skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Computer-aided diagnosis for classifying benign versus malignant thyroid nodules based on ultrasound images: A comparison with radiologist-based assessments

Abstract

Purpose: To develop a semiautomated computer-aided diagnosis (CAD) system for thyroid cancer using two-dimensional ultrasound images that can be used to yield a second opinion in the clinic to differentiate malignant and benign lesions. Methods: A total of 118 ultrasound images that included axial and longitudinal images from patients with biopsy-confirmed malignant (n = 30) and benign (n = 29) nodules were collected. Thyroid CAD software was developed to extract quantitative features from these images based on thyroid nodule segmentation in which adaptive diffusion flow for active contours was used. Various features, including histogram, intensity differences, elliptical fit, gray-level co-occurrence matrixes, and gray-level run-length matrixes, were evaluated for each region imaged. Based on these imaging features, a support vector machine (SVM) classifier was used to differentiate benign and malignant nodules. Leave-one-out cross-validation with sequential forward feature selection was performed to evaluate the overall accuracy of this method. Additionally, analyses with contingency tables and receiver operating characteristic (ROC) curves were performed to compare the performance of CAD with visual inspection by expert radiologists based on established gold standards. Results: Most univariate features for this proposed CAD system attained accuracies that ranged from 78.0% to 83.1%. When optimal SVM parameters that weremore » established using a grid search method with features that radiologists use for visual inspection were employed, the authors could attain rates of accuracy that ranged from 72.9% to 84.7%. Using leave-one-out cross-validation results in a multivariate analysis of various features, the highest accuracy achieved using the proposed CAD system was 98.3%, whereas visual inspection by radiologists reached 94.9% accuracy. To obtain the highest accuracies, “axial ratio” and “max probability” in axial images were most frequently included in the optimal feature sets for the authors’ proposed CAD system, while “shape” and “calcification” in longitudinal images were most frequently included in the optimal feature sets for visual inspection by radiologists. The computed areas under curves in the ROC analysis were 0.986 and 0.979 for the proposed CAD system and visual inspection by radiologists, respectively; no significant difference was detected between these groups. Conclusions: The use of thyroid CAD to differentiate malignant from benign lesions shows accuracy similar to that obtained via visual inspection by radiologists. Thyroid CAD might be considered a viable way to generate a second opinion for radiologists in clinical practice.« less

Authors:
 [1];  [2]; ; ;  [3];  [4]; ;  [5]; ;  [6]
  1. School of Electrical Engineering, Korea Advanced Institute of Science and Technology, 291, Daehak-ro, Yuseong-gu, Daejeon 34141 (Korea, Republic of)
  2. Funzin, Inc., 148 Ankuk-dong, Jongro-gu, Seoul 03060 (Korea, Republic of)
  3. Department of Radiology, University of Ulsan College of Medicine, 388-1 Pungnap2-dong, Songpa-gu, Seoul 05505 (Korea, Republic of)
  4. Department of Radiology, Ajou University School of Medicine, Wonchon-Dong, Yeongtong-Gu, Suwon 16499 (Korea, Republic of)
  5. Department of Otolaryngology Head and Neck Surgery, Kosin University College of Medicine, 34 Amnamdong, Seu-Gu, Busan 49267 (Korea, Republic of)
  6. MIDAS Information Technology, Pangyo-ro 228, Bundang-gu, Seongnam-si, Gyeonggi 13487 (Korea, Republic of)
Publication Date:
OSTI Identifier:
22579836
Resource Type:
Journal Article
Journal Name:
Medical Physics
Additional Journal Information:
Journal Volume: 43; Journal Issue: 1; Other Information: (c) 2016 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA); Journal ID: ISSN 0094-2405
Country of Publication:
United States
Language:
English
Subject:
62 RADIOLOGY AND NUCLEAR MEDICINE; 61 RADIATION PROTECTION AND DOSIMETRY; ACCURACY; AXIAL RATIO; BIOMEDICAL RADIOGRAPHY; BIOPSY; COMPUTERS; DIAGNOSIS; IMAGES; MULTIVARIATE ANALYSIS; NEOPLASMS; THYROID; TWO-DIMENSIONAL SYSTEMS; VALIDATION

