分两阶段精准分割肠道磁共振图像中的10个器官，提升炎症性肠病诊断效率。
A Two-Stage Deep Learning Framework for Segmentation of Ten Gastrointestinal Organs from Coronal MR Enterography
- 先粗后精：用两个深度网络分步定位并细化肠道器官边界
- 整体分割精度达mDSC 88.99%，附录等小器官性能显著提升
- 适合临床科研人员开发智能肠镜辅助诊断工具
准确分割磁共振肠造影（MRE）中的胃肠道（GI）器官对炎症性肠病（IBD）诊断至关重要。但解剖变异、类别不平衡和组织对比度低阻碍了自动化实现。本研究提出一种双阶段深度学习框架，针对冠状面MRE图像中的胃肠结构进行器官特异性分割。使用包含114例IBD患者共3,195张冠状面T2加权HASTE序列图像的公开数据集。第一阶段采用DenseNet201-UNet++模型生成粗略掩码以提取感兴趣区域（ROI）。第二阶段在器官特异性补丁上训练DenseNet121-SelfONN-UNet模型。通过广泛的数据增强、归一化、五折交叉验证及类别特定加权缓解严重类别不平衡，尤其是附录。第一阶段虽实现良好器官定位，但附录表现差；类别加权使其Dice相似系数（DSC）从6.76%提升至85.76%。第二阶段模型显著提升所有胃肠道结构分割效果，尤其在盲肠（+23.62%）、乙状结肠（+18.57%）、直肠（+17.99%）和小肠（+16.06%）上取得明显提升。整体框架实现平均DSC 88.99%、平均IoU 84.76%、平均豪斯多夫距离95%（mHD95）6.94 mm，优于所有基线方法。该框架验证了粗粒度到细粒度、器官感知分割策略在肠道MRE中的有效性。尽管计算成本较高，但具有较强临床转化潜力，可支持消化内科中基于解剖结构的智能诊断工具开发。
原文摘要 · Abstract (English)
Accurate segmentation of gastrointestinal (GI) organs in magnetic resonance enterography (MRE) is critical for diagnosing inflammatory bowel disease (IBD). However, anatomical variability, class imbalance, and low tissue contrast hinder reliable automation. This study proposes a dual-stage deep learning framework for organ-specific segmentation of GI structures from coronal MRE images to address these challenges. A publicly available MRE dataset of 3,195 coronal T2-weighted HASTE slices from 114 IBD patients was used. Initially, a DenseNet201-UNet++ model generated coarse masks for ROI extraction. A DenseNet121-SelfONN-UNet model was then trained on organ-specific patches. Extensive data augmentation, normalization, five-fold cross-validation, and class-specific weighting were applied to mitigate severe class imbalance, particularly for the appendix. The initial stage achieved strong organ localization but underperformed for the appendix; class weighting improved its DSC from 6.76% to 85.76%. The second-stage DenseNet121-SelfONN-UNet significantly enhanced segmentation across all GI structures, with notable DSC gains (cecum +23.62%, sigmoid +18.57%, rectum +17.99%, small intestine +16.06%). Overall, the framework achieved mDSC of 88.99%, mIoU of 84.76%, and mHD95 of 6.94 mm, outperforming all baselines. This framework demonstrates the effectiveness of a coarse-to-fine, organ-aware segmentation strategy for intestinal MRE. Despite higher computational cost, it shows strong potential for clinical translation and enables anatomically informed diagnostic tools in gastroenterology.
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。