Text-Guided Modulation and Boundary-Aware Refinement for Vision-Text COVID-19 CT Lesion Segmentation
Health Medicine and Therapeutics · 2026-07-28 · 2 (1) · 57
DOI: 10.63313/hmt.9030 ↗At a glance
Journal article in Health Medicine and Therapeutics, published online on 2026-07-28. Written by Jifa Li. 10 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
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.
Cite
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