https://vilab.team/tag/mri/ MRI Hugo Blox Builder (https://hugoblox.com)en-usSun, 03 May 2026 00:00:00 +0000 https://vilab.team/media/icon_hu2896232876136423579.png https://vilab.team/tag/mri/ https://vilab.team/publication/salient-diagnostic-value-perception-for-preoperative-posteri/ Sun, 03 May 2026 00:00:00 +0000 https://vilab.team/publication/salient-diagnostic-value-perception-for-preoperative-posteri/ <p>本文提出显著诊断价值感知方法（SDVP），用于后颅窝肿瘤的术前准确诊断。该方法整合MRI影像与放射学报告，从三个互补视角学习关键诊断线索：通过对抗性样本内对比学习增强跨中心与设备差异的鲁棒性；借助知识增强的样本内对比学习提取专家引导的样本特异性特征；并在干净MRI样本上进行监督式类间对比学习以强化类别特征。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/ Sun, 03 May 2026 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/ <p>热烈祝贺陈政同学、吴小满同学！近期，实验室共有 2 项科研成果正式发表。</p> <h2 id="salient-diagnostic-value-perception-for-preoperative-posterior-fossa-tumor-diagnosis">Salient Diagnostic Value Perception For Preoperative Posterior Fossa Tumor Diagnosis</h2> <p><strong>祝贺陈政同学！该论文已发表在 <em>ICASSP 2026</em>。</strong></p> <ul> <li><strong>作者：</strong> Zheng Chen、Peng Li、Zheyu Zhang、Siying Wu、Jing Zhang、Cuiling Hu、Yunwei Ou、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>ICASSP</em></li> <li><strong>发表时间：</strong> 2026年5月3日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11460465/" target="_blank" rel="noopener">论文链接</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出显著诊断价值感知方法（SDVP），用于后颅窝肿瘤的术前准确诊断。该方法整合MRI影像与放射学报告，从三个互补视角学习关键诊断线索：通过对抗性样本内对比学习增强跨中心与设备差异的鲁棒性；借助知识增强的样本内对比学习提取专家引导的样本特异性特征；并在干净MRI样本上进行监督式类间对比学习以强化类别特征。</p> <hr> <h2 id="sscm-a-spatial-semantic-consistent-model-for-multi-contrast-mri-super-resolution">SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution</h2> <p><strong>祝贺吴小满同学！该论文已发表在 <em>ICASSP 2026</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/images/paper-02_hu16643979777475813095.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/images/paper-02_hu13958872581769715241.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/images/paper-02_hu13117256722096246496.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/images/paper-02_hu16643979777475813095.webp" width="760" height="438" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Xiaoman Wu、Lubin Gan、Siying Wu、Jing Zhang、Yunwei Ou、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>ICASSP</em></li> <li><strong>发表时间：</strong> 2026年5月3日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11464902/" target="_blank" rel="noopener">论文链接</a> · <a href="https://arxiv.org/pdf/2509.18593" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍-1">论文介绍</h3> <p>本文提出空间语义一致模型（SSCM），用于多对比度磁共振成像超分辨率。该方法通过动态空间扭曲模块实现对比度间空间对齐，利用语义感知令牌聚合块建模长程依赖，并结合空间-频率融合块恢复高频细节，从而在结构差异和运动干扰下保持解剖结构的空间语义一致性。实验表明SSCM在效率和性能上优于现有方法。</p> https://vilab.team/publication/mmsupcon-an-image-fusion-based-multi-modal-supervised-contra/ Thu, 28 Aug 2025 00:00:00 +0000 https://vilab.team/publication/mmsupcon-an-image-fusion-based-multi-modal-supervised-contra/ <p>本文针对脑肿瘤多模态MRI诊断中融合策略受限于样本稀缺的问题，提出多模态监督对比学习方法MMSupcon。该方法通过多模态医学图像融合生成信息丰富的样本，并设计多模态监督对比损失，引导模型有效整合互补模态信息，提升诊断准确性。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-artificial-intelligence-in-medicine/ Thu, 28 Aug 2025 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-artificial-intelligence-in-medicine/ <p>热烈祝贺王浩宇同学！论文《MMSupcon: An image fusion-based multi-modal supervised contrastive method for brain tumor diagnosis》已发表在 <em>Artificial Intelligence in Medicine</em>。</p> <h2 id="mmsupcon-an-image-fusion-based-multi-modal-supervised-contrastive-method-for-brain-tumor-diagnosis">MMSupcon: An image fusion-based multi-modal supervised contrastive method for brain tumor diagnosis</h2> <p><strong>祝贺王浩宇同学！该论文已发表在 <em>Artificial Intelligence in Medicine</em>。</strong></p> <ul> <li><strong>作者：</strong> Haoyu Wang、Jing Zhang、Siying Wu、Haoran Wei、Xun Chen、Yunwei Ou、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>Artificial Intelligence in Medicine</em></li> <li><strong>发表时间：</strong> 2025年8月28日</li> <li><strong>相关链接：</strong> <a href="https://www.sciencedirect.com/science/article/pii/S0933365725001885" target="_blank" rel="noopener">论文链接</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文针对脑肿瘤多模态MRI诊断中融合策略受限于样本稀缺的问题，提出多模态监督对比学习方法MMSupcon。