EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Transvaginal ultrasound-based radiomics and integrated clinical indicators via multimodal deep learning for prediction of endometrial polyp recurrence after hysteroscopic surgery

Yun Shen, Boyang Ding, Juan Li

Biomedical Engineering / Biomedizinische Technik · 2026

DOI: 10.1515/bmt-2026-0223 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Engineering / Biomedizinische Technik, 2026. Verfasst von Yun Shen und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gynecology, Hefei First People's Hospital (Binhu Branch), Hefei, China. Hauptthemen laut MEDLINE: Hysteroscopy, Polyps, Deep Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To evaluate a multimodal deep learning model integrating preoperative transvaginal ultrasound (TVUS)-based radiomics features and clinical indicators for predicting 1-year postoperative recurrence of endometrial polyps (EP) after hysteroscopic polypectomy.

Methods

A total of 116 patients with pathologically confirmed EP were assigned to a training cohort (n=81) and validation cohort (n=35). Radiomics features were extracted from TVUS images, and deep learning features were obtained using ResNet-based networks. These features, with clinical variables, were combined to build a multimodal model. Feature selection in the training cohort used reproducibility filtering (intraclass correlation coefficient [ICC] >0.80), univariate analysis, Pearson correlation (|r|>0.90), and least absolute shrinkage and selection operator (LASSO) regression. Model performance was evaluated by receiver operating characteristic (ROC) curves, area under the curve (AUC), calibration, and decision curve analysis (DCA).

Results

The multimodal model achieved AUCs of 0.941 (95 % CI: 0.897–0.985) and 0.922 (95 % CI: 0.852–0.992) in training and validation cohorts, outperforming clinical (0.812, 0.791) and radiomics-only models (0.871, 0.843). DeLong tests were significant (p

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

HysteroscopyPolypsDeep LearningHumansRadiomicsFemaleUltrasonographyRecurrenceEndometriumROC Curve

Stichwörter der Autor:innen

endometrial polypsmultimodal deep learningradiomicsrecurrence predictiontransvaginal ultrasound

Autor:innen und Institutionen

  • Department of Gynecology, Hefei First People's Hospital (Binhu Branch), Hefei, China.

Zitieren

APA

Shen, Y., Ding, B., & Li, J. (2026). Transvaginal ultrasound-based radiomics and integrated clinical indicators via multimodal deep learning for prediction of endometrial polyp recurrence after hysteroscopic surgery. Biomedical Engineering / Biomedizinische Technik. https://doi.org/10.1515/bmt-2026-0223

Vancouver

Shen Y, Ding B, Li J. Transvaginal ultrasound-based radiomics and integrated clinical indicators via multimodal deep learning for prediction of endometrial polyp recurrence after hysteroscopic surgery. Biomedical Engineering / Biomedizinische Technik. 2026. doi:10.1515/bmt-2026-0223

BibTeX
@article{Shen2026,
  author = {Shen, Yun and Ding, Boyang and Li, Juan},
  title = {Transvaginal ultrasound-based radiomics and integrated clinical indicators via multimodal deep learning for prediction of endometrial polyp recurrence after hysteroscopic surgery},
  journal = {Biomedical Engineering / Biomedizinische Technik},
  year = {2026},
  doi = {10.1515/bmt-2026-0223}
}
Kostenlos starten →