EUVIMEDEUVIMED entdecken
Crossref

An Ultrasound Image‐Based Deep Learning Radiomics Nomogram for Differentiating Between Benign and Malignant Indeterminate Cytology (Bethesda III ) Thyroid Nodules: A Retrospective Study

Lichang Zhong iD, Lin Shi, Weimei Li, Liang Zhou, Kui Wang, Liping Gu

Journal of Clinical Ultrasound · 2025

DOI: 10.1002/jcu.24058 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Clinical Ultrasound, 2025. Verfasst von Lichang Zhong und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ultrasound in Medicine, Sixth People's Hospital Affiliated to Medical College of Shanghai Jiaotong University, Shanghai Institute of Ul…. Hauptthemen laut MEDLINE: Thyroid Nodule, Deep Learning, Nomograms, Thyroid Neoplasms. Die Arbeit nennt 35 Literaturangaben. Gefördert von: Shanghai Municipal Health Commission.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rationale and Objectives Our objective is to develop and validate a deep learning radiomics nomogram (DLRN) based on preoperative ultrasound images and clinical features, for predicting the malignancy of thyroid nodules with indeterminate cytology (Bethesda III). Materials and Methods Between June 2017 and June 2022, we conducted a retrospective study on 194 patients with surgically confirmed indeterminate cytology (Bethesda III) in our hospital. The training and internal validation cohorts were comprised of 155 and 39 patients, in a 7:3 ratio. To facilitate external validation, we selected an additional 80 patients from each of the remaining two medical centers. Utilizing preoperative ultrasound data, we obtained imaging markers that encompass both deep learning and manually radiomic features. After feature selection, we developed a comprehensive diagnostic model to evaluate the predictive value for Bethesda III benign and malignant cases. The model's diagnostic accuracy, calibration, and clinical applicability were systematically assessed.

Results

The results showed that the prediction model, which integrated 512 DTL features extracted from the pre‐trained Resnet34 network, ultrasound radiomics, and clinical features, exhibited superior stability in distinguishing between benign and malignant indeterminate thyroid nodules (Bethesda Class III). In the validation set, the AUC was 0.92 (95% CI: 0.831–1.000), and the accuracy, sensitivity, specificity, precision, and recall were 0.897, 0.882, 0.909, 0.882, and 0.882, respectively.

Conclusion

The comprehensive multidimensional data model based on deep transfer learning, ultrasound radiomics features, and clinical characteristics can effectively distinguish the benign and malignant indeterminate thyroid nodules (Bethesda Class III), providing valuable guidance for treatment selection in patients with indeterminate thyroid nodules (Bethesda Class III).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Thyroid NoduleDeep LearningNomogramsThyroid NeoplasmsHumansRetrospective StudiesFemaleMaleMiddle AgedUltrasonographyDiagnosis, DifferentialAdultThyroid GlandAgedPredictive Value of TestsReproducibility of ResultsRadiomics

Stichwörter der Autor:innen

convolutional neural networkdeep transfer learningindeterminate thyroid nodulemachine learningradiomics

Autor:innen und Institutionen

  • Department of Ultrasound in Medicine, Sixth People's Hospital Affiliated to Medical College of Shanghai Jiaotong University, Shanghai Institute of Ultrasound in Medicine, Shanghai, China.
  • Department of Information, Sixth People's Hospital Affiliated to Medical College of Shanghai Jiaotong University, Shanghai, China.
  • The Affiliated Jiangsu Shengze Hospital of Nanjing Medical University, Suzhou, China.

ORCID-Profile: Lichang Zhong

Förderung

  • Shanghai Municipal Health Commission

Zitieren

APA

Zhong, L., Shi, L., Li, W., Zhou, L., Wang, K., & Gu, L. (2025). An Ultrasound Image‐Based Deep Learning Radiomics Nomogram for Differentiating Between Benign and Malignant Indeterminate Cytology (Bethesda III ) Thyroid Nodules: A Retrospective Study. Journal of Clinical Ultrasound. https://doi.org/10.1002/jcu.24058

Vancouver

Zhong L, Shi L, Li W, Zhou L, Wang K, Gu L. An Ultrasound Image‐Based Deep Learning Radiomics Nomogram for Differentiating Between Benign and Malignant Indeterminate Cytology (Bethesda III ) Thyroid Nodules: A Retrospective Study. Journal of Clinical Ultrasound. 2025. doi:10.1002/jcu.24058

BibTeX
@article{Zhong2025,
  author = {Zhong, Lichang and Shi, Lin and Li, Weimei and Zhou, Liang and Wang, Kui and Gu, Liping},
  title = {An Ultrasound Image‐Based Deep Learning Radiomics Nomogram for Differentiating Between Benign and Malignant Indeterminate Cytology (Bethesda III ) Thyroid Nodules: A Retrospective Study},
  journal = {Journal of Clinical Ultrasound},
  year = {2025},
  doi = {10.1002/jcu.24058}
}
Kostenlos starten →