Citation Formats

Chang, Yongjun, Paul, Anjan Kumar, Kim, Namkug, E-mail: namkugkim@gmail.com, Baek, Jung Hwan, Choi, Young Jun, Ha, Eun Ju, Lee, Kang Dae, Lee, Hyoung Shin, Shin, DaeSeock, and Kim, Nakyoung. Computer-aided diagnosis for classifying benign versus malignant thyroid nodules based on ultrasound images: A comparison with radiologist-based assessments. United States: N. p., 2016. Web. doi:10.1118/1.4939060.
Chang, Yongjun, Paul, Anjan Kumar, Kim, Namkug, E-mail: namkugkim@gmail.com, Baek, Jung Hwan, Choi, Young Jun, Ha, Eun Ju, Lee, Kang Dae, Lee, Hyoung Shin, Shin, DaeSeock, & Kim, Nakyoung. Computer-aided diagnosis for classifying benign versus malignant thyroid nodules based on ultrasound images: A comparison with radiologist-based assessments. United States. doi:10.1118/1.4939060.
Chang, Yongjun, Paul, Anjan Kumar, Kim, Namkug, E-mail: namkugkim@gmail.com, Baek, Jung Hwan, Choi, Young Jun, Ha, Eun Ju, Lee, Kang Dae, Lee, Hyoung Shin, Shin, DaeSeock, and Kim, Nakyoung. Fri . "Computer-aided diagnosis for classifying benign versus malignant thyroid nodules based on ultrasound images: A comparison with radiologist-based assessments". United States. doi:10.1118/1.4939060.
@article{osti_22579836,
title = {Computer-aided diagnosis for classifying benign versus malignant thyroid nodules based on ultrasound images: A comparison with radiologist-based assessments},
author = {Chang, Yongjun and Paul, Anjan Kumar and Kim, Namkug, E-mail: namkugkim@gmail.com and Baek, Jung Hwan and Choi, Young Jun and Ha, Eun Ju and Lee, Kang Dae and Lee, Hyoung Shin and Shin, DaeSeock and Kim, Nakyoung},
abstractNote = {Purpose: To develop a semiautomated computer-aided diagnosis (CAD) system for thyroid cancer using two-dimensional ultrasound images that can be used to yield a second opinion in the clinic to differentiate malignant and benign lesions. Methods: A total of 118 ultrasound images that included axial and longitudinal images from patients with biopsy-confirmed malignant (n = 30) and benign (n = 29) nodules were collected. Thyroid CAD software was developed to extract quantitative features from these images based on thyroid nodule segmentation in which adaptive diffusion flow for active contours was used. Various features, including histogram, intensity differences, elliptical fit, gray-level co-occurrence matrixes, and gray-level run-length matrixes, were evaluated for each region imaged. Based on these imaging features, a support vector machine (SVM) classifier was used to differentiate benign and malignant nodules. Leave-one-out cross-validation with sequential forward feature selection was performed to evaluate the overall accuracy of this method. Additionally, analyses with contingency tables and receiver operating characteristic (ROC) curves were performed to compare the performance of CAD with visual inspection by expert radiologists based on established gold standards. Results: Most univariate features for this proposed CAD system attained accuracies that ranged from 78.0% to 83.1%. When optimal SVM parameters that were established using a grid search method with features that radiologists use for visual inspection were employed, the authors could attain rates of accuracy that ranged from 72.9% to 84.7%. Using leave-one-out cross-validation results in a multivariate analysis of various features, the highest accuracy achieved using the proposed CAD system was 98.3%, whereas visual inspection by radiologists reached 94.9% accuracy. To obtain the highest accuracies, “axial ratio” and “max probability” in axial images were most frequently included in the optimal feature sets for the authors’ proposed CAD system, while “shape” and “calcification” in longitudinal images were most frequently included in the optimal feature sets for visual inspection by radiologists. The computed areas under curves in the ROC analysis were 0.986 and 0.979 for the proposed CAD system and visual inspection by radiologists, respectively; no significant difference was detected between these groups. Conclusions: The use of thyroid CAD to differentiate malignant from benign lesions shows accuracy similar to that obtained via visual inspection by radiologists. Thyroid CAD might be considered a viable way to generate a second opinion for radiologists in clinical practice.},
doi = {10.1118/1.4939060},
journal = {Medical Physics},
issn = {0094-2405},
number = 1,
volume = 43,
place = {United States},
year = {2016},
month = {1}
}