Ultrasound-based radiomics to predict the volume reduction rate of benign thyroid nodules after microwave ablation.

IF 3 3区医学 Q2 ENDOCRINOLOGY & METABOLISM

Endocrine Pub Date : 2024-12-05 DOI:10.1007/s12020-024-04125-3

Fang Chen, Yuxiu Gao, Qingwen Xue, Xiaoyan Niu, Xiaojuan Zhang, Yichen Zang, Hui Zhang, Shuao Li, Cheng Zhao

{"title":"Ultrasound-based radiomics to predict the volume reduction rate of benign thyroid nodules after microwave ablation.","authors":"Fang Chen, Yuxiu Gao, Qingwen Xue, Xiaoyan Niu, Xiaojuan Zhang, Yichen Zang, Hui Zhang, Shuao Li, Cheng Zhao","doi":"10.1007/s12020-024-04125-3","DOIUrl":null,"url":null,"abstract":"Objective: To evaluate the predictive power of ultrasound-based radiomics models for benign thyroid nodules with a volume reduction rate (VRR) of < or ≥75% at 12 months after microwave ablation.Methods: A retrospective study was conducted on 194 individuals with benign thyroid nodules who received ultrasound-guided microwave ablation between November 2019 and June 2023. The clinical and ultrasound features, including age, gender, volume, echogenicity, duration of ablation, and so on were analysed by t-test or chi-square test. Radiomics features were extracted from longitudinal and transverse ultrasound images of the nodules. The features were selected using methods such as least absolute shrinkage and selection operator (LASSO). Radiomics models were established using longitudinal, transverse, and longitudinal + transverse ultrasound images to predict the VRR of benign thyroid nodules after ablation. Decision curve analysis (DCA) and receiver operating characteristic (ROC) curve analysis were used to assess the models' performance.Results: At 12 months following ablation, the VRR of the nodules was 77.8 ± 19.4% (7.4-98.8%). Statistical analysis revealed that the duration of ablation and the proportion of liquid extracted were significantly correlated with the 12-month VRR (P <0.05). In the radiomics models, Logistic Regression (LR) performed the best. In the training cohorts, the area under the curve (AUC) for the longitudinal, transverse, and combined groups were 0.935, 0.800, and 0.937. The AUC values in the test cohort were 0.820, 0.844, and 0.917.Conclusion: The radiomics models established based on pre-ablation ultrasound images showed good predictive efficacy for the VRR of nodules at 12 months following ablation. The predictive efficacy is best in the combined group. With the models, we can preoperatively predict patients' prognoses and thereby determine whether to proceed with ablation therapy.","PeriodicalId":49211,"journal":{"name":"Endocrine","volume":" ","pages":""},"PeriodicalIF":3.0000,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Endocrine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s12020-024-04125-3","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}

引用次数: 0

Abstract

Objective: To evaluate the predictive power of ultrasound-based radiomics models for benign thyroid nodules with a volume reduction rate (VRR) of < or ≥75% at 12 months after microwave ablation.

Methods: A retrospective study was conducted on 194 individuals with benign thyroid nodules who received ultrasound-guided microwave ablation between November 2019 and June 2023. The clinical and ultrasound features, including age, gender, volume, echogenicity, duration of ablation, and so on were analysed by t-test or chi-square test. Radiomics features were extracted from longitudinal and transverse ultrasound images of the nodules. The features were selected using methods such as least absolute shrinkage and selection operator (LASSO). Radiomics models were established using longitudinal, transverse, and longitudinal + transverse ultrasound images to predict the VRR of benign thyroid nodules after ablation. Decision curve analysis (DCA) and receiver operating characteristic (ROC) curve analysis were used to assess the models' performance.

Results: At 12 months following ablation, the VRR of the nodules was 77.8 ± 19.4% (7.4-98.8%). Statistical analysis revealed that the duration of ablation and the proportion of liquid extracted were significantly correlated with the 12-month VRR (P <0.05). In the radiomics models, Logistic Regression (LR) performed the best. In the training cohorts, the area under the curve (AUC) for the longitudinal, transverse, and combined groups were 0.935, 0.800, and 0.937. The AUC values in the test cohort were 0.820, 0.844, and 0.917.

Conclusion: The radiomics models established based on pre-ablation ultrasound images showed good predictive efficacy for the VRR of nodules at 12 months following ablation. The predictive efficacy is best in the combined group. With the models, we can preoperatively predict patients' prognoses and thereby determine whether to proceed with ablation therapy.

查看原文本刊更多论文

超声放射组学预测微波消融后良性甲状腺结节体积缩小率。

目的：评价超声放射组学模型对微波消融后12个月体积缩小率(VRR) <或≥75%的良性甲状腺结节的预测能力。方法：对2019年11月至2023年6月期间接受超声引导微波消融治疗的194例良性甲状腺结节患者进行回顾性研究。采用t检验或卡方检验分析年龄、性别、体积、回声强度、消融时间等临床及超声特征。从结节的纵向和横向超声图像中提取放射组学特征。使用最小绝对收缩和选择算子（LASSO）等方法选择特征。采用纵向、横向、纵向+横向超声图像建立放射组学模型，预测消融后良性甲状腺结节的VRR。采用决策曲线分析（DCA）和受试者工作特征（ROC）曲线分析来评估模型的性能。结果：消融后12个月，结节的VRR为77.8±19.4%（7.4-98.8%）。结论：基于消融前超声图像建立的放射组学模型对消融后12个月结节的VRR有较好的预测效果。联合用药组预测疗效最好。有了这些模型，我们可以术前预测患者的预后，从而决定是否继续进行消融治疗。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Endocrine ENDOCRINOLOGY & METABOLISM-

CiteScore

6.50

自引率

5.40%

发文量

295

审稿时长

1.5 months

期刊介绍： Well-established as a major journal in today’s rapidly advancing experimental and clinical research areas, Endocrine publishes original articles devoted to basic (including molecular, cellular and physiological studies), translational and clinical research in all the different fields of endocrinology and metabolism. Articles will be accepted based on peer-reviews, priority, and editorial decision. Invited reviews, mini-reviews and viewpoints on relevant pathophysiological and clinical topics, as well as Editorials on articles appearing in the Journal, are published. Unsolicited Editorials will be evaluated by the editorial team. Outcomes of scientific meetings, as well as guidelines and position statements, may be submitted. The Journal also considers special feature articles in the field of endocrine genetics and epigenetics, as well as articles devoted to novel methods and techniques in endocrinology. Endocrine covers controversial, clinical endocrine issues. Meta-analyses on endocrine and metabolic topics are also accepted. Descriptions of single clinical cases and/or small patients studies are not published unless of exceptional interest. However, reports of novel imaging studies and endocrine side effects in single patients may be considered. Research letters and letters to the editor related or unrelated to recently published articles can be submitted. Endocrine covers leading topics in endocrinology such as neuroendocrinology, pituitary and hypothalamic peptides, thyroid physiological and clinical aspects, bone and mineral metabolism and osteoporosis, obesity, lipid and energy metabolism and food intake control, insulin, Type 1 and Type 2 diabetes, hormones of male and female reproduction, adrenal diseases pediatric and geriatric endocrinology, endocrine hypertension and endocrine oncology.