Text-Guided Modulation and Boundary-Aware Refinement for Vision-Text COVID-19 CT Lesion Segmentation
Health Medicine and Therapeutics · 28.07.2026 · 2 (1) · 57
DOI: 10.63313/hmt.9030 ↗Kurz gefasst
Fachartikel in der Zeitschrift Health Medicine and Therapeutics, online erschienen am 28.07.2026. Verfasst von Jifa Li. Die Arbeit nennt 10 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate COVID-19 CT lesion segmentation is challenged by weak boundaries and variable lesion appearance. This paper investigates two enhancement strategies built upon a clean LViT/VT-MFLV baseline: Multi-scale Text-Guided Modulation (MTGM) and Boundary Context Auxiliary Learning (BCA). MTGM converts clinical text embeddings into residual channel gates, while BCA introduces boundary supervision and inference-active boundary-guided feature refinement. On MosMedData+, the clean baseline obtains 0.7318 Dice and 0.5996 IoU. The best evaluated variant, BCA-v2, reaches 0.747385 Dice and 0.613327 IoU. The experiments show that boundary-guided decoder refinement is more effective than training-only boundary supervision, while text-gate placement requires careful scale selection.
Zitieren
APA
Li, J. (2026). Text-Guided Modulation and Boundary-Aware Refinement for Vision-Text COVID-19 CT Lesion Segmentation. Health Medicine and Therapeutics, 2(1), 57. https://doi.org/10.63313/hmt.9030
Vancouver
Li J. Text-Guided Modulation and Boundary-Aware Refinement for Vision-Text COVID-19 CT Lesion Segmentation. Health Medicine and Therapeutics. 2026;2(1):57. doi:10.63313/hmt.9030
BibTeX
@article{Li2026,
author = {Li, Jifa},
title = {Text-Guided Modulation and Boundary-Aware Refinement for Vision-Text COVID-19 CT Lesion Segmentation},
journal = {Health Medicine and Therapeutics},
year = {2026},
volume = {2},
number = {1},
pages = {57},
doi = {10.63313/hmt.9030}
}
EUVIMED