EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Intelligent segmentation of thyroid nodule ultrasound images based on benign–malignant-aware semantic prototype calibration and class-conditional boundary refinement

Bin Luo, Runwen Li, Yao Tang

Frontiers in Cell and Developmental Biology · 21.08.2026 · 14

DOI: 10.3389/fcell.2026.1879094 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Cell and Developmental Biology, online erschienen am 21.08.2026. Verfasst von Bin Luo und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of General Surgery, Panzhihua Central Hospital, Panzhihua, Sichuan, China. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Ultrasound-based thyroid nodule segmentation remains challenging because of blurred boundaries, complex echo noise, and subtle morphological differences between benign and malignant lesions.

Methods

We propose a benign-malignant-aware segmentation framework based on SegFormer, incorporating adaptive semantic prototype calibration (ASPC) for class-level semantic discrimination and class-conditional boundary refinement (CCBR) for ambiguous contour correction. The model performs three-class segmentation of background, benign, and malignant regions.

Results

Experiments on the public TN3K dataset and an in-house clinical dataset demonstrate consistent performance under both external transfer and supervised evaluation settings. The proposed method achieved PA, mIoU, mDice, and mPrecision of 0.9449, 0.6427, 0.7517, and 0.8147 on TN3K; 0.7793, 0.5016, 0.6374, and 0.7089 under direct external transfer; and 0.8521, 0.6124, 0.7328, and 0.7996 under supervised in-house evaluation.

Discussion

Ablation studies and Grad-CAM visualization further confirm that ASPC and CCBR improve semantic discrimination, boundary refinement, and model interpretability, supporting the effectiveness of the proposed framework for thyroid nodule segmentation.

Schlagwörter

Stichwörter der Autor:innen

benign–malignant-aware segmentationboundary refinementsemantic prototype calibrationthyroid noduleultrasound image segmentation

Autor:innen und Institutionen

  • Department of General Surgery, Panzhihua Central Hospital, Panzhihua, Sichuan, China.
  • Department of Vascular Diseases, Panzhihua Central Hospital, Panzhihua, Sichuan, China.
  • Department of Ophthalmology, Panzhihua Central Hospital, Panzhihua, Sichuan, China.

Zitieren

APA

Luo, B., Li, R., & Tang, Y. (2026). Intelligent segmentation of thyroid nodule ultrasound images based on benign–malignant-aware semantic prototype calibration and class-conditional boundary refinement. Frontiers in Cell and Developmental Biology, 14. https://doi.org/10.3389/fcell.2026.1879094

Vancouver

Luo B, Li R, Tang Y. Intelligent segmentation of thyroid nodule ultrasound images based on benign–malignant-aware semantic prototype calibration and class-conditional boundary refinement. Frontiers in Cell and Developmental Biology. 2026;14. doi:10.3389/fcell.2026.1879094

BibTeX
@article{Luo2026,
  author = {Luo, Bin and Li, Runwen and Tang, Yao},
  title = {Intelligent segmentation of thyroid nodule ultrasound images based on benign–malignant-aware semantic prototype calibration and class-conditional boundary refinement},
  journal = {Frontiers in Cell and Developmental Biology},
  year = {2026},
  volume = {14},
  doi = {10.3389/fcell.2026.1879094}
}
Kostenlos starten →