Computer-Aided Diagnosis of Thyroid Nodules via Ultrasonography: Initial Clinical Experience

被引:65
作者
Yoo, Young Jin [1 ]
Ha, Eun Ju [1 ]
Cho, Yoon Joo [1 ]
Kim, Hye Lin [1 ]
Han, Miran [1 ]
Kang, So Young [2 ]
机构
[1] Ajou Univ, Sch Med, Dept Radiol, 164 World Cup Ro, Suwon 16499, South Korea
[2] Ajou Univ, Sch Med, Dept Biostat, Suwon 16499, South Korea
关键词
Artificial intelligence; Computer-aided diagnosis; Thyroid nodule; Thyroid cancer; Ultrasonography; Ultrasound; LESION CLASSIFICATION; ULTRASOUND; BENIGN; SYSTEM; DIFFERENTIATION; COMBINATION; POPULATION; MANAGEMENT;
D O I
10.3348/kjr.2018.19.4.665
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Objective: To prospectively evaluate the diagnostic performance of computer-aided diagnosis (CAD) for detection of thyroid cancers via ultrasonography (US). Materials and Methods: This study included 50 consecutive patients with 117 thyroid nodules on US during the period between June 2016 and July 2016. A radiologist performed US examinations using real-time CAD integrated into a US scanner. We compared the diagnostic performance of radiologist, the CAD system, and the CAD-assisted radiologist for the detection of thyroid cancers. Results: The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of the CAD system were 80.0, 88.1, 83.3, 85.5, and 84.6%, respectively, and were not significantly different from those of the radiologist (p > 0.05). The CAD-assisted radiologist showed improved diagnostic sensitivity compared with the radiologist alone (92.0% vs. 84.0%, p = 0.037), while the specificity and PPV were reduced (85.1% vs. 95.5%, p = 0.005 and 82.1% vs. 93.3%, p = 0.008). The radiologist assisted by the CAD system exhibited better diagnostic sensitivity and NPV than the CAD system alone (92.0% vs. 80.0%, p = 0.009 and 93.4% vs. 88.9%, p = 0.013), while the specificities and PPVs were not significantly different (88.1% vs. 85.1%, p = 0.151 and 83.3% vs. 82.1%, p = 0.613, respectively). Conclusion: The CAD system may be an adjunct to radiological intervention in the diagnosis of thyroid cancer.
引用
收藏
页码:665 / 672
页数:8
相关论文
共 20 条
  • [1] Cost-Effective and Non-Invasive Automated Benign & Malignant Thyroid Lesion Classification in 3D Contrast-Enhanced Ultrasound Using Combination of Wavelets and Textures: A Class of ThyroScan™ Algorithms
    Acharya, U. R.
    Faust, O.
    Sree, S. V.
    Molinari, F.
    Garberoglio, R.
    Suri, J. S.
    [J]. TECHNOLOGY IN CANCER RESEARCH & TREATMENT, 2011, 10 (04) : 371 - 380
  • [2] Computer-Aided Diagnostic System for Detection of Hashimoto Thyroiditis on Ultrasound Images From a Polish Population
    Acharya, U. Rajendra
    Sree, S. Vinitha
    Krishnan, M. Muthu Rama
    Molinari, Filippo
    Zieleznik, Witold
    Bardales, Ricardo H.
    Witkowska, Agnieszka
    Suri, Jasjit S.
    [J]. JOURNAL OF ULTRASOUND IN MEDICINE, 2014, 33 (02) : 245 - 253
  • [3] ThyroScreen system: High resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform
    Acharya, U. Rajendra
    Faust, Oliver
    Sree, S. Vinitha
    Molinari, Filippo
    Suri, Jasjit S.
    [J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2012, 107 (02) : 233 - 241
  • [4] Non-invasive automated 3D thyroid lesion classification in ultrasound: A class of ThyroScan™ systems
    Acharya, U. Rajendra
    Sree, S. Vinitha
    Krishnan, M. Muthu Rama
    Molinari, Filippo
    Garberoglio, Roberto
    Suri, Jasjit S.
    [J]. ULTRASONICS, 2012, 52 (04) : 508 - 520
  • [5] THYROID-GLAND - ULTRASOUND SCREENING IN A RANDOM ADULT-POPULATION
    BRANDER, A
    VIIKINKOSKI, P
    NICKELS, J
    KIVISAARI, L
    [J]. RADIOLOGY, 1991, 181 (03) : 683 - 687
  • [6] AMERICAN ASSOCIATION OF CLINICAL ENDOCRINOLOGISTS AND AMERICAN COLLEGE OF ENDOCRINOLOGY CLINICAL PRACTICE GUIDELINES FOR THE DIAGNOSIS AND TREATMENT OF POSTMENOPAUSAL OSTEOPOROSIS-2016
    Camacho, Pauline M.
    Petak, Steven M.
    Binkley, Neil
    Clarke, Bart L.
    Harris, Steven T.
    Hurley, Daniel L.
    Kleerekoper, Michael
    Lewiecki, E. Michael
    Miller, Paul D.
    Narula, Harmeet S.
    Pessah-Pollack, Rachel
    Tangpricha, Vin
    Wimalawansa, Sunil J.
    Watts, Nelson B.
    [J]. ENDOCRINE PRACTICE, 2016, 22 : 1 - 42
  • [7] Computer-aided diagnosis for classifying benign versus malignant thyroid nodules based on ultrasound images: A comparison with radiologist-based assessments
    Chang, Yongjun
    Paul, Anjan Kumar
    Kim, Namkug
    Baek, Jung Hwan
    Choi, Young Jun
    Ha, Eun Ju
    Lee, Kang Dae
    Lee, Hyoung Shin
    Shin, DaeSeock
    Kim, Nakyoung
    [J]. MEDICAL PHYSICS, 2016, 43 (01) : 554 - 567
  • [8] Interobserver and Intraobserver Variations in Ultrasound Assessment of Thyroid Nodules
    Choi, Seon Hyeong
    Kim, Eun-Kyung
    Kwak, Jin Young
    Kim, Min Jung
    Son, Eun Ju
    [J]. THYROID, 2010, 20 (02) : 167 - 172
  • [9] A Computer-Aided Diagnosis System Using Artificial Intelligence for the Diagnosis and Characterization of Thyroid Nodules on Ultrasound: Initial Clinical Assessment
    Choi, Young Jun
    Baek, Jung Hwan
    Park, Hye Sun
    Shim, Woo Hyun
    Kim, Tae Yong
    Shong, Young Kee
    Lee, Jeong Hyun
    [J]. THYROID, 2017, 27 (04) : 546 - 552
  • [10] A Multicenter Prospective Validation Study for the Korean Thyroid Imaging Reporting and Data System in Patients with Thyroid Nodules
    Ha, Eun Ju
    Moon, Won-Jin
    Na, Dong Gyu
    Lee, Young Hen
    Choi, Nami
    Kim, Soo Jin
    Kim, Jae Kyun
    [J]. KOREAN JOURNAL OF RADIOLOGY, 2016, 17 (05) : 811 - 821