Bini, Fabiano Pica, Andrada Azzimonti, Laura Giusti, Alessandro Ruinelli, Lorenzo Marinozzi, Franco Trimboli, Pierpaolo 2021-09-22 Artificial intelligence (AI) uses mathematical algorithms to perform tasks that require human cognitive abilities. AI-based methodologies, e.g., machine learning and deep learning, as well as the recently developed research field of radiomics have noticeable potential to transform medical diagnostics. AI-based techniques applied to medical imaging allow to detect biological abnormalities, to diagnostic neoplasms or to predict the response to treatment. Nonetheless, the diagnostic accuracy of these methods is still a matter of debate. In this article, we first illustrate the key concepts and workflow characteristics of machine learning, deep learning and radiomics. We outline considerations regarding data input requirements, differences among these methodologies and their limitations. Subsequently, a concise overview is presented regarding the application of AI methods to the evaluation of thyroid images. We developed a critical discussion concerning limits and open challenges that should be addressed before the translation of AI techniques to the broad clinical use. Clarification of the pitfalls of AI-based techniques results crucial in order to ensure the optimal application for each patient. application/pdf https://susi.usi.ch/global/documents/319322 https://n2t.net/ark:/12658/srd1319322 https://susi.usi.ch/documents/319322/files/Azzimonti_c_2021.pdf eng info:eu-repo/semantics/altIdentifier/doi/10.3390/cancers13194740 info:eu-repo/semantics/altIdentifier/ark/12658/srd1319322 info:eu-repo/semantics/openAccess CC BY Cancers. - MDPI. - 2021, vol. 13, no. 19, p. 18 Thyroid neoplasm Medical imaging Artificial intelligence Machine learning Deep learning Radiomics Prediction Diagnosis info:eu-repo/classification/udc/61 Artificial intelligence in thyroid field : a comprehensive review http://purl.org/coar/resource_type/c_6501