Differentiation of thyroid nodules on US using features learned and extracted from various convolutional neural networks

Eunjung Lee; Heonkyu Ha; Hye Jung Kim; Hee Jung Moon; Jung Hee Byon; Sun Huh; Jinwoo Son; Jiyoung Yoon; Kyunghwa Han; Jin Young Kwak

doi:10.1038/s41598-019-56395-x

Differentiation of thyroid nodules on US using features learned and extracted from various convolutional neural networks

Eunjung Lee, Heonkyu Ha, Hye Jung Kim, Hee Jung Moon, Jung Hee Byon, Sun Huh, Jinwoo Son, Jiyoung Yoon, Kyunghwa Han, Jin Young Kwak

Research output: Contribution to journal › Article › peer-review

10 Citations (Scopus)

Abstract

Thyroid nodules are a common clinical problem. Ultrasonography (US) is the main tool used to sensitively diagnose thyroid cancer. Although US is non-invasive and can accurately differentiate benign and malignant thyroid nodules, it is subjective and its results inevitably lack reproducibility. Therefore, to provide objective and reliable information for US assessment, we developed a CADx system that utilizes convolutional neural networks and the machine learning technique. The diagnostic performances of 6 radiologists and 3 representative results obtained from the proposed CADx system were compared and analyzed.

Original language	English
Article number	19854
Journal	Scientific reports
Volume	9
Issue number	1
DOIs	https://doi.org/10.1038/s41598-019-56395-x
Publication status	Published - 2019 Dec 1

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea grant NRF-2015R1A5A1009350. This study was also supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) by the Ministry of Education (2016R1D1A1B03930375). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Publisher Copyright:
© 2019, The Author(s).

All Science Journal Classification (ASJC) codes

General

UN SDGs

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

Access to Document

10.1038/s41598-019-56395-x

Cite this

@article{e4953229e956473ab6d5cad3daa1d11f,

title = "Differentiation of thyroid nodules on US using features learned and extracted from various convolutional neural networks",

abstract = "Thyroid nodules are a common clinical problem. Ultrasonography (US) is the main tool used to sensitively diagnose thyroid cancer. Although US is non-invasive and can accurately differentiate benign and malignant thyroid nodules, it is subjective and its results inevitably lack reproducibility. Therefore, to provide objective and reliable information for US assessment, we developed a CADx system that utilizes convolutional neural networks and the machine learning technique. The diagnostic performances of 6 radiologists and 3 representative results obtained from the proposed CADx system were compared and analyzed.",

author = "Eunjung Lee and Heonkyu Ha and Kim, {Hye Jung} and Moon, {Hee Jung} and Byon, {Jung Hee} and Sun Huh and Jinwoo Son and Jiyoung Yoon and Kyunghwa Han and Kwak, {Jin Young}",

note = "Funding Information: This work was supported by the National Research Foundation of Korea grant NRF-2015R1A5A1009350. This study was also supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) by the Ministry of Education (2016R1D1A1B03930375). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Publisher Copyright: {\textcopyright} 2019, The Author(s).",

year = "2019",

month = dec,

day = "1",

doi = "10.1038/s41598-019-56395-x",

language = "English",

volume = "9",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "Nature Publishing Group",

number = "1",

}

TY - JOUR

T1 - Differentiation of thyroid nodules on US using features learned and extracted from various convolutional neural networks

AU - Lee, Eunjung

AU - Ha, Heonkyu

AU - Kim, Hye Jung

AU - Moon, Hee Jung

AU - Byon, Jung Hee

AU - Huh, Sun

AU - Son, Jinwoo

AU - Yoon, Jiyoung

AU - Han, Kyunghwa

AU - Kwak, Jin Young

N1 - Funding Information: This work was supported by the National Research Foundation of Korea grant NRF-2015R1A5A1009350. This study was also supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) by the Ministry of Education (2016R1D1A1B03930375). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Publisher Copyright: © 2019, The Author(s).

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Thyroid nodules are a common clinical problem. Ultrasonography (US) is the main tool used to sensitively diagnose thyroid cancer. Although US is non-invasive and can accurately differentiate benign and malignant thyroid nodules, it is subjective and its results inevitably lack reproducibility. Therefore, to provide objective and reliable information for US assessment, we developed a CADx system that utilizes convolutional neural networks and the machine learning technique. The diagnostic performances of 6 radiologists and 3 representative results obtained from the proposed CADx system were compared and analyzed.

AB - Thyroid nodules are a common clinical problem. Ultrasonography (US) is the main tool used to sensitively diagnose thyroid cancer. Although US is non-invasive and can accurately differentiate benign and malignant thyroid nodules, it is subjective and its results inevitably lack reproducibility. Therefore, to provide objective and reliable information for US assessment, we developed a CADx system that utilizes convolutional neural networks and the machine learning technique. The diagnostic performances of 6 radiologists and 3 representative results obtained from the proposed CADx system were compared and analyzed.

UR - http://www.scopus.com/inward/record.url?scp=85077315400&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077315400&partnerID=8YFLogxK

U2 - 10.1038/s41598-019-56395-x

DO - 10.1038/s41598-019-56395-x

M3 - Article

C2 - 31882683

AN - SCOPUS:85077315400

SN - 2045-2322

VL - 9

JO - Scientific Reports

JF - Scientific Reports

IS - 1

M1 - 19854

ER -

Differentiation of thyroid nodules on US using features learned and extracted from various convolutional neural networks

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this