Artificial Intelligence in Thyroid Field—A Comprehensive Review
Open Access
- 22 September 2021
- Vol. 13 (19), 4740
- https://doi.org/10.3390/cancers13194740
Abstract
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.This publication has 81 references indexed in Scilit:
- Machine Learning methods for Quantitative Radiomic BiomarkersScientific Reports, 2015
- Thermal-electric model for piezoelectric ZnO nanowiresNanotechnology, 2015
- Deep learningNature, 2015
- A novel approach to a phantom based method for maximum depth of penetration measurement in diagnostic ultrasound: a preliminary studyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- What Is Machine Learning?Published by Springer Science and Business Media LLC ,2015
- Analysis of tissue surrounding thyroid nodules by ultrasound digital imagesEndocrine, 2014
- Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approachNature Communications, 2014
- Calibration procedure for performance evaluation of clinical Pulsed Doppler SystemsMeasurement, 2012
- Radiomics: Extracting more information from medical images using advanced feature analysisEuropean Journal of Cancer, 2012
- A support vector machine approach for detection of microcalcificationsIEEE Transactions on Medical Imaging, 2002