用跨中心影像校准+多平面融合，自动精准识别直肠癌侵袭信号。
A Pre-trained Foundation Model Framework for Multiplanar MRI Classification of Extramural Vascular Invasion and Mesorectal Fascia Invasion in Rectal Cancer
- 基于频域校准和多平面融合的预训练模型框架
- 对EVI和MFI分类AUC分别达0.82和0.77，优于基准
- 结果可解释，注意力聚焦于生物学相关区域
准确识别直肠癌患者的外膜血管侵犯（EVI）和筋膜侵犯（MFI）对风险分层治疗至关重要。然而，主观阅片和机构间差异限制了诊断一致性。本研究构建并外部验证了一个多中心、基于基础模型的框架，可自动分类轴位与矢状位MRI上的EVI与MFI。共纳入三家欧洲医院331例术前直肠癌患者T2加权MRI扫描。采用自监督频域校准策略减少扫描仪差异。训练三类分类器：SeResNet、通用生物医学预训练模型（UMedPT）搭配MLP头，以及使用冻结的UMedPT特征的逻辑回归变体（UMedPT_LR），在265例上训练，66例上测试。通过梯度加权类激活映射（Grad-CAM）可视化模型预测。结果显示，UMedPT_LR在多平面融合下对EVI表现最佳（测试集AUC=0.82）；在轴位校准图像上训练的UMedPT对MFI表现最优（AUC=0.77）。两项任务均优于CHAIMELEON 2024基准（EVI: 0.82 vs 0.74；MFI: 0.77 vs 0.75）。校准提升MFI分类性能，多平面融合进一步增强EVI表现。Grad-CAM确认模型关注区域具有生物学合理性（EVI：肿瘤周围；MFI：筋膜边缘）。结论表明，该基础模型驱动框架结合频域校准与多平面融合，实现了多中心环境下自动分类EVI与MFI的最先进性能，具备强泛化能力。
原文摘要 · Abstract (English)
Objectives Accurate MRI-based identification of extramural vascular invasion (EVI) and mesorectal fascia invasion (MFI) is crucial for risk-stratified rectal cancer treatment. However, subjective visual assessment and inter-institutional variability limit diagnostic consistency. This study developed and externally evaluated a multi-centre, foundation model-driven framework that automatically classifies EVI and MFI on axial and sagittal MRI. Methods A total of 331 pre-treatment rectal cancer T2-weighted MRI scans from three European hospitals were retrospectively recruited. A self-supervised frequency domain harmonization strategy was applied to reduce scanner variability. Three classifiers, SeResNet, the universal biomedical pretrained model (UMedPT) with a multilayer perceptron head, and a logistic-regression variant using frozen UMedPT features (UMedPT_LR), were trained (n=265) and tested (n=66). Gradient-weighted class activation mapping (Grad-CAM) visualized model predictions. Results UMedPT_LR achieved the best EVI performance with multiplanar fusion (AUC=0.82, test set). For MFI, UMedPT trained on axial harmonized images yielded the highest performance (AUC = 0.77). Both tasks outperformed the CHAIMELEON 2024 benchmark (EVI: 0.82 vs 0.74; MFI: 0.77 vs 0.75). Harmonization enhanced MFI classification, and multiplanar fusion further boosted EVI performance. Grad-CAM confirmed biologically plausible attention on peritumoral regions (EVI) and mesorectal fascia margins (MFI). Conclusion The proposed foundation model-driven framework, leveraging frequency domain harmonization and multiplanar fusion, achieves state-of-the-art performance for automated EVI and MFI classification on MRI, demonstrating strong generalizability across multiple centers.
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。