用自门控提示提升3D病变分割，解决小病灶与背景失衡问题。
SGP-SAM: Self-Gated Prompting for Transferring 3D Segment Anything Models to Lesion Segmentation
- 自门控模块按需融合多尺度特征，提升小病灶空间表征能力。
- 在肝脏和脑肿瘤数据集上，mDice提升7.3%，优于微调基线。
- 适合医疗影像中不规则小病灶分割任务，尤其关注精度的临床应用。
大型分割基础模型如分割一切模型（SAM）重塑了自然图像的可提示分割，近期工作已将其扩展至医学图像与体素场景。然而，直接将3D SAM类模型迁移至病变分割仍面临挑战：(i) 中间特征对小型、不规则目标的空间表征能力弱；(ii) 3D体数据中前景-背景极度不平衡。本文提出SGP-SAM，一种用于高效、有效迁移至3D病变分割的自门控提示框架。核心组件自门控提示模块（SGPM）实现条件式多尺度空间增强：轻量级多通道门控单元预测当前特征是否需额外多尺度融合，仅在必要时激活多尺度特征融合块以丰富空间上下文。为进一步应对小病灶学习，设计了缩放损失（Zoom Loss），通过结合Dice与体素平衡的焦点项，强化病变区域监督。在MSD肝脏肿瘤与MSD脑肿瘤（增强肿瘤）数据集上的实验表明，相较于基于SAM-Med3D的强迁移基线，本方法取得持续提升。在肝脏肿瘤数据集上，相比微调方法，mDice提升7.3%。
原文摘要 · Abstract (English)
Large segmentation foundation models such as the Segment Anything Model (SAM) have reshaped promptable segmentation in natural images, and recent efforts have extended these models to medical images and volumetric settings. However, directly transferring a 3D SAM-style model to lesion segmentation remains challenging due to (i) weak spatial representational capacity for small, irregular targets in intermediate features, and (ii) extreme foreground-background imbalance in 3D volumes.We propose SGP-SAM, a self-gated prompting framework for efficient and effective transfer to 3D lesion segmentation. Our key component, the Self-Gated Prompting Module (SGPM), performs conditional multi-scale spatial enhancement: a lightweight multi-channel gating unit predicts whether the current features require additional multi-scale fusion, and only then activates a Multi-Scale Feature Fusion Block to enrich spatial context. To further address small-lesion learning, we design a Zoom Loss that up-weights lesion-focused supervision by combining Dice and a voxel-balanced focal term.Experiments on MSD Liver Tumor and MSD Brain Tumor (enhancing tumor) show consistent gains over strong transfer baselines based on SAM-Med3D. On MSD Liver Tumor, SGP-SAM improves mDice by 7.3% over fine-tuning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。