用状态空间模型提升3D脑肿瘤影像的可解释表征能力
Learning Brain Tumor Representation in 3D High-Resolution MR Images via Interpretable State Space Models
- 基于状态空间模型设计掩码自编码器，高效处理高分辨率3D MR图像
- 在突变类型与染色体缺失分类任务上达到当前最优准确率
- 提出隐变量到空间的映射方法，直观展示特征对应病灶区域
从高维体素磁共振（MR）图像中学习有意义且可解释的表示，对推动个性化医疗至关重要。尽管视觉变换器（ViTs）在图像数据处理中展现潜力，但其在3D多对比度MR图像上的应用受限于计算复杂性和可解释性不足。为此，我们提出一种基于状态空间模型（SSM）的掩码自编码器，可有效扩展类ViT模型以处理高分辨率数据，同时增强学习表征的可解释性。我们还提出一种隐变量到空间的映射技术，使隐层特征与输入体积中特定区域的对应关系得以直接可视化。我们在两个关键神经肿瘤学任务上验证了该方法：异柠檬酸脱氢酶突变状态识别和1p/19q共缺失分类，均取得当前最优准确率。结果表明，基于SSM的自监督学习有望通过兼顾效率与可解释性，革新放射组学分析。
原文摘要 · Abstract (English)
Learning meaningful and interpretable representations from high-dimensional volumetric magnetic resonance (MR) images is essential for advancing personalized medicine. While Vision Transformers (ViTs) have shown promise in handling image data, their application to 3D multi-contrast MR images faces challenges due to computational complexity and interpretability. To address this, we propose a novel state-space-model (SSM)-based masked autoencoder which scales ViT-like models to handle high-resolution data effectively while also enhancing the interpretability of learned representations. We propose a latent-to-spatial mapping technique that enables direct visualization of how latent features correspond to specific regions in the input volumes in the context of SSM. We validate our method on two key neuro-oncology tasks: identification of isocitrate dehydrogenase mutation status and 1p/19q co-deletion classification, achieving state-of-the-art accuracy. Our results highlight the potential of SSM-based self-supervised learning to transform radiomics analysis by combining efficiency and interpretability.
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。