用扩散模型精修儿童脑瘤分割边界，提升精准度与临床可解释性。
Diffusion-Refined Segmentation and Vision-Language Interpretation for Pediatric Brain Tumor MRI
- 先用3D Swin-UNETR粗分割，再用条件扩散模型细化边界。
- 条件扩散模型使增强肿瘤边界分割的HD95降低至2.18，精度显著提升。
- 融合分割结果与语言模型，自动生成结构化放射科报告，适合儿科神经肿瘤场景。
由于标注数据有限、影像表型异质性强、肿瘤边界模糊及不同亚区类别不平衡，儿童脑瘤精确分割仍具挑战。本文提出两阶段深度学习框架，用于多模态儿童脑MRI分割与临床解读。首先，在BraTS-PEDs MRI数据上评估3D Res U-Net与Swin-UNETR基线模型，利用四种配准模态预测肿瘤核心、全肿瘤和增强肿瘤区域。其次，引入基于扩散的精修模型，以粗略的Swin-UNETR预测为条件，包括3D DDPM refiner和MedSegDiff。条件化显著提升扩散模型稳定性与性能，尤其在增强肿瘤边界分割方面表现优异。条件化MedSegDiff在边界一致性上达到最优，HD95最低（2.18）。最后，将预测的肿瘤体积与代表性分割叠加图整合至多模态语言模型，生成结构化放射科风格报告。结果表明，从粗到精的扩散分割策略能有效改善儿童脑瘤边界界定，并支持端到端可解释的AI辅助神经肿瘤学工作流。
原文摘要 · Abstract (English)
Accurate pediatric brain tumor segmentation remains challenging due to limited annotated data, heterogeneous imaging phenotypes, diffuse tumor boundaries, and class imbalance across tumor subregions. Here, we present a two-stage deep learning framework for improving multi-modal pediatric brain MRI segmentation and clinical interpretation. First, we evaluate 3D Res U-Net and Swin-UNETR baselines on BraTS-PEDs MRI scans, using four co-registered modalities to predict tumor core, whole tumor, and enhancing tumor regions. Second, we introduce diffusion-based refinement models conditioned on coarse Swin-UNETR predictions, including a 3D DDPM refiner and MedSegDiff. Conditioning substantially improves diffusion stability and performance, particularly for enhancing tumor boundary segmentation. Conditioned MedSegDiff achieves the strongest boundary agreement with the lowest HD95. Finally, predicted tumor volumes and representative segmentation overlays are integrated with a multimodal language model to generate structured radiology-style reports. Together, our results suggest that coarse-to-refined diffusion segmentation can improve pediatric tumor boundary delineation and support end-to-end interpretable AI-assisted neuro-oncology workflows.
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。