RETRACTED: Fully Convolutional Neural Network Deep Learning Model Fully in Patients with Type 2 Diabetes Complicated with Peripheral Neuropathy by High-Frequency Ultrasound Image (Retracted Article)

被引:5
|
作者
Liu, Xiaoqiang [1 ]
Zhou, Hongyan [1 ]
Wang, Zhaoyun [2 ]
Liu, Xiaoli [3 ]
Li, Xin [4 ]
Nie, Chen [5 ]
Li, Yang [1 ]
机构
[1] Dalian Med Univ, Dept Ultrasound, Hosp 2, Dalian 116027, Liaoning, Peoples R China
[2] Dalian Med Univ, Hosp 2, Dept Wound Repair, Dalian 116027, Liaoning, Peoples R China
[3] Dalian Med Univ, Hosp 2, Dept Resp, Dalian 116027, Liaoning, Peoples R China
[4] Dalian Med Univ, Hosp 2, Dept Radiol, Dalian 116027, Liaoning, Peoples R China
[5] Dalian Med Univ, Hosp 2, Dept Neurol, Dalian 116027, Liaoning, Peoples R China
关键词
MELLITUS; PREVALENCE; FALLS;
D O I
10.1155/2022/5466173
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
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 (n = 31) and a nonlesion group (n = 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%) (P < 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 (P < 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 (P <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.
引用
收藏
页数:8
相关论文
共 8 条
  • [1] RETRACTED: Applicability of High-Frequency Ultrasound to the Early Diagnosis of Diabetic Peripheral Neuropathy (Retracted Article)
    Ma, Xishun
    Li, Tongxia
    Du, Lizhen
    Liu, Gang
    Sun, Ting
    Han, Tongliang
    [J]. BIOMED RESEARCH INTERNATIONAL, 2021, 2021
  • [2] RETRACTED: High-Resolution Computer Tomography Image Features of Lungs for Patients with Type 2 Diabetes under the Faster-Region Recurrent Convolutional Neural Network Algorithm (Retracted Article)
    He, Yumei
    Tan, Juan
    Han, Xiuping
    [J]. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2022, 2022
  • [3] One-Step Deep Learning Approach to Ultrasound Image Formation and Image Segmentation with a Fully Convolutional Neural Network
    Nair, Arun Asokan
    Tran, Trac D.
    Reiter, Austin
    Bell, Muyinatu A. Lediju
    [J]. 2019 IEEE INTERNATIONAL ULTRASONICS SYMPOSIUM (IUS), 2019, : 1481 - 1484
  • [4] RETRACTED: Application of local fully Convolutional Neural Network combined with YOLO v5 algorithm in small target detection of remote sensing image (Retracted Article)
    Wu, Wentong
    Liu, Han
    Li, Lingling
    Long, Yilin
    Wang, Xiaodong
    Wang, Zhuohua
    Li, Jinglun
    Chang, Yi
    [J]. PLOS ONE, 2021, 16 (10):
  • [5] RETRACTED: The effect of sedentary time on the results of exercise therapy in patients with peripheral arterial disease complicated with type 2 diabetes (Retracted Article)
    Gu, Lu
    Duan, Ling
    Xie, Ping
    He, Lin
    Peng, Wentao
    Zhou, Fengling
    [J]. ANNALS OF PALLIATIVE MEDICINE, 2021, 10 (05) : 5366 - 5372
  • [6] RETRACTED ARTICLE: Parameter estimation method of option pricing model based on convolutional neural network in high frequency financial trading
    Wanli He
    Mingkun Guan
    [J]. Annals of Operations Research, 2023, 326 : 151 - 151
  • [7] RETRACTED: Computer-Aided Diagnosis of Children with Cerebral Palsy under Deep Learning Convolutional Neural Network Image Segmentation Model Combined with Three-Dimensional Cranial Magnetic Resonance Imaging (Retracted Article)
    Yang, Rui
    Zuo, Haoran
    Han, Shusheng
    Zhang, Xiaoping
    Zhang, Qian
    [J]. JOURNAL OF HEALTHCARE ENGINEERING, 2021, 2021
  • [8] RETRACTED: Application of Deep Neural Network Model Combined with Factor Analysis in Clinical Nursing Effect Analysis of Blood Glucose Level in Elderly Type 2 Diabetic Patients (Retracted Article)
    Ding, Yi
    Zhang, DanDan
    [J]. JOURNAL OF HEALTHCARE ENGINEERING, 2021, 2021