EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

From Fully-Automatic to Efficient Interaction: A Lightweight Prompting Framework for Jaw Cyst Segmentation

Chao Li, Zhe Rao, Tinglong Tang, Zhenyang Wang, Yalin Wang, Xiaotian Pan

Transactions on Artificial Intelligence · 17.11.2026 · 2 (1) · 231-244

DOI: 10.53941/tai.2026.100015 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions on Artificial Intelligence, online erschienen am 17.11.2026. Verfasst von Chao Li und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Zhejiang Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Faint, interrupted boundaries make jaw cysts difficult to delineate in medical images. Clinicians can help identify the lesion, yet a fully automatic segmentation model has no direct means of using their assessment to guide an individual mask. We developed PromptFormer to accept bounding box prompts through a compact medical segmentation backbone. Its Plug-in Prompt Process Module (PPPM) couples that backbone to the prompt encoder and mask decoder of the Segment Anything Model (SAM); SAM’s image encoder is omitted. The backbone is supplemented by a Frequency-domain Global Perception Module (FGPM) for global structure and a Multi-scale Detail Refinement Module (MDRM) for spatial detail. Tests used a clinically collected jaw cyst dataset, BUSI, and ISIC 2017. Across the three datasets, the highest Intersection over Union (IoU) among the compared models was obtained by PromptFormer. Its jaw cyst Dice score was 93.79%. Relative to the SAM-based comparators in the efficiency test, fewer than one seventh as many floating-point operations were needed, and inference was approximately 2.7 to 8.6 times as fast. These computational savings, together with the prompt interface, justify further evaluation on clinical devices with limited resources.

Förderung

  • Natural Science Foundation of Zhejiang Province

Zitieren

APA

Li, C., Rao, Z., Tang, T., Wang, Z., Wang, Y., & Pan, X. (2026). From Fully-Automatic to Efficient Interaction: A Lightweight Prompting Framework for Jaw Cyst Segmentation. Transactions on Artificial Intelligence, 2(1), 231-244. https://doi.org/10.53941/tai.2026.100015

Vancouver

Li C, Rao Z, Tang T, Wang Z, Wang Y, Pan X. From Fully-Automatic to Efficient Interaction: A Lightweight Prompting Framework for Jaw Cyst Segmentation. Transactions on Artificial Intelligence. 2026;2(1):231-244. doi:10.53941/tai.2026.100015

BibTeX
@article{Li2026,
  author = {Li, Chao and Rao, Zhe and Tang, Tinglong and Wang, Zhenyang and Wang, Yalin and Pan, Xiaotian},
  title = {From Fully-Automatic to Efficient Interaction: A Lightweight Prompting Framework for Jaw Cyst Segmentation},
  journal = {Transactions on Artificial Intelligence},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {231--244},
  doi = {10.53941/tai.2026.100015}
}
Kostenlos starten →