An integrated AI model to improve diagnostic accuracy of ultrasound and output known risk features in suspicious thyroid nodules

医学 神经组阅片室 放射科 超声波 甲状腺结节 介入放射学 甲状腺癌 甲状腺 组织病理学 病理 内科学 精神科 神经学
作者
Juan Wang,Jue Jiang,Dong Zhang,Yaozhong Zhang,Long Guo,Yusheng Jiang,Shaoyi Du,Qi Zhou
出处
期刊:European Radiology [Springer Nature]
卷期号:32 (3): 2120-2129 被引量:26
标识
DOI:10.1007/s00330-021-08298-7
摘要

From the viewpoint of ultrasound (US) physicians, an ideal thyroid US computer-assisted diagnostic (CAD) system for thyroid cancer should perform well in suspicious thyroid nodules with atypical risk features and be able to output explainable results. This study aims to develop an explainable US CAD model for suspicious thyroid nodules.A total of 2992 solid or almost-solid thyroid nodules were analyzed retrospectively. All nodules had pathological results (1070 malignancies and 1992 benignities) confirmed by ultrasound-guided fine-needle aspiration cytology and histopathology after thyroidectomy. A deep learning model (ResNet50) and a multiple risk features learning ensemble model (XGBoost) were used to train the US images of 2794 thyroid nodules. Then, an integrated AI model was generated by combining both models. The diagnostic accuracies of the three AI models (ResNet50, XGBoost, and the integrated model) were predicted in a testing set including 198 thyroid nodules and compared to the diagnostic efficacy of five ultrasonographers.The accuracy of the integrated model was 76.77%, while the mean accuracy of the ultrasonographers was 68.38%. Of the risk features, microcalcifications showed the highest contribution to the diagnosis of malignant nodules.The integrated AI model in our study can improve the diagnostic accuracy of suspicious thyroid nodules and output the known risk features simultaneously, thus aiding in training young ultrasonographers by linking the explainable results to their clinical experience and advancing the acceptance of AI diagnosis for thyroid cancer in clinical practice.• We developed an artificial intelligence (AI) diagnosis model based on both deep learning and multiple risk feature ensemble learning methods. • The AI diagnosis model showed higher diagnostic accuracy for suspicious thyroid nodules than ultrasonographers. • The AI diagnosis model showed partial explainability by outputting the known risk features, thus aiding young ultrasonic doctors in increasing the diagnostic level for thyroid cancer.
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
更新
大幅提高文件上传限制,最高150M (2024-4-1)

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
李健的粉丝团团长应助thia采纳,获得10
1秒前
1秒前
kaiko发布了新的文献求助20
1秒前
1秒前
2秒前
2秒前
鲤鱼初柳发布了新的文献求助10
2秒前
4秒前
NexusExplorer应助文静寄琴采纳,获得10
4秒前
ling完成签到 ,获得积分10
5秒前
happiness完成签到 ,获得积分10
5秒前
tonghau895完成签到 ,获得积分10
5秒前
5秒前
6秒前
7秒前
梅仑西西发布了新的文献求助20
7秒前
萧水白应助lovekobe采纳,获得10
7秒前
迷路海蓝应助lovekobe采纳,获得10
7秒前
传奇3应助lovekobe采纳,获得10
7秒前
7秒前
深情安青应助lovekobe采纳,获得10
7秒前
铭铭应助lovekobe采纳,获得10
7秒前
去看海嘛应助lovekobe采纳,获得10
7秒前
超帅路灯应助lovekobe采纳,获得10
7秒前
去看海嘛应助lovekobe采纳,获得10
7秒前
不配.应助lovekobe采纳,获得10
7秒前
星辰大海应助lovekobe采纳,获得10
8秒前
李爱国应助blUe采纳,获得10
8秒前
Lucas应助xuhang采纳,获得10
8秒前
爆米花应助周周采纳,获得10
8秒前
没有好的昵称可以取完成签到 ,获得积分10
8秒前
kieerw发布了新的文献求助30
8秒前
Akim应助betterzhu采纳,获得10
8秒前
wwf完成签到 ,获得积分10
9秒前
9秒前
霜揽月发布了新的文献求助10
9秒前
hyelachan发布了新的文献求助20
10秒前
852应助穿多点采纳,获得10
10秒前
10秒前
逆熵完成签到 ,获得积分10
11秒前
高分求助中
Evolution 10000
Sustainability in Tides Chemistry 2800
юрские динозавры восточного забайкалья 800
English Wealden Fossils 700
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
A new species of Velataspis (Hemiptera Coccoidea Diaspididae) from tea in Assam 500
Diagnostic immunohistochemistry : theranostic and genomic applications 6th Edition 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3155576
求助须知:如何正确求助?哪些是违规求助? 2806779
关于积分的说明 7870685
捐赠科研通 2465047
什么是DOI,文献DOI怎么找? 1312118
科研通“疑难数据库(出版商)”最低求助积分说明 629877
版权声明 601892