Diagnosing thyroid nodules with atypia of undetermined significance/follicular lesion of undetermined significance cytology with the deep convolutional neural network

Inyoung Youn,Jung Hyun Yoon,Do Joon Park,Sun Wook Cho,Hye Sun Lee,Mi-Ri Kwon,Young Joo Park,Sunyoung Kang,Seul Ki Kwon,Eunjung Lee,Juhee Moon,Jin Young Kwak,Kyong Yeun Jung

doi:10.1038/s41598-021-99622-0

Abstract

To compare the diagnostic performances of physicians and a deep convolutional neural network (CNN) predicting malignancy with ultrasonography images of thyroid nodules with atypia of undetermined significance (AUS)/follicular lesion of undetermined significance (FLUS) results on fine-needle aspiration (FNA). This study included 202 patients with 202 nodules ≥ 1 cm AUS/FLUS on FNA, and underwent surgery in one of 3 different institutions. Diagnostic performances were compared between 8 physicians (4 radiologists, 4 endocrinologists) with varying experience levels and CNN, and AUS/FLUS subgroups were analyzed. Interobserver variability was assessed among the 8 physicians. Of the 202 nodules, 158 were AUS, and 44 were FLUS; 86 were benign, and 116 were malignant. The area under the curves (AUCs) of the 8 physicians and CNN were 0.680–0.722 and 0.666, without significant differences (P > 0.05). In the subgroup analysis, the AUCs for the 8 physicians and CNN were 0.657–0.768 and 0.652 for AUS, 0.469–0.674 and 0.622 for FLUS. Interobserver agreements were moderate (k = 0.543), substantial (k = 0.652), and moderate (k = 0.455) among the 8 physicians, 4 radiologists, and 4 endocrinologists. For thyroid nodules with AUS/FLUS cytology, the diagnostic performance of CNN to differentiate malignancy with US images was comparable to that of physicians with variable experience levels.

Highlights

To compare the diagnostic performances of physicians and a deep convolutional neural network (CNN) predicting malignancy with ultrasonography images of thyroid nodules with atypia of undetermined significance (AUS)/follicular lesion of undetermined significance (FLUS) results on fine-needle aspiration (FNA)
The AUS/FLUS cytology includes a heterogeneous and broad spectrum of diagnoses which contain more pronounced cells with architectural and/or nuclear atypia than benign lesions but not enough of these cells to be considered malignant, and have a malignancy risk of 6–18% after NIFTP is removed which can make it difficult for clinicians to reach a decision on further management[2]
FNA/CNB or molecular tests as supplementary evaluation methods instead of proceeding to surgery; even results from repeated FNA show the same cytology in 10–30% of the nodules[15]

Summary

Introduction

To compare the diagnostic performances of physicians and a deep convolutional neural network (CNN) predicting malignancy with ultrasonography images of thyroid nodules with atypia of undetermined significance (AUS)/follicular lesion of undetermined significance (FLUS) results on fine-needle aspiration (FNA). Diagnostic performances were compared between 8 physicians (4 radiologists, 4 endocrinologists) with varying experience levels and CNN, and AUS/FLUS subgroups were analyzed. For thyroid nodules with AUS/FLUS cytology, the diagnostic performance of CNN to differentiate malignancy with US images was comparable to that of physicians with variable experience levels. The nodules with Bethesda class III lesions, otherwise known as atypia of undetermined significance (AUS) or follicular lesion of undetermined significance (FLUS), have a malignancy risk of 6–18%, and management plans vary widely from clinical observation, US follow up, repeat FNA or core needle biopsy, molecular test to thyroid s urgery[2,3]. Stratify the risk of Bethesda class III lesions[3,4], US assessment is limited in application due to its inherent limitations of poorly reproducible tests[5]

Objectives

Methods

Results

Conclusion