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

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Inyoung Youn ◽  
Eunjung Lee ◽  
Jung Hyun Yoon ◽  
Hye Sun Lee ◽  
Mi-Ri Kwon ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Diagnostic Performance ◽  
Thyroid Nodules ◽  
Interobserver Variability ◽  
Needle Aspiration ◽  
Deep Convolutional Neural Network ◽  
Fine Needle ◽  
Experience Levels ◽  
Undetermined Significance

AbstractTo 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.

scholarly journals Using the Deep Convolutional Neural Network to Evaluate Thyroid Nodules With Atypia of Undetermined Significance/follicular Lesion of Undetermined Significance Cytology: Multicenter Study

2021 ◽  
Author(s):  
Inyoung Youn ◽  
Eunjung Lee ◽  
Jung Hyun Yoon ◽  
Hye Sun Lee ◽  
Mi-Ri Kwon ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Diagnostic Performance ◽  
Thyroid Nodules ◽  
Interobserver Variability ◽  
Needle Aspiration ◽  
Deep Convolutional Neural Network ◽  
Fine Needle ◽  
Experience Levels ◽  
Undetermined Significance

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 ≥ 1cm 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.

scholarly journals Comparison of Diagnostic Performance in Thyroid Nodules on US: Deep Convolutional Neural Network Models vs Endocrinologists With Various Experiences

2021 ◽  
Vol 5 (Supplement_1) ◽  
pp. A859-A859
Author(s):  
Sunyoung Kang ◽  
Eunjung Lee ◽  
Yoo Hyung Kim ◽  
Seul Ki Kwon ◽  
Kyong Yeun Jung ◽  
...  
Keyword(s):  
Neural Network ◽  
Thyroid Cancer ◽  
Convolutional Neural Network ◽  
Diagnostic Performance ◽  
Thyroid Nodules ◽  
Deep Convolutional Neural Network ◽  
University Hospital ◽  
Neural Network Models ◽  
Maximal Diameter ◽  
Lower Accuracy

Abstract Objectives: To diagnose thyroid cancer, ultrasonography is a primary tool, but diagnostic accuracy varies according to the proficiency of clinicians. The aim of this study was to compare diagnostic performance between deep convolutional neural network (CNN) models and endocrinologist with various experiences. Methods: Patients who underwent fine needle aspiration at endocrinology department in Seoul National University Hospital, between April 2014 and June 2019, were reviewed. Among them, thyroid nodules which were pathologically confirmed by surgery and maximal diameter greater than 1cm were included. Ultrasonography images of thyroid nodules were reviewed by 13 endocrinologists with various experiences: 0 month (E0, n=8), 1 year (E1, n=2), and >5 years (E5, n=3). Results: Of total 451 thyroid nodules, 66.5% was diagnosed as cancer and 83.7% was papillary thyroid cancer (PTC). Sensitivity and specificity of CNN were 85.3% and 63.6%, respectively, and its area under the curve (AUC) was 0.855. Compared to CNN, mean accuracy of E0 group was significantly lower (Accuracy 68.7% vs 78.0%, P <0.001), and after CNN-assistance, that of E0 was significantly improved (68.7% [before] vs 73.93% [after], P = 0.008). E1 and E5 groups showed similar diagnostic performance to CNN, and CNN-assistance did not change it. Next, subgroup analysis was performed according to the histologic subtypes. AUC of CNN in PTC (0.925) was much higher than that of other cancers including FTC (0.529). Interestingly, CNN-assistance significantly improved diagnostic performance for PTC not only in beginners (E0), but also a subset of experienced endocrinologist (E1 and E5). Conclusions: CNN has good diagnostic performance in the diagnosis of PTC. Endocrinologist with lower experience in ultrasonography, CNN-assistance is beneficial for improving diagnostic performance especially in PTC.

scholarly journals Punção Aspirativa de Nódulos da Tiroide: Vale a Pena Repetir?

