Fifth Affiliated Hospital of Sun Yat-sen University, Spinal surgery, Zhuhai, Guangdong, China.
Fifth Affiliated Hospital of Sun Yat-sen University, Radiology, Zhuhai, Guangdong, China.
Pain Physician. 2022 Jan;25(1):E27-E35.
Segmentation of spinal structures is important in medical imaging analysis, which facilitates surgeons to plan a preoperative trajectory for the transforaminal approach. However, manual segmentation of spinal structures is time-consuming, and studies have not explored automatic segmentation of spinal structures at the L5/S1 level.
This study sought to develop a new method based on a deep learning algorithm for automatic segmentation of spinal structures. The resulting algorithm may be used to rapidly generate a precise 3D lumbosacral intervertebral foramen model to assist physicians in planning an ideal trajectory in L5/S1 lumbar transforaminal radiofrequency ablation (LTRFA).
This was an observational study for developing a new technique on spinal structures segmentation.
The study was carried out at the department of radiology and spine surgery at our hospital.
A total of 100 L5/S1 level data samples from 100 study patients were used in this study. Masks of vertebral bone structures (VBSs) and intervertebral discs (IVDs) for all data samples were segmented manually by a skilled surgeon and served as the "ground truth." After data preprocessing, a 3D-UNet model based on deep learning was used for automated segmentation of lumbar spine structures at L5/S1 level magnetic resonance imaging (MRI). Segmentation performances and morphometric measurement were used for 3D lumbosacral intervertebral foramen (LIVF) reconstruction generated by either manual segmentation and automatic segmentation.
The 3D-UNet model showed high performance in automatic segmentation of lumbar spinal structures (VBSs and IVDs). The corresponding mean Dice similarity coefficient (DSC) of 5-fold cross-validation scores for L5 vertebrae, IVDs, S1 vertebrae, and all L5/S1 level spinal structures were 93.46 ± 2.93%, 90.39 ± 6.22%, 93.32 ± 1.51%, and 92.39 ± 2.82%, respectively. Notably, the analysis showed no associated difference in morphometric measurements between the manual and automatic segmentation at the L5/S1 level.
Semantic segmentation of multiple spinal structures (such as VBSs, IVDs, blood vessels, muscles, and ligaments) was simultaneously not integrated into the deep-learning method in this study. In addition, large clinical experiments are needed to evaluate the clinical efficacy of the model.
The 3D-UNet model developed in this study based on deep learning can effectively and simultaneously segment VBSs and IVDs at L5/S1 level formMR images, thereby enabling rapid and accurate 3D reconstruction of LIVF models. The method can be used to segment VBSs and IVDs of spinal structures on MR images within near-human expert performance; therefore, it is reliable for reconstructing LIVF for L5/S1 LTRFA.
脊柱结构的分割在医学成像分析中很重要，这有助于外科医生规划经椎间孔入路的术前轨迹。然而，脊柱结构的手动分割非常耗时，并且尚未研究 L5/S1 水平的脊柱结构的自动分割。
本研究旨在开发一种基于深度学习算法的新方法，用于自动分割脊柱结构。由此产生的算法可用于快速生成精确的腰骶椎间孔 3D 模型，以帮助医生在 L5/S1 腰椎经椎间孔射频消融 (LTRFA) 中规划理想的轨迹。
这是一项关于脊柱结构分割新技术的观察性研究。
本研究在我院放射科和脊柱外科进行。
本研究共使用了 100 名研究患者的 100 个 L5/S1 水平数据样本。所有数据样本的椎骨结构 (VBS) 和椎间盘 (IVD) 蒙版均由熟练的外科医生手动分割，并作为“真实数据”。在数据预处理之后，使用基于深度学习的 3D-UNet 模型对 L5/S1 水平磁共振成像 (MRI) 的腰椎结构进行自动分割。手动分割和自动分割生成的 3D 腰骶椎间孔 (LIVF) 重建分别用于分割性能和形态测量。
3D-UNet 模型在自动分割腰椎脊柱结构 (VBS 和 IVD) 方面表现出较高的性能。5 折交叉验证得分的相应平均 Dice 相似系数 (DSC) 分别为 L5 椎体、IVD、S1 椎体和所有 L5/S1 水平脊柱结构的 93.46 ± 2.93%、90.39 ± 6.22%、93.32 ± 1.51%和 92.39 ± 2.82%。值得注意的是，分析表明手动和自动分割在 L5/S1 水平的形态测量结果无差异。
本研究中的深度学习方法并未同时对多个脊柱结构（如 VBS、IVD、血管、肌肉和韧带）进行语义分割。此外，需要进行大型临床实验来评估该模型的临床疗效。
本研究基于深度学习开发的 3D-UNet 模型可以有效地同时分割 L5/S1 水平 MR 图像中的 VBS 和 IVD，从而实现 LIVF 模型的快速准确 3D 重建。该方法可达到接近人类专家水平的脊柱结构 VBS 和 IVD 分割效果，因此可用于 L5/S1 LTRFA 的 LIVF 重建。
