Dataset Information

AI diagnosis of Bethesda category IV thyroid nodules.

ABSTRACT: Thyroid nodules are a common disease, and fine needle aspiration cytology (FNAC) is the primary method to assess their malignancy. For the diagnosis of follicular thyroid nodules, however, FNAC has limitations. FNAC can classify them only as Bethesda IV nodules, leaving their exact malignant status and pathological type undetermined. This imprecise diagnosis creates difficulties in selecting the follow-up treatment. In this retrospective study, we collected ultrasound (US) image data of Bethesda IV thyroid nodules from 2006 to 2022 from five hospitals. Then, US image-based artificial intelligence (AI) models were trained to identify the specific category of Bethesda IV thyroid nodules. We tested the models using two independent datasets, and the best AI model achieved an area under the curve (AUC) between 0.90 and 0.95, demonstrating its potential value for clinical application. Our research findings indicate that AI could change the diagnosis and management process of Bethesda IV thyroid nodules.

SUBMITTER: Yao J

PROVIDER: S-EPMC10589877 | biostudies-literature | 2023 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

AI diagnosis of Bethesda category IV thyroid nodules.

Yao Jincao J Zhang Yanming Y Shen Jiafei J Lei Zhikai Z Xiong Jing J Feng Bojian B Li Xiaoxian X Li Wei W Ou Di D Lu Yidan Y Feng Na N Yan Meiying M Chen Jinjie J Chen Liyu L Yang Chen C Wang Liping L Wang Kai K Zhou Jianhua J Liang Ping P Xu Dong D

iScience 20231004 11

Thyroid nodules are a common disease, and fine needle aspiration cytology (FNAC) is the primary method to assess their malignancy. For the diagnosis of follicular thyroid nodules, however, FNAC has limitations. FNAC can classify them only as Bethesda IV nodules, leaving their exact malignant status and pathological type undetermined. This imprecise diagnosis creates difficulties in selecting the follow-up treatment. In this retrospective study, we collected ultrasound (US) image data of Bethesda ...[more]

PMID: 37867955

Similar Datasets

Project description:BackgroundAccording to the latest guidelines, in patients with high-risk nodules with indeterminate cytology, diagnostic lobectomy should be the preferable surgical approach in the absence of factors that suggest a total thyroidectomy.MethodsThis retrospective observational study has as its main aim the evaluation of the cases that underwent surgery, for Bethesda class IV nodules in our iodocarent geographical area. Particular attention was paid to carcinoma incidence, preoperative nodule size, histological characteristics of the neoplasm, surgical approach and eventual need of radiometabolic treatment. A total of 320 patients were included that underwent surgery for Bethesda IV nodules, between January 2010 and December 2020, at the General Surgical Clinic of the University Hospital of Parma, Italy.ResultsA total of 230 total thyroidectomies (71.9%) and 90 lobectomies (28.1%) were performed. Our data showed a strong impact of the 2015 ATA Guidelines on the surgical approach choice, with a progressive propensity towards a conservative approach and an increase of lobectomies from 7.2% to 41.5% after the new guidelines introduction. However, in our sample the percentage of lobectomies remains below 50%; this data is certainly influenced by the number of cases of multinodular pathology, often bilateral, in our geographical area. The nodules malignancy rate resulted 28.8%. Our data showed that increasing size correlated with an increasing malignancy rate (P<0.01), and follicular carcinomas were found to be larger than papillary carcinomas (P<0.001). A statistically significant correlation also emerged between nodule size increase and local/lymphovascular invasion (P<0.05). On the other hand, there was no statistically significant correlation between nodule size and multifocality, and between nodule size and presence of lymph node metastases. Out of the patients where it was possible to find this data, 66% underwent radioiodiometabolic treatment: 59% with papillary carcinoma, and 85% with follicular carcinoma.ConclusionsIn patients with Bethesda IV thyroid nodules, diagnostic lobectomy should be the preferable surgical approach in absence of factors that suggest total thyroidectomy. In our opinion, total thyroidectomy remains the first choice in large nodules (≥4 cm) as these nodules have a high malignancy rate, greater local/lymphovascular invasion and a consequent frequent indication for post-operative radiometabolic treatment.