2017 ◽  
Vol 30 (6) ◽  
pp. 472
Author(s):  
Vera Fernandes ◽  
Tânia Pereira ◽  
Catarina Eloy
Keyword(s):  
Fine Needle Aspiration ◽  
Thyroid Nodules ◽  
Significant Proportion ◽  
Cost Effective ◽  
Needle Aspiration ◽  
Fine Needle ◽  
High Concordance ◽  
Benign Nodules ◽  
Cytology Result ◽  
Undetermined Significance

Introduction: The fine-needle aspiration has a significant role in assessing the malignancy risk of thyroid nodules. There is uncertainty regarding the value of repeat fine-needle aspiration in benign nodules. This study aims to evaluate the concordance of results in consecutive fine-needle aspiration and to study the relevance of repetition in benign results.Material and Methods: Retrospective study of the 4800 thyroid nodules fine-needle aspiration held in Instituto de Patologia e Imunologia Molecular da Universidade do Porto between January 1, 2014 and May 2, 2016. Of the initial sample, we selected the repeated fine-needle aspiration on the same nodule.Results: The first fine-needle aspiration result of the 309 nodules underwent revaluation was non-diagnostic in 103 (33.3%), benign in 120 (38.8%) and atypia/follicular lesion of undetermined significance in 86 (27.8%). The agreement between the first and second fine-needle aspiration was significantly higher in cases with an initial benign result (benign: 85.8%, non-diagnostic: 27.2% and atypia/ follicular lesion of undetermined significance: 17.4%, p < 0.005). The fine-needle aspiration repeating motifs in initially benign nodules (n = 78) were repetition suggestion in 58, nodule growth in 17 and suspicious ultrasonographic features in 3.Discussion: The fine-needle aspiration repetition in nodules with initial non-diagnostic and atypia/follicular lesion of undetermined significance result changed the initial diagnosis in a significant proportion of patients, modifying their therapeutic approach. The high concordance of results in initially benign nodules makes fine-needle aspiration repetition not cost-effective in most cases.Conclusion: The fine-needle aspiration should be repeated when the initial cytology result is non-diagnostic or atypia/follicular lesion of undetermined significance.

scholarly journals Surgical Outcome of Thyroid Nodules with Atypia of Undetermined Significance and Follicular Lesion of Undetermined Significance in Fine Needle Aspiration Biopsy

2017 ◽  
Vol 9 (3) ◽  
pp. 100-103
Author(s):  
Saad Alqahtani ◽  
Saif Alsobhi ◽  
Riyadh I Alsalloum ◽  
Saleh N Najjar ◽  
Hindi N Al-Hindi
Keyword(s):  
Fine Needle Aspiration ◽  
Surgical Outcome ◽  
Thyroid Nodules ◽  
Fine Needle Aspiration Biopsy ◽  
Needle Aspiration ◽  
Aspiration Biopsy ◽  
Fine Needle ◽  
Risk Of Malignancy ◽  
Needle Aspiration Biopsy ◽  
Undetermined Significance

ABSTRACT Aim To correlate selected clinical and ultrasonographic (US) characteristics with the final histopathological diagnosis in patients with atypia of undetermined significance (AUS) and follicular lesion of undetermined significance (FLUS), and whether this information can be used in planning the surgical approach. Materials and methods It is a retrospective study including the operated cases of AUS/FLUS from 2011 to 2014 treated at one center. Results This cohort included 87 women and 28 men. To test for independence between categorical variables, the chi-square test was used. There was no significant correlation between age or US variables and final pathological diagnosis. However, final diagnosis of malignancy was higher in men compared with women (64.3 and 41.4% respectively; p = 0.035). Furthermore, a significant association between the diagnosis of repeated fine needle aspiration biopsy (FNAB) and the final pathological diagnosis was noted (benign vs malignant, p = 0.005). Conclusion The FNAB has a significant role in the assessment of thyroid nodules. Our results showed no correlation between age, US variables, and the risk of malignancy. Male gender is associated with higher risk of malignancy. Clinical significance Determining the risk of malignancy and prediction of surgical outcome may help triaging cases for repeat FNA or proceeding to surgery. How to cite this article Alqahtani S, Alsobhi S, Alsalloum RI, Najjar SN, Al-Hindi HN. Surgical Outcome of Thyroid Nodules with Atypia of Undetermined Significance and Follicular Lesion of Undetermined Significance in Fine Needle Aspiration Biopsy. World J Endoc Surg 2017;9(3):100-103.

Core-needle biopsy versus repeat fine-needle aspiration for thyroid nodules initially read as atypia/follicular lesion of undetermined significance

Head & Neck ◽  
2016 ◽  
Vol 39 (2) ◽  
pp. 361-369 ◽  
Author(s):  
Young Jun Choi ◽  
Jung Hwan Baek ◽  
Chong Hyun Suh ◽  
Woo Hyun Shim ◽  
Boseul Jeong ◽  
...  
Keyword(s):  
Fine Needle Aspiration ◽  
Core Needle Biopsy ◽  
Needle Biopsy ◽  
Thyroid Nodules ◽  
Needle Aspiration ◽  
Core Needle ◽  
Fine Needle ◽  
Undetermined Significance
Sign in / Sign up

Export Citation Format

Share Document