Abstract
Background: Accurate lesion segmentation is critical for multiple sclerosis (MS) diagnosis, yet current deep learning approaches face robustness challenges. Aim: This study improves MS lesion segmentation by combining data fusion and deep learning techniques. Materials and Methods: We suggested novel radiomic features (concentration rate and Rényi entropy) to characterize different MS lesion types and fused these with raw imaging data. The study integrated radiomic features with imaging data through a ResNeXt-UNet architecture and attention-augmented U-Net architecture. Our approach was evaluated on scans from 46 patients (1102 slices), comparing performance before and after data fusion. Results: The radiomics-enhanced ResNeXt-UNet demonstrated high segmentation accuracy, achieving significant improvements in precision and sensitivity over the MRI-only baseline and a Dice score of 0.774$\pm$0.05; p<0.001 according to Bonferroni-adjusted Wilcoxon signed-rank tests. The radiomics-enhanced attention-augmented U-Net model showed a greater model stability evidenced by reduced performance variability (SDD = 0.18 $\pm$ 0.09 vs. 0.21 $\pm$ 0.06; p=0.03) and smoother validation curves with radiomics integration. Conclusion: These results validate our hypothesis that fusing radiomics with raw imaging data boosts segmentation performance and stability in state-of-the-art models.
Abstract (translated)
背景：准确的病变分割对于多发性硬化症（MS）的诊断至关重要，然而目前的深度学习方法在鲁棒性方面面临挑战。目的：本研究通过结合数据融合和深度学习技术来改进MS病变分割。 材料与方法：我们提出了新颖的放射组学特征（浓度率和Rényi熵），用于表征不同类型的MS病灶，并将这些特征与原始影像数据进行融合。这项研究整合了放射组学特征和影像数据，通过ResNeXt-UNet架构和增强注意力的U-Net架构实现。我们的方法在46名患者（1102个切片）的扫描上进行了评估，在数据融合前后对比性能表现。 结果：放射组学增强的ResNeXt-UNet展示了高分割准确性，与仅使用MRI基线相比，在精度和敏感度方面取得了显著提升，并且Dice得分达到了0.774±0.05；根据Bonferroni校正后的Wilcoxon符号秩检验结果，p<0.001。放射组学增强的注意力增强U-Net模型通过减少性能变异性（SDD = 0.18±0.09 对比 0.21±0.06； p=0.03）和结合放射组学后验证曲线更加平滑，显示出了更大的模型稳定性。 结论：这些结果证实了我们的假设，即通过将放射组学与原始影像数据融合可以提升最先进的模型的分割性能和稳定性。
URL
https://arxiv.org/abs/2506.14524
