Imaging of the Thyroid: Practical Approach

Preoperative Evaluation of Thyroid Cancer: A Review of Current Best Practices

OBJECTIVE

The incidence of thyroid cancer has significantly increased in recent decades. Although most thyroid cancers are small and carry an excellent prognosis, a subset of patients present with advanced thyroid cancer, which is associated with increased rates of morbidity and mortality. The management of thyroid cancer requires a thoughtful individualized approach to optimize oncologic outcomes and minimize morbidity associated with treatment. Because endocrinologists usually play a key role in the initial diagnosis and evaluation of thyroid cancers, a thorough understanding of the critical components of the preoperative evaluation facilitates the development of a timely and comprehensive management plan. The following review outlines considerations in the preoperative evaluation of patients with thyroid cancer.

METHODS

A clinical review based on current literature was generated by a multidisciplinary author panel.

RESULTS

A review of considerations in the preoperative evaluation of thyroid cancer is provided. The topic areas include initial clinical evaluation, imaging modalities, cytologic evaluation, and the evolving role of mutational testing. Special considerations in the management of advanced thyroid cancer are discussed.

CONCLUSION

Thorough and thoughtful preoperative evaluation is critical for formulating an appropriate treatment strategy in the management of thyroid cancer.

Automatic segmentation of thyroid with the assistance of the devised boundary improvement based on multicomponent small dataset

Deep learning has been widely considered in medical image segmentation. However, the difficulty of acquiring medical images and labels can affect the accuracy of the segmentation results for deep learning methods. In this paper, an automatic segmentation method is proposed by devising a multicomponent neighborhood extreme learning machine to improve the boundary attention region of the preliminary segmentation results. The neighborhood features are acquired by training U-Nets with the multicomponent small dataset, which consists of original thyroid ultrasound images, Sobel edge images and superpixel images. Afterward, the neighborhood features are selected by min-redundancy and max-relevance filter in the designed extreme learning machine, and the selected features are used to train the extreme learning machine to obtain supplementary segmentation results. Finally, the accuracy of the segmentation results is improved by adjusting the boundary attention region of the preliminary segmentation results with the supplementary segmentation results. This method combines the advantages of deep learning and traditional machine learning, boosting the accuracy of thyroid segmentation accuracy with a small dataset in a multigroup test.