News & Views | Published:


Sonographic diagnosis of thyroid cancer with support of AI

Nature Reviews Endocrinologyvolume 15pages319321 (2019) | Download Citation

Thyroid ultrasonography is an important element of clinical thyroid diagnostics. Unfortunately, the results of this technique can vary based on the skill and experience of the operator. A new study suggests that assessment of ultrasound images using artificial intelligence has similar sensitivity and improved specificity compared with the judgement of experienced radiologists.

Access optionsAccess options

Rent or Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.


  1. 1.

    Li, X. et al. Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study. Lancet Oncol. 20, 193–201 (2019).

  2. 2.

    Hu, X., Liu, Y. & Qian, L. Diagnostic potential of real-time elastography (RTE) and shear wave elastography (SWE) to differentiate benign and malignant thyroid nodules: a systematic review and meta-analysis. Medicine (Baltimore) 96, e8282 (2017).

  3. 3.

    Lyshchik, A., Drozd, V. & Reiners, C. Accuracy of three-dimensional ultrasound for thyroid volume measurement in children and adolescents. Thyroid 14, 113–120 (2004).

  4. 4.

    Tessler, F. N., Middleton, W. D. & Grant, E. G. Thyroid Imaging Reporting and Data System (TI-RADS): a user’s guide. Radiology 287, 29–36 (2018).

  5. 5.

    Wei, X. et al. Meta-analysis of thyroid imaging reporting and data system in the ultrasonographic diagnosis of 10,437 thyroid nodules. Head Neck 38, 309–315 (2016).

  6. 6.

    Mao, F. et al. Assessment of virtual touch tissue imaging quantification and the ultrasound Thyroid Imaging Reporting and Data System in patients with thyroid nodules referred for biopsy. J. Ultrasound Med. 37, 725–736 (2018).

  7. 7.

    Poudel, P. et al. Evaluation of commonly used algorithms for thyroid ultrasound images segmentation and improvement using machine learning approaches. J. Healthc. Eng. 2018, 8087624 (2018).

  8. 8.

    Song, W. et al. Multi-task cascade convolution neural networks for automatic thyroid nodule detection and recognition. IEEE J. Biomed. Health Inform. (2018).

  9. 9.

    Wu, H. et al. Classifier model based on machine learning algorithms: application to differential diagnosis of suspicious thyroid nodules via sonography. AJR Am. J. Roentgenol. 207, 859–864 (2016).

  10. 10.

    Chi, J. et al. Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network. J. Digit. Imaging 30, 477–486 (2017).

Download references

Author information


  1. Nuclear Medicine, University Hospital Marburg, Marburg, Germany

    • Frederik Verburg
  2. Nuclear Medicine, University Hospital Würzburg, Würzburg, Germany

    • Christoph Reiners


  1. Search for Frederik Verburg in:

  2. Search for Christoph Reiners in:

Competing interests

The authors declare no competing interests.

Corresponding author

Correspondence to Christoph Reiners.

About this article

Publication history


Issue Date


Newsletter Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing