用多模态知识引导，实现医学影像任意分辨率超分。
Nexus-INR: Diverse Knowledge-guided Arbitrary-Scale Multimodal Medical Image Super-Resolution
- 双分支编码器分离解剖结构与模态特异性特征
- 跨模态注意力+自监督损失提升重建一致性
- 嵌入解剖语义，兼顾超分质量与分割性能
任意分辨率超分辨率（ARSR）可灵活适应不同空间分辨率，对医学图像分析至关重要。传统基于CNN的方法因专为固定放大倍数设计，难以胜任ARSR；尽管INR方法克服了此限制，仍难以有效处理多模态、异构分辨率的医学图像。本文提出Nexus-INR框架，通过多样化信息与下游任务实现高质量、自适应分辨率的医学图像超分辨率。该框架包含三个关键组件：双分支编码器结合辅助分类任务，有效解耦共享解剖结构与模态特异性特征；基于交叉模态注意力的知识蒸馏模块，利用高分辨率参考引导低分辨率模态重建，并引入自监督一致性损失增强性能；集成分割模块嵌入解剖语义，同时提升重建质量与下游分割表现。在BraTS2020数据集上的实验表明，该方法在多种指标上均优于现有先进方法。
原文摘要 · Abstract (English)
Arbitrary-resolution super-resolution (ARSR) provides crucial flexibility for medical image analysis by adapting to diverse spatial resolutions. However, traditional CNN-based methods are inherently ill-suited for ARSR, as they are typically designed for fixed upsampling factors. While INR-based methods overcome this limitation, they still struggle to effectively process and leverage multi-modal images with varying resolutions and details. In this paper, we propose Nexus-INR, a Diverse Knowledge-guided ARSR framework, which employs varied information and downstream tasks to achieve high-quality, adaptive-resolution medical image super-resolution. Specifically, Nexus-INR contains three key components. A dual-branch encoder with an auxiliary classification task to effectively disentangle shared anatomical structures and modality-specific features; a knowledge distillation module using cross-modal attention that guides low-resolution modality reconstruction with high-resolution reference, enhanced by self-supervised consistency loss; an integrated segmentation module that embeds anatomical semantics to improve both reconstruction quality and downstream segmentation performance. Experiments on the BraTS2020 dataset for both super-resolution and downstream segmentation demonstrate that Nexus-INR outperforms state-of-the-art methods across various metrics.
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。