Journal of the Korean Society of Radiology (한국방사선학회논문지)

The Korean Society of Radiology (한국방사선학회)
권호 표지
DOI QR코드

DOI QR Code

Performance of Artificial Intelligence and Elastography in Thyroid Nodule Diagnosis

갑상선 결절 진단에서 인공지능과 탄성초음파의 성능 분석

  • Jee-Yeon Park (Department of Radiological Science, Jangpalpal Internal Medicine Clinic) ;
  • Sung-Hee Yang (Department of Radiological Science, College of Health Sciences, Catholic University of Pusan)
  • 박지연 (장팔팔내과 영상의학과) ;
  • 양성희 (부산가톨릭대학교 방사선학과)
  • Received : 2024.09.02
  • Accepted : 2024.10.31
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

The objective of this study is to analyze and evaluate the diagnostic performance and utility of elastography and artificial intelligence program in distinguishing between benign and malignant thyroid nodule. In a hospital outpatient clinic, we performed thyroid ultrasound from January 2023 to June 2024, and retrospectively analyzed 126 patients who performed elastography, S-detect, and fine needle aspiration cytology(FNAC) because nodules were found. The analysis of differences based on cytology results showed statistically significant differences in age, nodule size, echogenicity, nodule orientation, margins, shape, presence of calcification, posterior shadowing, K-TIRADS ultrasound interpretation, S-detect results and elasticity contrast index. The ROC curve analysis determined a cut off value for the elasticity contrast index at 2.32, with diagnostic concordance rates of 0.66 for expert interpretation, 0.49 for S-detect, and 0.67 for the elasticity contrast index, indicating superior diagnostic performance with elastography. Thus, elastography may ge used as an adjunct tool to minimize unnecessary repeat examinations and the frequency of tissue biopsies in the diagnosis of thyroid nodules.

본 연구는 갑상선 결절의 양성과 악성 가능성을 진단하는데 있어서 탄성초음파와 인공지능 프로그램의 진단 성능을 분석하고 유용성을 평가하는데 있다. 일개 병원 외래에서 2023년 1월부터 2024년 6월까지 갑상선 초음파검사를 실시하고 결절이 발견되어 탄성초음파, S-detect, 세침흡인세포검사를 시행한 환자 126명을 대상으로 후향적으로 분석하였다. 그 결과 세침흡인세포검사 결과에 따른 차이 분석에서 나이, 결절의 크기, 에코발생정도, 결절의 방향, 변연, 모양, 석회화 유무, 후방음영, K-TIRADS 초음파 판독, S-detect의 진단 결과, 탄성대비지수에서 통계적으로 유의한 차이를 나타냈다. ROC curve 분석 결과 탄성대비지수의 cut off value 는 2.32로 산출되었으며 진단 일치도는 전문의 판독 0.66, S-detect 0.49, 탄성대비지수 0.67로 탄성초음파에서 높은 진단 성능을 나타냈다. 따라서 탄성초음파를 이용한 갑상선 결절의 진단은 불필요한 반복 검사와 조직검사의 빈도를 최소화하기 위한 보조 프로그램으로 활용 가능성이 있을 것으로 판단된다.

Keywords

Acknowledgement

This paper was supported by RESEARCH FUND offered from Catholic University of Pusan in 2024.

