轻量模型实现跨模态快速颅骨剥离，浏览器也能运行
MindGrab for BrainChop: Fast and Accurate Skull Stripping for Command Line and Browser
- 基于频谱视角设计空洞卷积结构，全卷积架构更高效
- 平均Dice达95.9（标准差1.6），速度比传统方法快40倍
- 支持命令行与网页直接运行，适合资源受限场景
深度学习模型在神经影像中的应用受部署复杂性和专用硬件限制。我们提出MindGrab，一种轻量级、全卷积的体积分割模型，适用于所有成像模态的颅骨剥离。其架构基于空洞卷积的频谱解释从头设计，在跨数据集和模态上的平均Dice分数达95.9（标准差1.6），相比现有方法速度提升最高达40倍，内存占用显著降低。极小的模型体积使其可在资源受限环境实现全体积快速处理，支持直接在浏览器中运行。MindGrab通过BrainChop平台提供，既可通过pip安装为命令行工具，也可作为零安装网页应用（brainchop.org）使用。该方法在不牺牲精度的前提下，消除了传统部署障碍，使前沿神经影像分析更易普及。
原文摘要 · Abstract (English)
Deployment complexity and specialized hardware requirements hinder the adoption of deep learning models in neuroimaging. We present MindGrab, a lightweight, fully convolutional model for volumetric skull stripping across all imaging modalities. MindGrab's architecture is designed from first principles using a spectral interpretation of dilated convolutions, and demonstrates state-of-the-art performance (mean Dice score across datasets and modalities: 95.9 with SD 1.6), with up to 40-fold speedups and substantially lower memory demands compared to established methods. Its minimal footprint allows for fast, full-volume processing in resource-constrained environments, including direct in-browser execution. MindGrab is delivered via the BrainChop platform as both a simple command-line tool (pip install brainchop) and a zero-installation web application (brainchop.org). By removing traditional deployment barriers without sacrificing accuracy, MindGrab makes state-of-the-art neuroimaging analysis broadly accessible.
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。