Biomaterial Database

Artificial Intelligence in Thyroid Fine Needle Aspiration Biopsies. 2021

Brie Kezlarian, and Oscar Lin

Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA.

BACKGROUND From cell phones to aerospace, artificial intelligence (AI) has wide-reaching influence in the modern age. In this review, we discuss the application of AI solutions to an equally ubiquitous problem in cytopathology - thyroid fine needle aspiration biopsy (FNAB). Thyroid nodules are common in the general population, and FNAB is the sampling modality of choice. The resulting prevalence in the practicing pathologist's daily workload makes thyroid FNAB an appealing target for the application of AI solutions. CONCLUSIONS This review summarizes all available literature on the application of AI to thyroid cytopathology. We follow the evolution from morphometric analysis to convolutional neural networks. We explore the application of AI technology to different questions in thyroid cytopathology, including distinguishing papillary carcinoma from benign, distinguishing follicular adenoma from carcinoma and identifying non-invasive follicular thyroid neoplasm with papillary-like nuclear features by key words and phrases. Key Messages: The current literature shows promise towards the application of AI technology to thyroid fine needle aspiration biopsy. Much work is needed to define how this powerful technology will be of best use to the future of cytopathology practice.

UI	MeSH Term	Description	Entries
D007090	Image Interpretation, Computer-Assisted	Methods developed to aid in the interpretation of ultrasound, radiographic images, etc., for diagnosis of disease.	Image Interpretation, Computer Assisted,Computer-Assisted Image Interpretation,Computer-Assisted Image Interpretations,Image Interpretations, Computer-Assisted,Interpretation, Computer-Assisted Image,Interpretations, Computer-Assisted Image
D011237	Predictive Value of Tests	In screening and diagnostic tests, the probability that a person with a positive test is a true positive (i.e., has the disease), is referred to as the predictive value of a positive test; whereas, the predictive value of a negative test is the probability that the person with a negative test does not have the disease. Predictive value is related to the sensitivity and specificity of the test.	Negative Predictive Value,Positive Predictive Value,Predictive Value Of Test,Predictive Values Of Tests,Negative Predictive Values,Positive Predictive Values,Predictive Value, Negative,Predictive Value, Positive
D003936	Diagnosis, Computer-Assisted	Application of computer programs designed to assist the physician in solving a diagnostic problem.	Computer-Assisted Diagnosis,Computer Assisted Diagnosis,Computer-Assisted Diagnoses,Diagnoses, Computer-Assisted,Diagnosis, Computer Assisted
D003937	Diagnosis, Differential	Determination of which one of two or more diseases or conditions a patient is suffering from by systematically comparing and contrasting results of diagnostic measures.	Diagnoses, Differential,Differential Diagnoses,Differential Diagnosis
D006801	Humans	Members of the species Homo sapiens.	Homo sapiens,Man (Taxonomy),Human,Man, Modern,Modern Man
D000069550	Machine Learning	A type of ARTIFICIAL INTELLIGENCE that enable COMPUTERS to independently initiate and execute LEARNING when exposed to new data.	Transfer Learning,Learning, Machine,Learning, Transfer
D013964	Thyroid Neoplasms	Tumors or cancer of the THYROID GLAND.	Cancer of Thyroid,Thyroid Cancer,Cancer of the Thyroid,Neoplasms, Thyroid,Thyroid Adenoma,Thyroid Carcinoma,Adenoma, Thyroid,Adenomas, Thyroid,Cancer, Thyroid,Cancers, Thyroid,Carcinoma, Thyroid,Carcinomas, Thyroid,Neoplasm, Thyroid,Thyroid Adenomas,Thyroid Cancers,Thyroid Carcinomas,Thyroid Neoplasm
D015203	Reproducibility of Results	The statistical reproducibility of measurements (often in a clinical context), including the testing of instrumentation or techniques to obtain reproducible results. The concept includes reproducibility of physiological measurements, which may be used to develop rules to assess probability or prognosis, or response to a stimulus; reproducibility of occurrence of a condition; and reproducibility of experimental results.	Reliability and Validity,Reliability of Result,Reproducibility Of Result,Reproducibility of Finding,Validity of Result,Validity of Results,Face Validity,Reliability (Epidemiology),Reliability of Results,Reproducibility of Findings,Test-Retest Reliability,Validity (Epidemiology),Finding Reproducibilities,Finding Reproducibility,Of Result, Reproducibility,Of Results, Reproducibility,Reliabilities, Test-Retest,Reliability, Test-Retest,Result Reliabilities,Result Reliability,Result Validities,Result Validity,Result, Reproducibility Of,Results, Reproducibility Of,Test Retest Reliability,Validity and Reliability,Validity, Face
D016571	Neural Networks, Computer	A computer architecture, implementable in either hardware or software, modeled after biological neural networks. Like the biological system in which the processing capability is a result of the interconnection strengths between arrays of nonlinear processing nodes, computerized neural networks, often called perceptrons or multilayer connectionist models, consist of neuron-like units. A homogeneous group of units makes up a layer. These networks are good at pattern recognition. They are adaptive, performing tasks by example, and thus are better for decision-making than are linear learning machines or cluster analysis. They do not require explicit programming.	Computational Neural Networks,Connectionist Models,Models, Neural Network,Neural Network Models,Neural Networks (Computer),Perceptrons,Computational Neural Network,Computer Neural Network,Computer Neural Networks,Connectionist Model,Model, Connectionist,Model, Neural Network,Models, Connectionist,Network Model, Neural,Network Models, Neural,Network, Computational Neural,Network, Computer Neural,Network, Neural (Computer),Networks, Computational Neural,Networks, Computer Neural,Networks, Neural (Computer),Neural Network (Computer),Neural Network Model,Neural Network, Computational,Neural Network, Computer,Neural Networks, Computational,Perceptron
D044963	Biopsy, Fine-Needle	Using fine needles (finer than 22-gauge) to remove tissue or fluid specimens from the living body for examination in the pathology laboratory and for disease diagnosis.	Aspiration Biopsy, Fine-Needle,Fine Needle Biopsy,Fine-Needle Aspiration,Aspiration Biopsies, Fine-Needle,Aspiration Biopsy, Fine Needle,Aspiration, Fine-Needle,Aspirations, Fine-Needle,Biopsies, Fine Needle,Biopsies, Fine-Needle,Biopsies, Fine-Needle Aspiration,Biopsy, Fine Needle,Biopsy, Fine-Needle Aspiration,Fine Needle Aspiration,Fine Needle Biopsies,Fine-Needle Aspiration Biopsies,Fine-Needle Aspiration Biopsy,Fine-Needle Aspirations,Fine-Needle Biopsies,Fine-Needle Biopsy,Needle Biopsies, Fine,Needle Biopsy, Fine