Project description:ObjectivesThis study aimed to explore the performance of a model based on Chinese Thyroid Imaging Reporting and Data Systems (C-TIRADS), clinical characteristics, and other ultrasound characteristics for the prediction of Bethesda III/IV thyroid nodules before fine needle aspiration (FNA).Materials and methodsA total of 855 thyroid nodules from 810 patients were included. All nodules underwent ultrasound examination before FNA. All nodules were categorized according to the C-TIRADS criteria and classified into two groups, Bethesda III/IV and non-III/IV thyroid nodules, using cytologic diagnosis as the gold standard. The clinical and ultrasonographic characteristics of the nodules in the two groups were compared, and independent predictors of Bethesda III/IV nodules were determined by univariate and multivariate logistic regression analyses, based on which a prediction model was constructed. The predictive efficacy of the model was compared with that of C-TIRADS alone by sensitivity, specificity, and area under the curve (AUC).ResultsOur study found that the C-TIRADS category, homogeneous echotexture, blood flow signal present, and posterior echo unchanged were independent predictors for Bethesda III/IV thyroid nodules. Based on multiple logistic regression, a predictive model was established: Logit (p)= - 4.213 + 0.965 × homogeneous echotexture+ 1.050 × blood flow signal present + 0.473 × posterior echo unchanged+ 2.859 × C-TIRADS 3 + 2.804 × C-TIRADS 4A + 1.824 × C-TIRADS 4B + 0.919 × C-TIRADS 4C. The AUC of the model among all nodules was 0.746 (95%CI: 0.710-0.782), 0.779 (95%CI: 0.730-0.829) among nodules with a diameter (D) > 10mm, and 0.718 (95%CI: 0.667-0.769) among nodules with D ≤ 10mm, which were significantly higher than that of the C-TIRADS alone.ConclusionWe developed a predictive model for Bethesda III/IV thyroid nodules that is better for nodules with D > 10mm FNA operators can choose the optimal puncture strategy based on the prediction results to improve the rate of definitive diagnosis of the first FNA of Bethesda III/IV nodules and thus reduce repeat FNA.

Project description:Background: Analysis of plasma circulating cell-free DNA integrity (cfDI) has emerged as a promising tool in the diagnosis of malignant vs. benign tumors. There is limited data on the role of cfDI in thyroid cancer. The goal of this study was to analyze cfDI as a biomarker of malignancy in patients with cytologically indeterminate thyroid nodules. Methods: The cfDI was measured in the plasma of patients with cytologically indeterminate thyroid nodules. All patients underwent plasma collection within 24-72 h before surgical treatment for thyroid nodules. Additionally, samples were collected from seven patients via the vein draining the thyroid and peripheral vein during surgery. Quantitative real-time PCR was performed on the isolated cell-free DNA using two different primer sets (115 and 247 bp) to amplify consensus ALU sequences. The cfDI was calculated as the ratio of ALU247 to ALU115. Results: All data are given as median [25th-75th percentile]. The study group consisted of 67 patients with 100 nodules, 80.6% (54/67) women, aged 43 [33-60] years. There was no difference in cfDI between 29 patients with benign nodules (0.49 [0.41-0.59]) and 38 patients with malignant lesions (0.45 [0.36-0.57], p = 0.19). There was no difference in cfDI in the vein draining the thyroid (0.47 [0.24-1.05]) and peripheral vein (0.48 [0.36-0.56], p = 0.44). In comparison to thyroid cancer patients, patients with benign nodules were characterized by significantly higher concentrations of ALU115 (1,064 [529-2,960] vs. 411 [27-1,049] ng/ml; p = 0.002) and ALU247 (548 [276-1,894] vs. 170 [17-540] ng/ml; p = 0.0005), most likely because benign tumors were larger (3, [1.8-4.1 cm]) than malignant lesions (0.7 [0.23-1.45], p < 0.0001). Women had significantly lower cfDI (0.45 [0.27-0.54]) than men (0.56 [0.44-0.8], p = 0.011). Conclusion: The cfDI measured in the vein draining the thyroid is similar to the cfDI measured in the antecubital vein, validating cfDI measurements by peripheral liquid biopsy. Analysis of cfDI needs to be stratified by patients gender. In contrast to its diagnostic utility in aggressive cancers, cfDI has limited utility as a biomarker of malignancy in cytologically indeterminate thyroid nodules.

Dataset Information

AI diagnosis of Bethesda category IV thyroid nodules.

Publications

AI diagnosis of Bethesda category IV thyroid nodules.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets