一个统一框架，一次训练就能跨模态矫正各类医学影像运动伪影。
A Unified Deep Learning Framework for Motion Correction in Medical Imaging
- 用统一损失函数联合训练刚性与局部变形校正网络。
- 单次训练后在多模态数据上保持高精度与稳定性。
- 适合需要跨设备、跨模态的医学影像运动校正场景。
深度学习在医学图像配准用于运动校正方面展现出巨大潜力，但现有方法或受限于可处理运动类型与范围，或需对新数据进行迭代推理和/或重新训练。为此，我们提出UniMo——一种统一运动校正框架，利用深度神经网络校正医学影像中的多种运动。UniMo采用交替优化方案，通过统一损失函数训练集成模型：1）等变神经网络用于全局刚性运动校正；2）编码器-解码器网络用于局部形变校正。其几何形变增强器一方面提升全局运动校正对局部形变的鲁棒性，另一方面生成增强数据以优化训练过程。UniMo为混合模型，结合图像强度与形状信息，在图像外观变化下表现稳健，因此无需重训练即可泛化至多种医学成像模态。我们在胎儿磁共振成像中训练并测试UniMo，随后在三个公开数据集（MedMNIST、肺部CT、BraTS）的多种模态上无重训练测试。结果表明，UniMo在准确性上超越现有方法，尤其实现了仅一次训练即可在多个未见数据集上保持高稳定性和适应性，为兼具大范围运动与局部形变的复杂应用提供统一解决方案。
原文摘要 · Abstract (English)
Deep learning has shown significant value in medical image registration for motion correction, however, current techniques are either limited by the type and range of motion they can handle, or require iterative inference and/or retraining for new imaging data. To address these limitations, we introduce UniMo, a Unified Motion Correction framework that leverages deep neural networks to correct for various types of motion in medical imaging. UniMo exploits an alternating optimization scheme for a unified loss function to train an integrated model of 1) an equivariant neural network for global rigid motion correction and 2) an encoder-decoder network to correct local deformations. It features a geometric deformation augmenter that 1) enhances the robustness of global motion correction by addressing any local deformations, and 2) generates augmented data to improve the training process. UniMo is a hybrid model that uses both image intensities and shapes to achieve robust performance amid image appearance variations, and, therefore, it generalizes well to various medical imaging modalities without a need for network retraining. We trained and tested UniMo to track motion in fetal magnetic resonance imaging. Then we tested the trained model, without retraining, on various image modalities from three public datasets, including MedMNIST, lung CT, and BraTS. The results show that UniMo surpassed existing motion correction methods in terms of accuracy, and, notably, it enabled one-time training on a single modality while maintaining high stability and adaptability for inference across multiple unseen imaging datasets. By offering a unified solution, UniMo marks a significant advantage in challenging applications with a mixture of bulk motion and local deformations. https://github.com/IntelligentImaging/UNIMO
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。