Value of Artificial Intelligence in Improving the Accuracy of Diagnosing TI-RADS Category 4 Nodules

甲状腺结节 人工智能 接收机工作特性 卷积神经网络 恶性肿瘤 医学 逻辑回归 放射科 计算机科学 多层感知器 机器学习 人工神经网络 模式识别(心理学) 病理
作者
Min Lai,Bojian Feng,Jincao Yao,Yifan Wang,Qianmeng Pan,Yuhang Chen,Chen Chen,Na Feng,Fang Shi,Yuan Tian,Lu Gao,Dong Xu
出处
期刊:Ultrasound in Medicine and Biology [Elsevier BV]
卷期号:49 (11): 2413-2421 被引量:7
标识
DOI:10.1016/j.ultrasmedbio.2023.08.008
摘要

Considerable heterogeneity is observed in the malignancy rates of thyroid nodules classified as category 4 according to the Thyroid Imaging Reporting and Data System (TI-RADS). This study was aimed at comparing the diagnostic performance of artificial intelligence algorithms and radiologists with different experience levels in distinguishing benign and malignant TI-RADS 4 (TR4) nodules.Between January 2019 and September 2022, 1117 TR4 nodules with well-defined pathological findings were collected for this retrospective study. An independent external data set of 125 TR4 nodules was incorporated for testing purposes. Traditional feature-based machine learning (ML) models, deep convolutional neural networks (DCNN) models and a fusion model that integrated the prediction outcomes from all models were used to classify benign and malignant TR4 nodules. A fivefold cross-validation approach was employed, and the diagnostic performance of each model and radiologists was compared.In the external test data set, the area under the receiver operating characteristic curve (AUROC) of the three DCNN-based secondary transfer learning models-InceptionV3, DenseNet121 and ResNet50-were 0.852, 0.837 and 0.856, respectively. These values were higher than those of the three traditional ML models-logistic regression, multilayer perceptron and random forest-at 0.782, 0.790, and 0.767, respectively, and higher than that of an experienced radiologist (0.815). The fusion diagnostic model we developed, with an AUROC of 0.880, was found to outperform the experienced radiologist in diagnosing TR4 nodules.The integration of artificial intelligence algorithms into medical imaging studies could improve the accuracy of identifying high-risk TR4 nodules pre-operatively and have significant clinical application potential.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
2秒前
淡淡的就会顺顺的完成签到,获得积分10
2秒前
dingdong发布了新的文献求助10
2秒前
Jameslee0015完成签到,获得积分20
2秒前
小蘑菇的应助被羊羔蓉采纳,获得10
2秒前
zy发布了新的文献求助10
2秒前
情怀的应助被LKF采纳,获得10
4秒前
脑洞疼的应助被行空宇采纳,获得10
4秒前
黄油小熊发布了新的文献求助10
4秒前
4秒前
5秒前
李爱国的应助被ReEscort采纳,获得10
5秒前
Ava的应助被yunyu采纳,获得10
6秒前
柿子完成签到,获得积分10
7秒前
科研通AI6.2的应助被鱼鱼鱼采纳,获得10
8秒前
1900完成签到,获得积分10
8秒前
科研通AI6.4的应助被dingdong采纳,获得10
8秒前
9秒前
9秒前
Lucas的应助被陨落的繁星采纳,获得10
9秒前
panqiujiang完成签到,获得积分10
9秒前
yang完成签到,获得积分10
10秒前
10秒前
10秒前
11秒前
12秒前
shen的应助被波波采纳,获得10
12秒前
sss2021完成签到,获得积分10
12秒前
13秒前
等等发布了新的文献求助10
14秒前
14秒前
sunsun发布了新的文献求助10
15秒前
maq完成签到,获得积分10
15秒前
啊呦阿柚完成签到,获得积分10
15秒前
15秒前
ysq发布了新的文献求助30
16秒前
oleskarabach发布了新的文献求助10
16秒前
16秒前
科研狗完成签到,获得积分10
16秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology)求助 1000
Encyclopedia of Modern Artificial Intelligence 1000
John McDowells Bildungstheorie 800
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
Synthesis, Application and Future Perspectives of Smart Nano-materials - Part 1 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8153617
求助须知:如何正确求助?哪些是违规求助? 9550393
关于积分的说明 21697779
捐赠科研通 7742326
什么是DOI,文献DOI怎么找? 3425555
关于科研通互助平台的介绍 2550668
邀请新用户注册赠送积分活动 2469191