EUVIMEDEUVIMED entdecken
Crossref

Generalizability and Diagnostic Performance of AI Models for Thyroid US

WenWen Xu, XiaoHong Jia, ZiHan Mei, XiaoLin Gu iD, Yang Lu iD, Chi-Cheng Fu iD, RuiFang Zhang, Ying Gu, Xia Chen, XiaoMao Luo, Ning Li, BaoYan Bai und 14 weitere

Radiology · 01.06.2023 · 307 (5)

DOI: 10.1148/radiol.221157 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiology, erschienen am 01.06.2023. Verfasst von WenWen Xu und 25 weiteren Autor:innen. Beteiligte Einrichtung: From the Department of Ultrasound, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, 197 Ruijin Er Road, 200025, Shanghai, China (W.W…. Hauptthemen laut MEDLINE: Thyroid Nodule, Thyroid Neoplasms. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 20 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Artificial intelligence (AI) models have improved US assessment of thyroid nodules; however, the lack of generalizability limits the application of these models.

Purpose

To develop AI models for segmentation and classification of thyroid nodules in US using diverse data sets from nationwide hospitals and multiple vendors, and to measure the impact of the AI models on diagnostic performance. Materials and Methods This retrospective study included consecutive patients with pathologically confirmed thyroid nodules who underwent US using equipment from 12 vendors at 208 hospitals across China from November 2017 to January 2019. The detection, segmentation, and classification models were developed based on the subset or complete set of images. Model performance was evaluated by precision and recall, Dice coefficient, and area under the receiver operating characteristic curve (AUC) analyses. Three scenarios (diagnosis without AI assistance, with freestyle AI assistance, and with rule-based AI assistance) were compared with three senior and three junior radiologists to optimize incorporation of AI into clinical practice.

Results

A total of 10 023 patients (median age, 46 years [IQR 37-55 years]; 7669 female) were included. The detection, segmentation, and classification models had an average precision, Dice coefficient, and AUC of 0.98 (95% CI: 0.96, 0.99), 0.86 (95% CI: 0.86, 0.87), and 0.90 (95% CI: 0.88, 0.92), respectively. The segmentation model trained on the nationwide data and classification model trained on the mixed vendor data exhibited the best performance, with a Dice coefficient of 0.91 (95% CI: 0.90, 0.91) and AUC of 0.98 (95% CI: 0.97, 1.00), respectively. The AI model outperformed all senior and junior radiologists (P < .05 for all comparisons), and the diagnostic accuracies of all radiologists were improved (P < .05 for all comparisons) with rule-based AI assistance.

Conclusion

Thyroid US AI models developed from diverse data sets had high diagnostic performance among the Chinese population. Rule-based AI assistance improved the performance of radiologists in thyroid cancer diagnosis. © RSNA, 2023 Supplemental material is available for this article.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Thyroid NoduleThyroid NeoplasmsHumansFemaleMiddle AgedArtificial IntelligenceRetrospective Studies

Autor:innen und Institutionen

  • From the Department of Ultrasound, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, 197 Ruijin Er Road, 200025, Shanghai, China (W.W.X., X.H.J., Z.H.M., W.W.Z., T.L., H.T.Z., Y.J.D., J.Q.Z.); Department…

ORCID-Profile: XiaoLin Gu, Yang Lu, Chi-Cheng Fu, KeYang Zhao, Qu Fang, Chuan He, WeiWei Zhan, JianQiao Zhou

Zitieren

APA

Xu, W., Jia, X., Mei, Z., Gu, X., Lu, Y., Fu, C. C., Zhang, R., Gu, Y., Chen, X., Luo, X., Li, N., Bai, B., Li, Q., Yan, J., Zhai, H., Guan, L., Gong, B., Zhao, K., Fang, Q., …, & Chinese Artificial Intelligence Alliance for Thyroid and Breast Ultrasound (2023). Generalizability and Diagnostic Performance of AI Models for Thyroid US. Radiology, 307(5). https://doi.org/10.1148/radiol.221157

Vancouver

Xu W, Jia X, Mei Z, Gu X, Lu Y, Fu CC, et al. Generalizability and Diagnostic Performance of AI Models for Thyroid US. Radiology. 2023;307(5). doi:10.1148/radiol.221157

BibTeX
@article{Xu2023,
  author = {Xu, WenWen and Jia, XiaoHong and Mei, ZiHan and Gu, XiaoLin and Lu, Yang and Fu, Chi-Cheng and Zhang, RuiFang and Gu, Ying and Chen, Xia and Luo, XiaoMao and Li, Ning and Bai, BaoYan and Li, QiaoYing and Yan, JiPing and Zhai, Hong and Guan, Ling and Gong, Bing and Zhao, KeYang and Fang, Qu and He, Chuan and Zhan, WeiWei and Luo, Ting and Zhang, HuiTing and Dong, YiJie and Zhou, JianQiao and Chinese Artificial Intelligence Alliance for Thyroid and Breast Ultrasound, Chinese Artificial Intelligence Alliance for Thyroid and Breast Ultrasound},
  title = {Generalizability and Diagnostic Performance of AI Models for Thyroid US},
  journal = {Radiology},
  year = {2023},
  volume = {307},
  number = {5},
  doi = {10.1148/radiol.221157}
}
Kostenlos starten →