feature space, it was found that the combination of EAC and 10/μ resulted in both a sensitivity and specificity of 100%.

Original languageEnglish (US)
Title of host publicationIEEE International Ultrasonics Symposium, IUS
PublisherIEEE Computer Society
Pages1916-1919
Number of pages4
ISBN (Electronic)9781479970490
DOIs
StatePublished - Oct 20 2014
Event2014 IEEE International Ultrasonics Symposium, IUS 2014 - Chicago, United States
Duration: Sep 3 2014Sep 6 2014

Other

Other2014 IEEE International Ultrasonics Symposium, IUS 2014
CountryUnited States
CityChicago
Period9/3/149/6/14

Fingerprint

Thyroid Neoplasms
Rodentia
Thyroid Gland
Acoustics
Ultrasonography
Factor IX
Discriminant Analysis
Fine Needle Biopsy
Transducers
Adenoma
Neoplasms
Databases
Sensitivity and Specificity
Incidence
Papillary Thyroid cancer

Keywords

  • linear discriminant analysis
  • Quantitative ultrasound
  • thyroid cancer
  • tissue characterization

Cite this

Montero, M. L., Zenteno, O., Castaneda, B., Oelze, M., & Lavarello, R. (2014). Evaluation of classification strategies using quantitative ultrasound markers and a thyroid cancer rodent model. In IEEE International Ultrasonics Symposium, IUS (pp. 1916-1919). [6931744] IEEE Computer Society. https://doi.org/10.1109/ULTSYM.2014.0476

Evaluation of classification strategies using quantitative ultrasound markers and a thyroid cancer rodent model. / Montero, Maria Luisa; Zenteno, Omar; Castaneda, Benjamin; Oelze, Michael; Lavarello, Roberto.

IEEE International Ultrasonics Symposium, IUS. IEEE Computer Society, 2014. p. 1916-1919 6931744.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Montero, ML, Zenteno, O, Castaneda, B, Oelze, M & Lavarello, R 2014, Evaluation of classification strategies using quantitative ultrasound markers and a thyroid cancer rodent model. in IEEE International Ultrasonics Symposium, IUS., 6931744, IEEE Computer Society, pp. 1916-1919, 2014 IEEE International Ultrasonics Symposium, IUS 2014, Chicago, United States, 9/3/14. https://doi.org/10.1109/ULTSYM.2014.0476
Montero ML, Zenteno O, Castaneda B, Oelze M, Lavarello R. Evaluation of classification strategies using quantitative ultrasound markers and a thyroid cancer rodent model. In IEEE International Ultrasonics Symposium, IUS. IEEE Computer Society. 2014. p. 1916-1919. 6931744 https://doi.org/10.1109/ULTSYM.2014.0476
Montero, Maria Luisa ; Zenteno, Omar ; Castaneda, Benjamin ; Oelze, Michael ; Lavarello, Roberto. / Evaluation of classification strategies using quantitative ultrasound markers and a thyroid cancer rodent model. IEEE International Ultrasonics Symposium, IUS. IEEE Computer Society, 2014. pp. 1916-1919
@inproceedings{c6f6395435304c8481ac8bad08309061,
title = "Evaluation of classification strategies using quantitative ultrasound markers and a thyroid cancer rodent model",
abstract = "The incidence rate of diagnosed thyroid cancer has increased over the last decades. Although ultrasonic imaging has increased the malignancy detection rate, current ultrasonography markers do not provide a sufficient level of diagnostic accuracy to replace the fine needle aspiration biopsy. Recently, studies have reported that significant differences were observed in the values of quantitative ultrasound (QUS) parameters derived from a thyroid cancer rodent model between normal/benign and malignant tissues. In the present study, the performance of a multi-parametric classification for the differentiation of thyroid cancer in this rodent model has been evaluated. The experimental database consisted of 32 mice having different predispositions to developing thyroid abnormalities; 6 of them developed thyroid cancer papillary carcinoma (PTC), 5 follicular variant papillary thyroid carcinoma (FV-PTC), 6 developed benign tumors (c-cell adenoma) and 15 did not develop any thyroid abnormalities. Backscattered data was obtained from excised thyroid tissues using a 40 MHz, f/3 single element transducer. A total of five QUS parameters were derived from the ultrasound data: two from backscatter coefficients (i.e., the effective scatterer diameter (ESD) and effective acoustic concentration (EAC)), two from envelope statistics (i.e., the μ and k parameters), and one from ultrasound attenuation (i.e., attenuation coefficient slope). A two-class classification between normal/benign and malignant cases was performed using linear discriminant analysis with both one- and two-dimensional feature spaces. When using a two-dimensional feature space, it was found that the combination of EAC and 10/μ resulted in both a sensitivity and specificity of 100{\%}.",
keywords = "linear discriminant analysis, Quantitative ultrasound, thyroid cancer, tissue characterization",
author = "Montero, {Maria Luisa} and Omar Zenteno and Benjamin Castaneda and Michael Oelze and Roberto Lavarello",
year = "2014",
month = "10",
day = "20",
doi = "10.1109/ULTSYM.2014.0476",
language = "English (US)",
pages = "1916--1919",
booktitle = "IEEE International Ultrasonics Symposium, IUS",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Evaluation of classification strategies using quantitative ultrasound markers and a thyroid cancer rodent model