该方法通过多模态医学图像融合生成信息丰富的样本，并设计多模态监督对比损失，引导模型有效整合互补模态信息，提升诊断准确性。</p> https://vilab.team/publication/incomplete-multi-modal-brain-tumor-segmentation-via-learnabl/ Tue, 10 Jun 2025 00:00:00 +0000 https://vilab.team/publication/incomplete-multi-modal-brain-tumor-segmentation-via-learnabl/ <p>本文提出一种可学习排序状态空间模型（LS3M），用于不完整多模态脑肿瘤分割。该方法基于Mamba架构高效建模长距离依赖，并引入可微置换矩阵，根据模态特定特征对输入序列进行动态重排序，从而保留3D脑MRI中关键的空间归纳偏置与长程语义相关性。LS3M能够充分利用可用模态信息，提升分割性能。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/ Tue, 10 Jun 2025 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/ <p>热烈祝贺张哲宇同学！论文《Incomplete multi-modal brain tumor segmentation via learnable sorting state space model》已发表在 <em>CVPR</em>。</p> <h2 id="incomplete-multi-modal-brain-tumor-segmentation-via-learnable-sorting-state-space-model">Incomplete multi-modal brain tumor segmentation via learnable sorting state space model</h2> <p><strong>祝贺张哲宇同学！该论文已发表在 <em>CVPR</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Incomplete multi-modal brain tumor segmentation via learnable sorting state space model" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/images/paper-01_hu12446196012194697519.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/images/paper-01_hu11624591397241064252.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/images/paper-01_hu8784721236978794445.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/images/paper-01_hu12446196012194697519.webp" width="760" height="210" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Zheyu Zhang、Yayuan Lu、Feipeng Ma、Yueyi Zhang、Huanjing Yue、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>CVPR</em></li> <li><strong>发表时间：</strong> 2025年6月10日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11094296/" target="_blank" rel="noopener">论文链接</a> · <a href="https://openaccess.thecvf.com/content/CVPR2025/papers/Zhang_Incomplete_Multi-modal_Brain_Tumor_Segmentation_via_Learnable_Sorting_State_Space_CVPR_2025_paper.pdf" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出一种可学习排序状态空间模型（LS3M），用于不完整多模态脑肿瘤分割。该方法基于Mamba架构高效建模长距离依赖，并引入可微置换矩阵，根据模态特定特征对输入序列进行动态重排序，从而保留3D脑MRI中关键的空间归纳偏置与长程语义相关性。LS3M能够充分利用可用模态信息，提升分割性能。</p> https://vilab.team/publication/advancing-presurgical-non-invasive-molecular-subgroup-predic/ Mon, 08 Jul 2024 00:00:00 +0000 https://vilab.team/publication/advancing-presurgical-non-invasive-molecular-subgroup-predic/ <p>本文构建了涵盖中国和美国13个中心934例髓母细胞瘤患者的国际分子特征数据库，利用人工智能和MRI影像特征实现术前无创的分子亚型预测。通过交叉验证、外部验证和连续验证，证明了模型作为通用分子诊断分类器的有效性，并通过对MRI特征的详细分析，从影像学角度深化了对髓母细胞瘤的理解，为临床管理提供了低成本、可推广的替代路径。</p> https://vilab.team/publication/tmformer-token-merging-transformer-for-brain-tumor-segmentat/ Sun, 24 Mar 2024 00:00:00 +0000 https://vilab.team/publication/tmformer-token-merging-transformer-for-brain-tumor-segmentat/ <p>本文提出 TMFormer，一种用于缺失模态脑肿瘤分割的 Token 合并 Transformer。该方法通过提取并合并可用模态为更紧凑的 token 序列，解决现有方法以零图填充缺失模态带来的特征偏差与冗余计算问题。其核心包括单模态 Token 合并块（UMB）和多模态 Token 合并块（MMB），分别增强单模态表示并缓解多模态融合偏差。在 BraTS 2018 和 2020 数据集上的实验表明，TMFormer 在缺失模态场景下优于现有方法。</p> https://vilab.team/publication/anatomical-consistency-distillation-and-inconsistency-synthe/ Mon, 01 Jan 2024 00:00:00 +0000 https://vilab.team/publication/anatomical-consistency-distillation-and-inconsistency-synthe/ <p>本文提出ACDIS框架，用于解决脑肿瘤分割中MRI模态缺失的问题。通过解剖一致性蒸馏将多模态图像中的共享解剖结构迁移至单模态表示，并利用模态特征合成块生成模态特定特征，从而增强单模态图像在特定区域的组织表现。该方法有效缓解了模态缺失带来的性能下降，提升了分割精度。</p> https://vilab.team/publication/eoformer-edge-oriented-transformer-for-brain-tumor-segmentat/ Sun, 01 Oct 2023 00:00:00 +0000 https://vilab.team/publication/eoformer-edge-oriented-transformer-for-brain-tumor-segmentat/ <p>本文提出边缘导向Transformer（EoFormer），用于脑肿瘤MRI图像分割。该方法采用CNN-Transformer混合编码器，CNN提取局部低级特征，Transformer建模长距离依赖以生成全局高级特征；解码器集成边缘导向Sobel与Laplacian锐化模块，增强边缘信息。同时引入高效注意力与重参数化技术，提升特征表示能力与分割精度。</p>