References

  1. Y. J. Park, E. K. Lee, Y. S. Song, S. H. Kang, B. S. Koo, S. W. Kim, D. G. Na, S. K. Baek, S. W. Oh, M. K. Lee, S. W. Lee, Y. A. Lee, Y. S. Lee, D. J. Lim, "2023 Korean thyroid association management guidelines for patients with thyroid nodules", International Journal of Thyroidology, Vol. 16, No. 1, pp. 1-311, 2023. https://doi.org/10.11106/ijt.2023.16.1.1 
  2. L. Hegedus, "Clinical practice: The thyroid nodule", The New England Journal of Medicine, Vol. 351, No. 17, pp. 1764-1771, 2004. https://doi.org/10.1056/NEJMcp031436 
  3. K. H. Kim, E. K. Kim, J. Y. Kwak, M. J. Kim, "Detection and management of thyroid incidentaloma", Korean Society of Ultrasound in Medicine, Vol. 27, No. 3, pp. 111-117, 2008. https://doi.org/JAKO200810103435312  10103435312
  4. Korea Central Cancer Registry, National Cancer Center, "Annual report of cancer statistics in Korea in 2020", Ministry of Health and Welfare, From URL; https://www.ncc.re.kr/cancerStatsList.ncc 
  5. S. Y. Hahn, J. H. Shin, Y. L. Oh, Y. I. Son, "Discrepancies between the ultrasonographic and gross pathological size of papillary thyroid carcinomas", Ultrasonography, Vol. 35, No. 3, pp. 220-225, 2016. https://doi.org/10.14366/usg.15077 
  6. W. Tian, S. Hao, Y. Jiang, S. Zhang, L. Guo, D. Luo, "Comparison of diagnostic accuracy of real-time elastography and shear wave elastography in differentiation malignant from benign thyroid nodules", Medicine(Baltimore), Vol. 94, No. 52, e2312, 2015. https://doi.org/10.1097/MD.0000000000002312 
  7. Y. J. Lee, D. W. Kim, Y. M. Park, H. K. Park, S. J. Jung, D. H. Kim, S. M. Lee, M. K. Oh, "Comparison of sonographic and cytological diagnoses of solid thyroid nodules:emphasis on the discordant cases", Diagn Cytopathol, Vol. 43, No. 12, pp. 953-959, 2015. https://doi.org/10.1002/dc.23363 
  8. B. R. Haugen, E. K. Alexander, K. C. Bible, G. M. Doherty, S. J. Mandel, Y. E. Nikiforov, F. Pacini, G. W. Randolph, A. M. Sawka, M. Schlumberger, K. G. Schuff, S. I. Sherman, J. A. Sosa, D. L. Steward, R. M. Tuttle, L. Wartofsky, "2015 American thyroid association management guidelines for adult patients with thyroid nodules and differntiated thyroid cancer:the American thyroid association guidelines task force on thyroid nodules and differentiated thyroid cancer", Thyroid, Vol. 26, No. 1, pp. 1-133, 2016. https://doi.org/10.1089/thy.2015.0020 
  9. E. J. Ha, J. H. Baek, "Applications of machine learning and deep learning to thyroid imaging:where do we stand?", Ultrasonography, Vol. 40, No. 1, pp. 23-29, 2021. https://doi.org/10.14366/usg.20068 
  10. C. K. Zhao, H. X. Xu, "Ultrasound elastography of the thyroid:principles and current status", Ultrosonography, Vol. 38, No. 2, pp. 106-124, 2018. https://doi.org/10.14366/usg.18037 
  11. S. Y. Hahn, J. H. Shin, E. Y. Ko, J. M. Bae, J. S. Choi, K. W. Park, "Complementary role of elastography using carotid artery pulsation in the ultrasonography assessment of thyroid nodules: A prospective study", Korean Journal of Radiology, Vol. 19, No. 5, pp. 992-999, 2018. https://doi.org/10.3348/kjr.2018.19.5.992 
  12. E. Y. Ko, "S-detect in breast ultrasound: Initial experience", Samsung Medical Center, Medison, Seoul, Korea, From URL; http://www.samsung.com/global/business 
  13. J. Y. Park, Y. I. Cho, S. H. Yang, "Diagnostic Usefulness of Deep Learning Based S-detect Using Thyroid Ultrasonography", The Journal of Next-generation Convergence Technology Association, Vol. 8, No. 2, pp. 343-350, 2024. https://doi.org/10.33097/JNCTA.2024.08.2.343 
  14. A. Jha, "Ultrasonographic elasticity contrast index of palpable breast lumps", Journal of Nepal Medical Association, Vol. 56, No. 212, pp. 787-790, 2018. https://doi.org/10.131729/jnma.3536 
  15. W. K. Moon, J. M. Chang, N. Cho, "Elastography of the breast:Imaging techniques and pitfalls in interpretation", ULTRASONOGRAPHY (USG), Vol. 30, No. 4, pp.245-249, 2011. 
  16. J. Ophir, B. Garra, F. Kallel, E. Konofagou, T. Krouskop, R. Righetti, T. Varghese, "Elastographic imaging", Ultrasound in Medicine & Biology, Vol. 26, No. 1, pp. 23-29, 2000. http://doi.org/10.1016/S0301-5629(00)00156-3 
  17. Y. Hong, X. Liu, Z. Li, X. Zhang, M. Chen, Z. Luo, "Real-time ultrasound elastography in the differential diagnosis of benign and malignant thyroid nodules", Journal of Ultrasound in Medicine, Vol. 28, No. 7, pp. 861-867, 2009. https://doi.org/10.7863/jum.2009.28.7.861 
  18. S. H. Yang, J. S. Lee, "Evaluation of breast ultrasound lesion recognition rate using machine leaarning application", Nest-generation Convergence Technology Association, Vol. 7, No. 8, pp. 1261-1267, 2023. https://doi.org/1033097/JNCTA.2023.07.08.1261  1033097/JNCTA.2023.07.08.1261
  19. Z. Di, Z. Li, J. Tian, D. Wang, L. Liu, C. Liu, "The value of elasticity contrast index in the differential diagnosis of thyroid solid nodules", Ultrasound Quarterly, Vol. 35, No. 3, pp. 259-263, 2019. https://doi.org/10.1097.RUQ.0000000000000457  https://doi.org/10.1097.RUQ.0000000000000457
  20. P. Cong, X. M. Wang, Y. F. Zhang, "Comparison of artificial intelligence, elastic imaging, and the thyroid imaging reporting and data system in the differential diagnosis of suspicious nodules", Quantitative Imaging in Medicine and Surgery, Vol. 14, No. 1, pp. 711-721, 2024. https://doi.org/10.21037/qims-23-788 
  21. J. L. Reverter, F. Vazquez, M. Puig-Domingo, "Diagnostic performance evaluation of computer-assisted imaging analysis system for ultrasoun risk stratification of thyroid nodules", American Journal of Roentgenology, Vol. 213, No. 1, pp. 169-174, 2019. https://doi.org/10.2214/AJR.18.20740 
  22. P. Sun, Y. Feng, C. Chen, A. Dekker, L. Qian, Z. Wang, J. Guo, "An AI model of sonogarpher's evaluation + S-Detect + elastography + clinical information improves the preoperative identification of benign and malignant breast masses", Frontiers in Oncology, 2022. https://doi.org/10.3389/fonc.2022.1022441 
  23. S. H. Park, S. J. Kim, E. K. Kim, M. J. Kim, E. J. Son, J. Y. Kwak, "Interobserver agreement in assessing the sonographic and elastographic features of malignant thyroid nodules", American Journal of Roentgenology, Vol. 193, N0. 5, pp. 416-423, 2009. https://doi.org/102214/AJR.09.2541 102214/AJR.09.2541