Gui Chengzhi, An Xingwei, Li Tingting, Liu Shuang, Ming Dong
Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China.
Quant Imaging Med Surg. 2024 Dec 5;14(12):9459-9476. doi: 10.21037/qims-24-725. Epub 2024 Nov 29.
Stroke is one of the leading causes of disability and death worldwide. Ischemic stroke accounts for 75-90% of all stroke incidents. Assessing the size and location of the stroke lesion is crucial for treatment decisions, especially those related to urgent vascular reconstruction surgery. Magnetic resonance imaging (MRI) offers excellent soft tissue contrast and multimodal imaging characteristics, which can reflect changes in the physiological functions of brain soft tissues in patients with ischemic stroke. However, using deep learning (DL) techniques for MRI segmentation of stroke lesions still faces many challenges. On the one hand, single-modal segmentation models cannot effectively integrate multimodal information; on the other hand, there is a semantic content drift between multimodal stroke MRI images, leading to lower accuracy in subsequent multimodal image segmentation. To address these issues, we aimed to propose the stroke unsupervised registration and segmentation (St-RegSeg) framework.
The St-RegSeg framework integrates an unsupervised registration model, ConvNXMorph, and a segmentation model, nnUNet-v2, enabling both registration and segmentation of multimodal MRI images. The St-RegSeg framework was evaluated on the ISLES'22 dataset from three centers.
The St-RegSeg framework demonstrated significant improvements in performance metrics and computational efficiency. Compared to advanced normalization tools (ANTs) [symmetric normalization (SyN)] + nnUNet-v2, the St-RegSeg framework improved the Dice similarity coefficient (DSC) by 25.31% in the registration phase, reduced mean squared error (MSE) by 17.36%, increased normalized cross-correlation (NCC) by 16.06%, and enhanced mutual information (MI) by 17.09%. Additionally, in the segmentation phase, it increased the DSC by 0.84%, and the overall inference speed was increased by 40.91 times. Compared to the suboptimal TransMorph + nnUNet-v2, the St-RegSeg framework improved the DSC by 3.68% in the registration phase, reduced MSE by 8.91%, increased NCC by 8.49%, enhanced MI by 6.18%, and in the segmentation phase, it raised the DSC by 0.5%, with the overall inference speed increased by 2.13 times.
The St-RegSeg framework provides a highly effective solution for the registration and segmentation of multimodal MRI images in ischemic stroke cases. Its performance metrics and computational efficiency significantly outperform existing methods, making it a promising tool for clinical applications. The code is open-sourced and available at: https://github.com/Cooper-Gu/St-RegSeg.
中风是全球致残和致死的主要原因之一。缺血性中风占所有中风事件的75 - 90%。评估中风病灶的大小和位置对于治疗决策至关重要，特别是与紧急血管重建手术相关的决策。磁共振成像（MRI）具有出色的软组织对比度和多模态成像特性，能够反映缺血性中风患者脑软组织生理功能的变化。然而，使用深度学习（DL）技术对中风病灶进行MRI分割仍面临诸多挑战。一方面，单模态分割模型无法有效整合多模态信息；另一方面，多模态中风MRI图像之间存在语义内容漂移，导致后续多模态图像分割的准确性降低。为解决这些问题，我们旨在提出中风无监督配准与分割（St-RegSeg）框架。
St-RegSeg框架整合了无监督配准模型ConvNXMorph和分割模型nnUNet-v2，实现多模态MRI图像的配准和分割。该框架在来自三个中心的ISLES'22数据集上进行了评估。
St-RegSeg框架在性能指标和计算效率方面展现出显著提升。与先进的归一化工具（ANTs）[对称归一化（SyN）]+nnUNet-v2相比，St-RegSeg框架在配准阶段将骰子相似系数（DSC）提高了25.31%，均方误差（MSE）降低了17.36%，归一化互相关（NCC）提高了16.06%，互信息（MI）增强了17.09%。此外，在分割阶段，它将DSC提高了0.84%，整体推理速度提高了40.91倍。与次优的TransMorph + nnUNet-v2相比，St-RegSeg框架在配准阶段将DSC提高了3.68%，MSE降低了8.91%，NCC提高了8.49%，MI增强了6.18%，在分割阶段，它将DSC提高了0.5%，整体推理速度提高了2.13倍。
St-RegSeg框架为缺血性中风病例的多模态MRI图像配准和分割提供了一种高效的解决方案。其性能指标和计算效率显著优于现有方法，使其成为临床应用中一个很有前景的工具。代码已开源，可在以下网址获取：https://github.com/Cooper-Gu/St-RegSeg。
