基于频谱适配器的分割一切模型在计算机断层扫描中结直肠癌肝转移灶分割
Spectral Adapters for Segment Anything Model-based Segmentation of Colorectal Liver Metastases in Computed Tomography
浏览论文内容
中文总结 AI 辅助
针对CT图像中结直肠癌肝转移灶分割，提出两种频谱适配器（DiSECT和SiGA）高效微调SAM，在446个体数据上验证，SiGA单点Dice达0.77，DiSECT仅需14万参数，性能媲美nnU-Net。
中文摘要 AI 辅助
在对比增强计算机断层扫描（CT）中准确分割结直肠癌肝转移灶（CRLM）对于疗效评估、手术规划和随访至关重要。我们为分割一切模型（SAM）提出了两种参数高效的频谱适配器：方向性频谱适配器（DiSECT）和频谱实例引导适配器（SiGA）。DiSECT利用冻结权重的奇异值分解，将残差更新约束到主要频谱方向，而SiGA通过多层感知器增加全局和输入条件门控。我们在446个对比增强CT体数据（355个训练，91个测试）上评估了这些方法，并与LoRA、QLoRA、卷积适配器（CAD）以及3D nnU-Net基线进行了比较。实验考虑了单点、三点、边界框和无提示（no-prompt）模式。SiGA在单点模式下取得了最佳性能，Dice得分为0.77，IoU为0.69，HD95为35.39毫米。在无提示推理下，SiGA达到0.76的Dice、0.68的IoU和46.76毫米的HD95，与nnU-Net基线（0.758 Dice）相当。DiSECT仅使用14万个可训练参数。这些结果表明，频谱适配器可以高效地使SAM适应CRLM分割，同时在有限的可训练参数下保持较强的准确性。
英文摘要
Accurate segmentation of colorectal liver metastases (CRLM) in contrast-enhanced computed tomography (CT) is important for response assessment, surgical planning, and follow-up. We propose two parameter-efficient spectral adapters for the Segment Anything Model (SAM): the Directional Spectral Adapter (DiSECT) and Spectral Instance-Guided Adapter (SiGA). DiSECT uses singular value decomposition of frozen weights to constrain residual updates to leading spectral directions, while SiGA adds global and input-conditioned gating through a multilayer perceptron. We evaluate these methods on 446 contrast-enhanced CT volumes (355 training, 91 testing) and compare them with LoRA, QLoRA, convolutional adapters (CAD), and a 3D nnU-Net baseline. Experiments consider single-point, three-point, bounding-box, and no-prompt regimes. SiGA achieves the best single-point performance with a Dice score of 0.77, IoU of 0.69, and HD95 of 35.39 mm. Under no-prompt inference, SiGA reaches 0.76 Dice, 0.68 IoU, and 46.76 mm HD95, comparable to the nnU-Net baseline (0.758 Dice). DiSECT uses only 0.14 million trainable parameters. These results show that spectral adapters can efficiently adapt SAM for CRLM segmentation while retaining strong accuracy with limited trainable parameters.
发表机构
- Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心）
- University of Alberta（阿尔伯塔大学）
- Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）
- The University of Texas MD Anderson Cancer Center（德克萨斯大学MD安德森癌症中心）
- Toronto General Hospital Research Institute, University Health Network（大学健康网络多伦多总医院研究所）
机构由 AI 辅助整理，请以论文原文为准。
