Application of a machine learning algorithm to predict malignancy in thyroid cytopathology

Abstract

BACKGROUND:The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) comprises 6 categories used for the diagnosis of thyroid fine-needle aspiration biopsy (FNAB). Each category has an associated risk of malignancy, which is important in the management of a thyroid nodule. More accurate predictions of malignancy may help to reduce unnecessary surgery. A machine learning algorithm (MLA) was developed to evaluate thyroid FNAB via whole slide images (WSIs) to predict malignancy. METHODS: Files were searched for all thyroidectomy specimens with preceding FNAB over 8 years.All cytologic and surgical pathology diagnoses were recorded and correlated for each nodule. One representative slide from each case was scanned to create a WSI. An MLA was designed to identify follicular cells and predict the malignancy of the final pathology. The test set comprised cases blindly reviewed by a cytopathologist who assigned a TBSRTC category. The area under the receiver operating characteristic curve was used to assess the MLA performance. RESULTS: Nine hundred eight FNABs met the criteria. The MLA predicted malignancy with a sensitivity and specificity of 92.0% and 90.5%, respectively. The areas under the curve for the prediction of malignancy by the cytopathologist and the MLA were 0.931 and 0.932, respectively. CONCLUSIONS: The performance of the MLA in predicting thyroid malignancy from FNAB WSIs is comparable to the performance of an expert cytopathologist. When the MLA and electronic medical record diagnoses are combined, the performance is superior to the performance of either alone. An MLA may be used as an adjunct to FNAB to assist in refining the indeterminate categories. Cancer Cytopathol 2020;128:287-295.

Artificial Intelligence for Personalized Medicine in Thyroid Cancer: Current Status and Future Perspectives

“…While TBSRTC includes six diagnostic categories on the estimated risk of malignancy (ROM) ( Table 2 ), 15%–30% of TN continues to be classified as indeterminate TN (ITN), most frequently TBSRTC categories III, IV, and V ( 8 ). Recent studies showed excellent consistency between machine learning (ML) models and cytologists in malignancy prediction ( 49 – 51 ), in which the ROM of TBSRTC III determined by the ML model was considerably lower than by manual classification (4.2% vs. 18.8%) ( 51 ). It’s worth noting that morphological and genetic classifications assisted by the AI model are fairly accurate at distinguishing malignancy from benign TN ( 52 – 54 ) ( Table 3 ).…”

Advances in Imaging Modalities, Artificial Intelligence, and Single Cell Biomarker Analysis, and Their Applications in Cytopathology

“…However, most of these studies proved successful only in analyzing binary outcomes: malignant or benign. Many of these have been small studies and have not demonstrated enough strength to be applied to routine clinical work (32,43,44). One study has shown success in distinguishing benign from malignant tumors in the parotid gland (45).…”

Combined molecular and mathematical analysis of long noncoding RNAs expression in fine needle aspiration biopsies as novel tool for early diagnosis of thyroid cancer

“…Linear and nonlinear machine-learning algorithms showed similar performance for predicting thyroid nodules malignancy using pathological reports as reference standard [ 23 ]. Recently, a machine-learning algorithm has been proposed to predict malignancy in thyroid FNAs via whole slide images reaching a performance comparable to an expert cytopathologist [ 24 ]. With the development of new mathematical models and the inclusion of novel predictors, the performance for predicting the malignancy of thyroid nodules is expected to increase.…”