当前位置: X-MOL 学术J. Comput. Des. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Intervertebral disc instance segmentation using a multistage optimization mask-RCNN (MOM-RCNN)
Journal of Computational Design and Engineering ( IF 4.8 ) Pub Date : 2021-06-18 , DOI: 10.1093/jcde/qwab030
Malinda Vania 1, 2 , Deukhee Lee 1, 2
Affiliation  

Lower back pain is one of the major global challenges in health problems. Medical imaging is rapidly taking a predominant position for the diagnosis and treatment of lower back abnormalities. Magnetic resonance imaging (MRI) is a primary tool for detecting anatomical and functional abnormalities in the intervertebral disc (IVD) and provides valuable data for both diagnosis and research. Deep learning methods perform well in computer visioning when labeled general image training data are abundant. In the practice of medical images, the labeled data or the segmentation data are produced manually. However, manual medical image segmentation leads to two main issues: much time is needed for delineation, and reproducibility is called into question. To handle this problem, we developed an automated approach for IVD instance segmentation that can utilize T1 and T2 images during this study to handle data limitation problems and computational time problems and improve the generalization of the algorithm. This method builds upon mask-RCNN; we proposed a multistage optimization mask-RCNN (MOM-RCNN) for deep learning segmentation networks. We used a multi-optimization training system by utilizing stochastic gradient descent and adaptive moment estimation (Adam) with T1 and T2 in MOM-RCNN. The proposed method showed a significant improvement in processing time and segmentation results compared to previous commonly used segmentation methods. We evaluated the results using several different key performance measures. We obtain the Dice coefficient (99%). Our method can define the IVD’s segmentation as much as 88% (sensitivity) and recognize the non-IVD as much as 98% (specificity). The results also obtained increasing precision (92%) with a low global consistency error (0.03), approaching 0 (the best possible score). On the spatial distance measures, the results show a promising reduction from 0.407 ± 0.067 mm in root mean square error to 0.095 ± 0.026 mm, Hausdorff distance from 12.313 ± 3.015 to 5.155 ± 1.561 mm, and average symmetric surface distance from 1.944 ± 0.850 to 0.49 ± 0.23 mm compared to other state-of-the-art methods. We used MRI images from 263 patients to demonstrate the efficiency of our proposed method.

中文翻译:

使用多级优化掩码-RCNN (MOM-RCNN) 进行椎间盘实例分割

腰痛是全球健康问题的主要挑战之一。医学成像正在迅速占据腰部异常的诊断和治疗的主导地位。磁共振成像 (MRI) 是检测椎间盘 (IVD) 解剖和功能异常的主要工具,可为诊断和研究提供有价值的数据。当标记的通用图像训练数据丰富时,深度学习方法在计算机视觉中表现良好。在医学图像的实践中,标记数据或分割数据是手动产生的。然而,手动医学图像分割导致两个主要问题:描绘需要大量时间,并且可重复性受到质疑。为了处理这个问题,我们开发了一种用于 IVD 实例分割的自动化方法,该方法可以在本研究期间利用 T1 和 T2 图像来处理数据限制问题和计算时间问题,并提高算法的泛化能力。该方法建立在 mask-RCNN 之上;我们为深度学习分割网络提出了一种多级优化掩码-RCNN(MOM-RCNN)。我们通过在 MOM-RCNN 中使用具有 T1 和 T2 的随机梯度下降和自适应矩估计 (Adam) 来使用多优化训练系统。与以前常用的分割方法相比,所提出的方法在处理时间和分割结果方面都有显着改善。我们使用几种不同的关键绩效指标评估了结果。我们获得了骰子系数 (99%)。我们的方法可以将 IVD 的分割定义为高达 88%(灵敏度),并可以识别高达 98%(特异性)的非 IVD。结果还获得了提高的精度 (92%),同时全局一致性误差 (0.03) 较低,接近 0(可能的最佳分数)。在空间距离测量方面,结果显示均方根误差从 0.407 ± 0.067 mm 有希望减少到 0.095 ± 0.026 mm,Hausdorff 距离从 12.313 ± 3.015 减少到 5.155 ± 1.561 mm,平均对称表面距离从 ± 1.9504 减少到与其他最先进的方法相比,0.49 ± 0.23 毫米。我们使用来自 263 名患者的 MRI 图像来证明我们提出的方法的效率。接近 0(最好的分数)。在空间距离测量方面,结果显示均方根误差从 0.407 ± 0.067 mm 有希望减少到 0.095 ± 0.026 mm,Hausdorff 距离从 12.313 ± 3.015 减少到 5.155 ± 1.561 mm,平均对称表面距离从 ± 1.9504 减少到与其他最先进的方法相比,0.49 ± 0.23 毫米。我们使用来自 263 名患者的 MRI 图像来证明我们提出的方法的效率。接近 0(最好的分数)。在空间距离测量方面,结果显示均方根误差从 0.407 ± 0.067 mm 有希望减少到 0.095 ± 0.026 mm,Hausdorff 距离从 12.313 ± 3.015 减少到 5.155 ± 1.561 mm,平均对称表面距离从 ± 1.9504 减少到与其他最先进的方法相比,0.49 ± 0.23 毫米。我们使用来自 263 名患者的 MRI 图像来证明我们提出的方法的效率。
更新日期:2021-06-30
down
wechat
bug