Department of Ultrasound, The Second Hospital of Dalian Medical University, Dalian City, 116027 Liaoning Province, China.
Department of Wound Repair, The Second Hospital of Dalian Medical University, Dalian City, 116027 Liaoning Province, China.
Comput Math Methods Med. 2022 Mar 24;2022:5466173. doi: 10.1155/2022/5466173. eCollection 2022.
This study was aimed at exploring the diagnostic value of high-frequency ultrasound imaging based on a fully convolutional neural network (FCN) for peripheral neuropathy in patients with type 2 diabetes (T2D). A total of 70 patients with T2D mellitus were selected and divided into a lesion group ( = 31) and a nonlesion group ( = 39) according to the type of peripheral neuropathy. In addition, 30 healthy people were used as controls. Hypervoxel-based and FCN-based high-frequency ultrasound images were used to examine the three groups of patients to evaluate their diagnostic performance and to compare the changes of peripheral nerves and ultrasound characteristics. The results showed that the Dice coefficient (92.7) and mean intersection over union (mIOU) (82.6) of the proposed algorithm after image segmentation were the largest, and the Hausdorff distance (7.6) and absolute volume difference (AVD) (8.9) were the smallest. The high-frequency ultrasound based on the segmentation algorithm showed higher diagnostic accuracy (94.0% vs. 86.0%), sensitivity (87.1% vs. 67.7%), specificity (97.1% vs. 94.2%), positive predictive value (93.1% vs. 86.7%), and negative predictive value (94.4% vs. 84.0%) ( < 0.05). There were significant differences in the detection values of the three major nerve segments of the upper limbs in the control group, the lesion group, and the nonlesion group ( < 0.05). Compared with the nonlesion group, the patients in the lesion group were more likely to have reduced nerve bundle echo, blurred reticular structure, thickened epineurium, and unclear borders of adjacent tissues ( < 0.05). In summary, the high-frequency ultrasound processed by the algorithm proposed in this study showed a high diagnostic value for peripheral neuropathy in T2D patients, and high-frequency ultrasound can be used to evaluate the morphological changes of peripheral nerves in T2D patients.
本研究旨在探索基于全卷积神经网络（FCN）的高频超声成像对 2 型糖尿病（T2D）患者周围神经病变的诊断价值。选择 70 例 T2D 患者，根据周围神经病变类型分为病变组（=31 例）和非病变组（=39 例）。此外，选择 30 名健康人作为对照组。采用超像素和 FCN 两种基于高频超声图像的方法对三组患者进行检测，评估其诊断效能，并比较各组患者外周神经的超声特征变化。结果显示，所提出的图像分割算法的 Dice 系数（92.7）和平均交并比（mIOU）（82.6）最大，Hausdorff 距离（7.6）和绝对体积差（AVD）（8.9）最小。基于分割算法的高频超声具有较高的诊断准确性（94.0%比 86.0%）、敏感性（87.1%比 67.7%）、特异性（97.1%比 94.2%）、阳性预测值（93.1%比 86.7%）和阴性预测值（94.4%比 84.0%）（<0.05）。对照组、病变组和非病变组三组上肢主要神经节段的检出值比较差异有统计学意义（<0.05）。与非病变组相比，病变组患者神经束回声减弱、网织结构模糊、神经外膜增厚、毗邻组织边界不清的检出率更高（<0.05）。综上，该研究提出的算法处理后的高频超声对 T2D 患者周围神经病变具有较高的诊断价值，高频超声可用于评估 T2D 患者周围神经的形态学变化。
