Ultrasound characteristics of follicular and parafollicular thyroid neoplasms: diagnostic performance of artificial neural network.

IF 1.9 Q3 ENDOCRINOLOGY & METABOLISM
Michael Cordes, Theresa Ida Götz, Stephan Coerper, Torsten Kuwert, Christian Schmidkonz
{"title":"Ultrasound characteristics of follicular and parafollicular thyroid neoplasms: diagnostic performance of artificial neural network.","authors":"Michael Cordes,&nbsp;Theresa Ida Götz,&nbsp;Stephan Coerper,&nbsp;Torsten Kuwert,&nbsp;Christian Schmidkonz","doi":"10.1186/s13044-023-00168-2","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Ultrasound is the first-line imaging modality for detection and classification of thyroid nodules. Certain features observable by ultrasound have recently been equated with potential malignancy. This retrospective cohort study was conducted to test the hypothesis that radiomics of the four categorical divisions (medullary [MTC], papillary [PTC], or follicular [FTC] carcinoma and follicular thyroid adenoma [FTA]) demonstrate distinctive sonographic characteristics. Using an artificial neural network model for proof of concept, these sonographic features served as input.</p><p><strong>Methods: </strong>A total of 148 patients were enrolled for study, all with confirmed thyroid pathology in one of the four named categories. Preoperative ultrasound profiles were obtained via standardized protocols. The neural network consisted of seven input neurons; three hidden layers with 50, 250, and 100 neurons, respectively; and one output layer.</p><p><strong>Results: </strong>Radiomics of contour, structure, and calcifications differed significantly according to nodule type (p = 0.025, p = 0.032, and p = 0.0002, respectively). Levels of accuracy shown by artificial neural network analysis in discriminating among categories ranged from 0.59 to 0.98 (95% confidence interval [CI]: 0.57-0.99), with positive and negative predictive ranges of 0.41-0.99 and 0.78-0.97, respectively.</p><p><strong>Conclusions: </strong>Our data indicate that some MTCs, PTCs, FTCs, and FTAs have distinctive sonographic characteristics. However, a significant overlap of these characteristics may impede an explicit classification. Further prospective investigations involving larger patient and nodule numbers and multicenter access should be pursued to determine if neural networks of this sort are beneficial, helping to classify neoplasms of the thyroid gland.</p>","PeriodicalId":39048,"journal":{"name":"Thyroid Research","volume":"16 1","pages":"25"},"PeriodicalIF":1.9000,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10463771/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Thyroid Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1186/s13044-023-00168-2","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Ultrasound is the first-line imaging modality for detection and classification of thyroid nodules. Certain features observable by ultrasound have recently been equated with potential malignancy. This retrospective cohort study was conducted to test the hypothesis that radiomics of the four categorical divisions (medullary [MTC], papillary [PTC], or follicular [FTC] carcinoma and follicular thyroid adenoma [FTA]) demonstrate distinctive sonographic characteristics. Using an artificial neural network model for proof of concept, these sonographic features served as input.

Methods: A total of 148 patients were enrolled for study, all with confirmed thyroid pathology in one of the four named categories. Preoperative ultrasound profiles were obtained via standardized protocols. The neural network consisted of seven input neurons; three hidden layers with 50, 250, and 100 neurons, respectively; and one output layer.

Results: Radiomics of contour, structure, and calcifications differed significantly according to nodule type (p = 0.025, p = 0.032, and p = 0.0002, respectively). Levels of accuracy shown by artificial neural network analysis in discriminating among categories ranged from 0.59 to 0.98 (95% confidence interval [CI]: 0.57-0.99), with positive and negative predictive ranges of 0.41-0.99 and 0.78-0.97, respectively.

Conclusions: Our data indicate that some MTCs, PTCs, FTCs, and FTAs have distinctive sonographic characteristics. However, a significant overlap of these characteristics may impede an explicit classification. Further prospective investigations involving larger patient and nodule numbers and multicenter access should be pursued to determine if neural networks of this sort are beneficial, helping to classify neoplasms of the thyroid gland.

Abstract Image

Abstract Image

Abstract Image

甲状腺滤泡及滤泡旁肿瘤的超声特征:人工神经网络的诊断性能。
背景:超声是甲状腺结节检测和分类的一线影像学手段。超声观察到的某些特征最近被认为是潜在的恶性肿瘤。本回顾性队列研究旨在验证四种类型(髓样癌(MTC)、乳头状癌(PTC)、滤泡癌(FTC)和滤泡甲状腺腺瘤(FTA))的放射组学表现出不同超声特征的假设。使用人工神经网络模型进行概念验证,这些超声特征作为输入。方法:共纳入148例患者进行研究,所有患者均确诊为四类甲状腺病理之一。术前超声资料通过标准化方案获得。该神经网络由7个输入神经元组成;三个隐藏层,分别有50、250和100个神经元;还有一个输出层。结果:不同类型结节的轮廓、结构、钙化放射组学差异有统计学意义(p = 0.025, p = 0.032, p = 0.0002)。人工神经网络分析的分类判别准确率范围为0.59 ~ 0.98(95%置信区间[CI]: 0.57 ~ 0.99),阳性预测范围为0.41 ~ 0.99,阴性预测范围为0.78 ~ 0.97。结论:我们的数据表明,一些MTCs、ptc、FTCs和FTAs具有独特的超声特征。然而,这些特征的显著重叠可能会妨碍明确的分类。进一步的前瞻性研究涉及更多的患者和结节数量和多中心访问,以确定这种类型的神经网络是否有益,有助于甲状腺肿瘤的分类。
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
Thyroid Research
Thyroid Research Medicine-Endocrinology, Diabetes and Metabolism
CiteScore
3.10
自引率
4.50%
发文量
21
审稿时长
8 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信