Deep Learning Spinal Cord Segmentation Based on B0 Reference for Diffusion Tensor Imaging Analysis in Cervical Spondylotic Myelopathy

Abstract

Diffusion Tensor Imaging (DTI) is a crucial imaging technique for accurately assessing pathological changes in Cervical Spondylotic Myelopathy (CSM). However, the segmentation of spinal cord DTI images primarily relies on manual methods, which are labor-intensive and heavily dependent on the subjective experience of clinicians, and existing research on DTI automatic segmentation cannot fully satisfy clinical requirements. Thus, this poses significant challenges for DTI-assisted diagnostic decision-making. This study aimed to deliver AI-driven segmentation for spinal cord DTI. To achieve this goal, a comparison experiment of candidate input features was conducted, with the preliminary results confirming the effectiveness of applying a diffusion-free image (B0 image) for DTI segmentation. Furthermore, a deep-learning-based model, named SCS-Net (Spinal Cord Segmentation Network), was proposed accordingly. The model applies a classical U-shaped architecture with a lightweight feature extraction module, which can effectively alleviate the training data scarcity problem. The proposed method supports eight-region spinal cord segmentation, i.e., the lateral, dorsal, ventral, and gray matter areas on the left and right sides. To evaluate this method, 89 CSM patients from a single center were collected. The model demonstrated satisfactory accuracy for both general segmentation metrics (precision, recall, and Dice coefficient) and a DTI-specific feature index. In particular, the proposed model's error rate for the DTI-specific feature index was evaluated as 5.32%, 10.14%, 7.37%, and 5.70% on the left side, and 4.60%, 9.60%, 8.74%, and 6.27% on the right side of the spinal cord, respectively, affirming the model's consistent performance for radiological rationality. In conclusion, the proposed AI-driven segmentation model significantly reduces the dependence on DTI manual interpretation, providing a feasible solution that can improve potential diagnostic outcomes for patients.

Keywords: cervical spondylotic myelopathy; deep learning; diffusion tensor imaging; medical image segmentation.

Figure A1

The loss of SCS-Net during the training process.

Figure 1

Spinal cord anatomical-level ROI visualization, in the segmentation experiment, the ROI definitions distinguished between the anatomical structures on the left and right sides, including the left lateral column (L_LC), left dorsal column (L_DC), left ventral column (L_VC), left gray matter(L_GM), right lateral column (R_LC), right dorsal column (R_DC), right ventral column (R_VC), and right gray matter (R_GM).

Figure 2

The structure of the proposed segmentation model SCS-Net.

Figure 3

The structure of the feature extraction block of SCS-Net.

Figure 4

The design of the proposed segmentation pipeline, major steps including image registration, segmentation model configuration, and result visualization.

Figure 5

The Dice performance of the different input features for segmentation, ROIs including left lateral column (L_LC), left dorsal column (L_DC), left ventral column (L_VC), left gray matter (L_GM), right lateral column (R_LC), right dorsal column (R_DC), right ventral column (R_VC), right gray matter (R_GM), and Mean result.

Figure 6

The Dice results of segmentation model performance under DTI B0 images.

Figure 7

The segmentation results predicted on the sample DTI slice.

Figure 8

The Visualization of segmentation results. Three samples has been demonstrated. (a) sample input DTI slice, (b) visualization of labeled ground truth, and (c) visualization of segmentation prediction.