ScarNet可精准自动量化心脏磁共振瘢痕，提升诊断效率与一致性
ScarNet: A Novel Foundation Model for Automated Myocardial Scar Quantification from LGE in Cardiac MRI
- 融合Transformer与U-Net，设计专用注意力模块增强分割能力
- 测试集平均Dice达0.912，显著优于MedSAM与nnU-Net
- 对噪声鲁棒性强，适合临床真实场景中复杂瘢痕分析
背景：晚期钆增强（LGE）成像是评估心肌纤维化和瘢痕的金标准，左室（LV）LGE范围可预测主要不良心脏事件（MACE）。尽管重要，常规的基于LGE的左室瘢痕定量仍受限于人工分割耗时及观察者间差异。方法：我们提出ScarNet，一种结合MedSAM中Transformer编码器与卷积U-Net解码器的混合模型，并引入定制注意力块。该模型在552例缺血性心肌病患者（含专家标注的心肌与瘢痕边界）上训练，于184例独立患者上测试。结果：在184名测试患者中，ScarNet实现稳健的瘢痕分割，中位Dice分数为0.912（IQR：0.863–0.944），显著优于MedSAM（中位数Dice=0.046，IQR：0.043–0.047）和nnU-Net（中位数Dice=0.638，IQR：0.604–0.661）。ScarNet偏差更低（-0.63%），变异系数更小（4.3%），优于MedSAM（偏差：-13.31%，CoV：130.3%）和nnU-Net（偏差：-2.46%，CoV：20.3%）。蒙特卡洛噪声扰动模拟中，ScarNet瘢痕Dice为0.892±0.053（CoV=5.9%），显著高于MedSAM（0.048±0.112，CoV=233.3%）和nnU-Net（0.615±0.537，CoV=28.7%）。结论：ScarNet在准确分割LGE图像的心肌与瘢痕边界方面优于MedSAM与nnU-Net，且在多种图像质量与瘢痕模式下表现稳健。
原文摘要 · Abstract (English)
Background: Late Gadolinium Enhancement (LGE) imaging is the gold standard for assessing myocardial fibrosis and scarring, with left ventricular (LV) LGE extent predicting major adverse cardiac events (MACE). Despite its importance, routine LGE-based LV scar quantification is hindered by labor-intensive manual segmentation and inter-observer variability. Methods: We propose ScarNet, a hybrid model combining a transformer-based encoder from the Medical Segment Anything Model (MedSAM) with a convolution-based U-Net decoder, enhanced by tailored attention blocks. ScarNet was trained on 552 ischemic cardiomyopathy patients with expert segmentations of myocardial and scar boundaries and tested on 184 separate patients. Results: ScarNet achieved robust scar segmentation in 184 test patients, yielding a median Dice score of 0.912 (IQR: 0.863--0.944), significantly outperforming MedSAM (median Dice = 0.046, IQR: 0.043--0.047) and nnU-Net (median Dice = 0.638, IQR: 0.604--0.661). ScarNet demonstrated lower bias (-0.63%) and coefficient of variation (4.3%) compared to MedSAM (bias: -13.31%, CoV: 130.3%) and nnU-Net (bias: -2.46%, CoV: 20.3%). In Monte Carlo simulations with noise perturbations, ScarNet achieved significantly higher scar Dice (0.892 \pm 0.053, CoV = 5.9%) than MedSAM (0.048 \pm 0.112, CoV = 233.3%) and nnU-Net (0.615 \pm 0.537, CoV = 28.7%). Conclusion: ScarNet outperformed MedSAM and nnU-Net in accurately segmenting myocardial and scar boundaries in LGE images. The model exhibited robust performance across diverse image qualities and scar patterns.
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。