Diagnostic Efficacy of Ultrasound, Cytology, and BRAFV600E Mutation Analysis and Their Combined Use in Thyroid Nodule Screening for Papillary Thyroid Microcarcinoma

US of thyroid nodules: can AI-assisted diagnostic system compete with fine needle aspiration?

OBJECTIVES

Artificial intelligence (AI) systems can diagnose thyroid nodules with similar or better performance than radiologists. Little is known about how this performance compares with that achieved through fine needle aspiration (FNA). This study aims to compare the diagnostic yields of FNA cytopathology alone and combined with BRAFV600E mutation analysis and an AI diagnostic system.

METHODS

The ultrasound images of 637 thyroid nodules were collected in three hospitals. The diagnostic efficacies of an AI diagnostic system, FNA-based cytopathology, and BRAFV600E mutation analysis were evaluated in terms of sensitivity, specificity, accuracy, and the κ coefficient with respect to the gold standard, defined by postsurgical pathology and consistent benign outcomes from two combined FNA and mutation analysis examinations performed with a half-year interval.

RESULTS

The malignancy threshold for the AI system was selected according to the Youden index from a retrospective cohort of 346 nodules and then applied to a prospective cohort of 291 nodules. The combination of FNA cytopathology according to the Bethesda criteria and BRAFV600E mutation analysis showed no significant difference from the AI system in terms of accuracy for either cohort in our multicenter study. In addition, for 45 included indeterminate Bethesda category III and IV nodules, the accuracy, sensitivity, and specificity of the AI system were 84.44%, 95.45%, and 73.91%, respectively.

CONCLUSIONS

The AI diagnostic system showed similar diagnostic performance to FNA cytopathology combined with BRAFV600E mutation analysis. Given its advantages in terms of operability, time efficiency, non-invasiveness, and the wide availability of ultrasonography, it provides a new alternative for thyroid nodule diagnosis.

CLINICAL RELEVANCE STATEMENT

Thyroid ultrasonic artificial intelligence shows statistically equivalent performance for thyroid nodule diagnosis to FNA cytopathology combined with BRAFV600E mutation analysis. It can be widely applied in hospitals and clinics to assist radiologists in thyroid nodule screening and is expected to reduce the need for relatively invasive FNA biopsies.

KEY POINTS

• In a retrospective cohort of 346 nodules, the evaluated artificial intelligence (AI) system did not significantly differ from fine needle aspiration (FNA) cytopathology alone and combined with gene mutation analysis in accuracy. • In a prospective multicenter cohort of 291 nodules, the accuracy of the AI diagnostic system was not significantly different from that of FNA cytopathology either alone or combined with gene mutation analysis. • For 45 indeterminate Bethesda category III and IV nodules, the AI system did not perform significantly differently from BRAFV600E mutation analysis.

Age and BRAFV600E Mutation Stratified Patients with Cytologically Benign Thyroid Nodules

Purpose

Our objective was to evaluate the diagnostic performance of BRAFV600E mutation for malignant, and to identify clinical characteristics associated with positive BRAFV600E mutation in low-risk cytological and ultrasound diagnostic thyroid nodules. This aims to identify patients who may benefit from BRAFV600E mutation testing and subsequent surgical intervention.

Patients and Methods

We analysis the clinical characteristics correlated with BRAFV600E mutation in our detection cohort, including 204 patients with 217 thyroid nodules, and separate analyses were performed in 103 thyroid nodules with benign cytological result. Signaling pathway and immune response associated with age and BRAFV600E mutation status were also evaluated in Asian patients with thyroid cancer from the Cancer Genome Atlas (TCGA) dataset.

Results

The positive BRAFV600E mutation was significantly associated with higher Ultrasound (US) classification (p<0.001) and fine-needle aspiration (FNA) categories (p<0.001). BRAFV600E mutation as a risk factor for malignancy, showing the optimal diagnostic efficacy for malignancy combined with FNA categories, with the AUC was 0.923. Otherwise, BRAFV600E mutation is a risk factor in screening malignancy in low-risk FNA and US classification, which is significant correlation with patients age. Patients over 50 years old exhibiting a higher percentage of positive BRAFV600E mutation when both ultrasound and FNA results indicate benign conditions, with higher risk of malignancy.

