揭示不完整模态脑肿瘤分割：利用掩码预测自编码器与散度学习
Unveiling Incomplete Modality Brain Tumor Segmentation: Leveraging Masked Predicted Auto-Encoder and Divergence Learning
AI总结：
本文针对多模态MRI脑肿瘤分割中模态缺失问题，提出掩码预测预训练结合Holder伪散度知识蒸馏的新策略，在BRATS2018和BRATS2020数据集上显著提升了分割性能。
摘要：
脑肿瘤分割仍然是一项重大挑战，特别是在多模态磁共振成像（MRI）的背景下，临床环境中缺失模态图像十分常见，导致分割精度下降。为了解决这一问题，我们提出了一种新策略，称为掩码预测预训练，能够从不完整模态数据中学习鲁棒特征。此外，在微调阶段，我们利用知识蒸馏技术对齐完整模态数据与缺失模态数据之间的特征，同时增强模型鲁棒性。值得注意的是，我们采用Holder伪散度代替KLD作为蒸馏损失，提供了更好的数学可解释性和性质。在BRATS2018和BRATS2020数据集上的大量实验表明，与现有最先进方法相比，性能显著提升。
英文摘要：
Brain tumor segmentation remains a significant challenge, particularly in the context of multi-modal magnetic resonance imaging (MRI) where missing modality images are common in clinical settings, leading to reduced segmentation accuracy. To address this issue, we propose a novel strategy, which is called masked predicted pre-training, enabling robust feature learning from incomplete modality data. Additionally, in the fine-tuning phase, we utilize a knowledge distillation technique to align features between complete and missing modality data, simultaneously enhancing model robustness. Notably, we leverage the Holder pseudo-divergence instead of the KLD for distillation loss, offering improve mathematical interpretability and properties. Extensive experiments on the BRATS2018 and BRATS2020 datasets demonstrate significant performance enhancements compared to existing state-of-the-art methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
