Thyroid nodules are a very common finding, with a prevalence greater than 50% in women and older populations (>60 years old). The clinical impact is primarily represented by the precocious identification of thyroid nodule malignant potential, representing the 5-10% of thyroid nodule. Currently the gold standard for the diagnosis of thyroid tumors is fine needle aspiration cytology (FNAC), but in the last decades there have been many efforts in order to reduce the number of unnecessary procedures by enhancing the diagnostic accuracy of ultrasound. Ultrasonography (US) is the gold standard imaging in thyroid diseases, offering many perks such as being economic and non invasive, besides having a wide diffusion on the territory. The improvements in this field have been aimed on: 1) developing new techniques in order to better characterize thyroid nodules, such as elastography; 2) identifying the neoplastic iconographic features to create classification systems able to stratify nodules on a risk basis, such as TI-RADS; 3) create automated
systems based on artificial intelligence to help physician in detecting and evaluating thyroid nodules, on the model of Computer Aided Diagnosis (CAD) systems already existing in other radiological fields.
The aim of the present project is therefore to assess the diagnostic accuracy and interobserver variability of ultrasound techniques performed by physicians with different levels of expertise using two distinct TI-RADS and elastography in comparison with two CAD systems, and to create a repository for newer AI System.
All the above mentioned advancements in ultrasound evaluation of thyroid nodules are not fully entered in the daily clinical practice. TI-RADS lexicons and risk classification are still not widely used, causing misunderstanding among the professional figures in charge of different parts of the management of patients affected by thyroid nodules, above all when they belong to different institutions. New technologies as CAD systems and elastography often find resistance and mistrust as well, above all by operators (e.g. general practitioners) who do not have a direct contact with them and often do not know the potential benefits deriving from their utilization. The production of studies demonstrating the validity, the diagnostic accuracy and potentialities of these methods and tools, as well as the advantages for both the patients and the operators, is desirable in order to allow their wider acceptance and employment.
As previously discussed, the role of elastography in the diagnosis of thyroid nodules is still controversial, above all because of the overlapping of the values of benign and malignant nodules; the addition of an elastographic evaluation in a wide setting which includes the assessment of operators with different level of experience, two different TI-RADS and two CAD systems and in which histologic exam is utilized as a gold standard, could improve our comprehension of the real role of elastography in the diagnosis of thyroid nodules and could be helpful in defining more precise cut-off values, also in association with the results of the other available tools. Consequently this could bring to a reduction of the afore mentioned overlapping and could help defining the role of elastography in this field.
In previous study ACR TI-RADS and EU-TIRADS yelded similar diagnostic results; however their employment in this study with the addition of elastographic evaluation and the comparison with histologic exam and the results of two CAD systems could be useful in sorting out if one of them is able to show some perks in comparison with the other one.
Concerning CAD systems, they are gaining space in different fields of medicine with diagnostic imaging being the most conspicuous one; it is predictable that their role will become increasingly essential in the near future of daily clinical practice as technology, and therefore their performances, will advance. However in thyroid nodules diagnosis some studies demonstrated that their results are still inferior when compared with expert operators and nobody compared more than one semi-automatically applied TIRADS system. Finally, the collection of our images will be used for producing a possible new and more effective CAD to improve the performance of the thyroid nodule classification system
Results will be presented at National and International Meeting and reported in possible Open access publications in High Level IF Journals.
1) Chambara N, Liu SYW, Lo X, Ying M. Diagnostic performance evaluation of different TI-RADS using ultrasound computer-aided diagnosis of thyroid nodules: An experience with adjusted settings. PLoS One. 2021 Jan 15;16(1):e0245617.
2) Wildman-Tobriner B, Buda M, Hoang JK, et al. Using Artificial Intelligence to Revise ACR TI-RADS Risk Stratification of Thyroid Nodules: Diagnostic Accuracy and Utility. Radiology. 2019 Jul;292(1):112-119.