RESUMO
The purpose of this study is to evaluate the potential synergic effect of BRAFV600E mutation and multifocality on central lymph nodes metastasis (CLNM) in the patients with unilateral papillary thyroid carcinoma (PTC). We enrolled 413 patients with unilateral PTCs who accepted prophylactic unilateral or bilateral central lymph node dissection (LND). Univariate and multivariate analyses were made to determine the association between related factors and CLNM. Then, all patients were divided into 4 groups based on their status of BRAFV600E mutation and multifocality. Relative excess risk of interaction (RERI), attributable proportion (AP) of interaction and synergy index (SI) were applied to evaluate the interactive effect of these two factors on CLNM. Results showed that BRAFV600E mutation and multifocality were independent risk factors for CLNM. A further study revealed that unilateral PTCs accompanying multifocality with BRAFV600E mutation had the highest incidence of CLNM compared with other subgroups. Besides, RERI was 4.323 (95% CI = 1.276-7.369), AP was 0.523 (95% CI = 0.364-0.682) and SI was 2.469 (95% CI = 1.607 to 3.794), indicating a significant additive interaction of BRAFV600E mutation and multifocality on CLNM. The present study has confirmed that BRAFV600E mutation and multifocality are risk factors for CLNM in unilateral PTC. Additionally, unilateral PTC patients accompanying multifocality with BRAFV600E mutation may have an increased risk of CLNM in clinically negative CLNM.
Assuntos
Carcinoma Papilar/secundário , Predisposição Genética para Doença , Mutação , Proteínas Proto-Oncogênicas B-raf/genética , Neoplasias da Glândula Tireoide/genética , Adulto , Substituição de Aminoácidos , Institutos de Câncer , Carcinoma Papilar/genética , Carcinoma Papilar/metabolismo , Carcinoma Papilar/patologia , Carcinoma Papilar/cirurgia , China , Estudos Transversais , Análise Mutacional de DNA , Éxons , Feminino , Estudos de Associação Genética , Humanos , Linfonodos/metabolismo , Linfonodos/patologia , Linfonodos/cirurgia , Metástase Linfática , Masculino , Pessoa de Meia-Idade , Proteínas Proto-Oncogênicas B-raf/química , Proteínas Proto-Oncogênicas B-raf/metabolismo , Estudos Retrospectivos , Câncer Papilífero da Tireoide , Glândula Tireoide/metabolismo , Glândula Tireoide/patologia , Glândula Tireoide/cirurgia , Neoplasias da Glândula Tireoide/metabolismo , Neoplasias da Glândula Tireoide/patologia , Neoplasias da Glândula Tireoide/cirurgia , Carga TumoralRESUMO
Background: Both calcification and colloid in thyroid nodules are reflected as echogenic foci in ultrasound images. However, calcification and colloid have significantly different probabilities of malignancy. We explored the performance of a deep learning (DL) model in distinguishing the echogenic foci of thyroid nodules as calcification or colloid. Methods: We conducted a retrospective study using ultrasound image sets. The DL model was trained and tested on 30,388 images of 1127 nodules. All nodules were pathologically confirmed. The area under the receiver-operator characteristic curve (AUC) was employed as the primary evaluation index. Results: The YoloV5 (You Only Look Once Version 5) transfer learning model for thyroid nodules based on DL detection showed that the average sensitivity, specificity, and accuracy of distinguishing echogenic foci in the test 1 group (n = 192) was 78.41%, 91.36%, and 77.81%, respectively. The average sensitivity, specificity, and accuracy of the three radiologists were 51.14%, 82.58%, and 61.29%, respectively. The average sensitivity, specificity, and accuracy of distinguishing small echogenic foci in the test 2 group (n = 58) was 70.17%, 77.14%, and 73.33%, respectively. Correspondingly, the average sensitivity, specificity, and accuracy of the radiologists were 57.69%, 63.29%, and 59.38%. Conclusions: The study demonstrated that DL performed far better than radiologists in distinguishing echogenic foci of thyroid nodules as calcifications or colloid.