AU - Montero, Maria Luisa

AU - Zenteno, Omar

AU - Castaneda, Benjamin

AU - Oelze, Michael

AU - Lavarello, Roberto

PY - 2014/10/20

Y1 - 2014/10/20

N2 - The incidence rate of diagnosed thyroid cancer has increased over the last decades. Although ultrasonic imaging has increased the malignancy detection rate, current ultrasonography markers do not provide a sufficient level of diagnostic accuracy to replace the fine needle aspiration biopsy. Recently, studies have reported that significant differences were observed in the values of quantitative ultrasound (QUS) parameters derived from a thyroid cancer rodent model between normal/benign and malignant tissues. In the present study, the performance of a multi-parametric classification for the differentiation of thyroid cancer in this rodent model has been evaluated. The experimental database consisted of 32 mice having different predispositions to developing thyroid abnormalities; 6 of them developed thyroid cancer papillary carcinoma (PTC), 5 follicular variant papillary thyroid carcinoma (FV-PTC), 6 developed benign tumors (c-cell adenoma) and 15 did not develop any thyroid abnormalities. Backscattered data was obtained from excised thyroid tissues using a 40 MHz, f/3 single element transducer. A total of five QUS parameters were derived from the ultrasound data: two from backscatter coefficients (i.e., the effective scatterer diameter (ESD) and effective acoustic concentration (EAC)), two from envelope statistics (i.e., the μ and k parameters), and one from ultrasound attenuation (i.e., attenuation coefficient slope). A two-class classification between normal/benign and malignant cases was performed using linear discriminant analysis with both one- and two-dimensional feature spaces. When using a two-dimensional feature space, it was found that the combination of EAC and 10/μ resulted in both a sensitivity and specificity of 100%.

AB - The incidence rate of diagnosed thyroid cancer has increased over the last decades. Although ultrasonic imaging has increased the malignancy detection rate, current ultrasonography markers do not provide a sufficient level of diagnostic accuracy to replace the fine needle aspiration biopsy. Recently, studies have reported that significant differences were observed in the values of quantitative ultrasound (QUS) parameters derived from a thyroid cancer rodent model between normal/benign and malignant tissues. In the present study, the performance of a multi-parametric classification for the differentiation of thyroid cancer in this rodent model has been evaluated. The experimental database consisted of 32 mice having different predispositions to developing thyroid abnormalities; 6 of them developed thyroid cancer papillary carcinoma (PTC), 5 follicular variant papillary thyroid carcinoma (FV-PTC), 6 developed benign tumors (c-cell adenoma) and 15 did not develop any thyroid abnormalities. Backscattered data was obtained from excised thyroid tissues using a 40 MHz, f/3 single element transducer. A total of five QUS parameters were derived from the ultrasound data: two from backscatter coefficients (i.e., the effective scatterer diameter (ESD) and effective acoustic concentration (EAC)), two from envelope statistics (i.e., the μ and k parameters), and one from ultrasound attenuation (i.e., attenuation coefficient slope). A two-class classification between normal/benign and malignant cases was performed using linear discriminant analysis with both one- and two-dimensional feature spaces. When using a two-dimensional feature space, it was found that the combination of EAC and 10/μ resulted in both a sensitivity and specificity of 100%.

KW - linear discriminant analysis

KW - Quantitative ultrasound

KW - thyroid cancer

KW - tissue characterization

UR - http://www.scopus.com/inward/record.url?scp=84910049109&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84910049109&partnerID=8YFLogxK

U2 - 10.1109/ULTSYM.2014.0476

DO - 10.1109/ULTSYM.2014.0476

M3 - Conference contribution

SP - 1916

EP - 1919

BT - IEEE International Ultrasonics Symposium, IUS

PB - IEEE Computer Society

ER -