Parameter-Efficient Adaptation of SAM 3 for Automated ITV Generation from 4DCT Images 文章

ArXiv CS.CV2026-06-16NEWSen作者: Changwoo Song

详细信息

来源站点
ArXiv CS.CV
作者
Changwoo Song
文章类型
NEWS
语言
en
发布日期
2026-06-16

摘要

arXiv:2606.15604v1 Announce Type: new Abstract: Four-dimensional computed tomography (4DCT) captures the full respiratory cycle of thoracic anatomy, yet current Internal Target Volume contouring workflows process each phase in isolation, discarding temporal coherence and leaving contours vulnerable to phase-specific artifacts. We present a lightweight framework that applies parameter-efficient fine-tuning to the Segment Anything Model 3 (SAM 3) via low-rank adaptation (LoRA) to align its text-prompted segmentation with the medical domain using only seven annotated 3D CT volumes. Furthermore, the framework incorporates a hard negative mining strategy to improve boundary discrimination in low-contrast thoracic regions. At inference, phase-wise predictions are refined through phase-coherent temporal filtering and spatial connectivity analysis.