Conclusion

BRAFV600E mutation is an accurate adjunctive diagnostic marker on FNA to screen malignancy. In low risk of both ultrasound and FNA results, the positive BRAFV600E was significant increased in patients over 50 years old, which have higher risk of malignancy. Thus, the BRAFV600E mutation detection and further surgery should be strengthened in older patients with benign cytological and US results thyroid nodules.

Diagnostic Value and Challenges of BRAF V600E Molecular Testing and Thyroid Fine-Needle Aspiration Cytology: A Retrospective Study from a Tertiary Institution in Southern Hunan Province, China

INTRODUCTION

Combined thyroid fine-needle aspiration (FNA) cytology and valine-to-glutamate substitution at codon 600 of B-Raf proto-oncogene, serine/threonine kinase (BRAF V600E) mutation detection are procedures used for diagnosing thyroid nodules in many Chinese tertiary institutions. This retrospective study at our institution aimed to explore the effectiveness and challenges of the combined approach in diagnosing thyroid nodules and the correlation between BRAF V600E mutation status and behavior of papillary thyroid carcinoma.

METHODS

Thyroid FNA cytology and BRAF V600E mutation detection results were reviewed between November 2020 and July 2022. A total of 623 patients, each of whom underwent thyroidectomy and final pathological examination after FNA cytology diagnosis, were included in the study. The relationship between the BRAF V600E mutational status and pathological parameters was analyzed using the χ2 test. The effectiveness and challenges of FNA cytology alone and the combined procedure were also evaluated based on the final pathology.

RESULTS

Of 623 patients, 591 were diagnosed with papillary thyroid carcinoma (PTC), of which 456 were positive for the BRAF V600E mutation. It demonstrated near-perfect specificity for identifying PTC, and its incidence rate showed an age-specific curve with an inverted U-shaped distribution. The final pathological examination showed that the combined procedure had a higher sensitivity (83.91%) than FNA cytology alone (63.45%) for distinguishing PTC from other lesions (p < 0.001). Mutational status was associated with a larger maximum tumor diameter (p = 0.003) and a tendency of capsular invasion (p = 0.0542) but possibly unrelated to central lymph node metastasis (p = 0.1846). Nodular goiters accounted for most benign entities initially designated as Bethesda categories III-V.

CONCLUSION

BRAF V600E mutational analysis complements cytopathology and improves the PTC detection rate in FNA cytology samples due to the high prevalence of the mutation in China. BRAF V600E mutation does not show a statistical correlation with tumor aggressiveness. Morphological pitfalls such as histocyte aggregation, cystic-lining cells in nodular goiters, and oncocytes in Hashimoto's thyroiditis, were overwhelmingly found in BRAF V600E-negative specimens.

BRAF p.V600E genetic testing based on ultrasound-guided fine-needle biopsy improves the malignancy rate in thyroid surgery: our single-center experience in the past 10 years

Purpose

Ultrasound-guided fine-needle aspiration biopsy (UG-FNAB) was implemented in Qilu Hospital of Shandong University in 2015 as a preoperative diagnostic method for thyroid surgery. BRAF p.V600E genetic testing was implemented in 2019. This study evaluated the impact of these two tests on the malignancy rate in patients undergoing thyroidectomy.

Methods

A total of 19,496 patients were included in the study. We retrospectively collected data from patients undergoing thyroid surgery in the Hospital Information System (HIS) of Qilu Hospital of Shandong University from January 2012 to December 2021. Meanwhile, data of FNAB, UG-FNAB, and BRAF p.V600E genetic testing were collected. Differences in means among groups were analyzed via one-way ANOVA, and differences in frequencies were analyzed via Pearson’s chi-squared test.

Results

In this study, the 10-year period was divided into three stages, with the implementation of UG-FNAB in 2015 and that of BRAF p.V600E genetic testing in 2019 as dividing lines. The malignancy rate in thyroid surgery increased significantly during these three stages (48.06% vs. 73.47% vs. 88.17%; P < 0.001). In the same period (May 2019 to December 2021), the malignancy rate in thyroid surgery was significantly different between the Non-FNAB, UG-FNAB, and UG-FNAB-BRAF groups (78.87% vs. 95.63% vs. 98.32%; P < 0.001).

Conclusions

The successful implementation of UG-FNAB and BRAF p.V600E genetic testing improved the malignancy rate in thyroid surgery and reduced unnecessary diagnostic surgery for benign and marginal lesions. It can, therefore, provide a clinical reference for other hospitals.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00432-022-04235-3.