Cargando…

Fully Convolutional Neural Network Deep Learning Model Fully in Patients with Type 2 Diabetes Complicated with Peripheral Neuropathy by High-Frequency Ultrasound Image

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Xiaoqiang, Zhou, Hongyan, Wang, Zhaoyun, Liu, Xiaoli, Li, Xin, Nie, Chen, Li, Yang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8970954/
https://www.ncbi.nlm.nih.gov/pubmed/35371289
http://dx.doi.org/10.1155/2022/5466173
_version_ 1784679547240710144
author Liu, Xiaoqiang
Zhou, Hongyan
Wang, Zhaoyun
Liu, Xiaoli
Li, Xin
Nie, Chen
Li, Yang
author_facet Liu, Xiaoqiang
Zhou, Hongyan
Wang, Zhaoyun
Liu, Xiaoli
Li, Xin
Nie, Chen
Li, Yang
author_sort Liu, Xiaoqiang
collection PubMed
description 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.
format Online
Article
Text
id pubmed-8970954
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-89709542022-04-01 Fully Convolutional Neural Network Deep Learning Model Fully in Patients with Type 2 Diabetes Complicated with Peripheral Neuropathy by High-Frequency Ultrasound Image Liu, Xiaoqiang Zhou, Hongyan Wang, Zhaoyun Liu, Xiaoli Li, Xin Nie, Chen Li, Yang Comput Math Methods Med Research Article 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. Hindawi 2022-03-24 /pmc/articles/PMC8970954/ /pubmed/35371289 http://dx.doi.org/10.1155/2022/5466173 Text en Copyright © 2022 Xiaoqiang Liu et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Liu, Xiaoqiang
Zhou, Hongyan
Wang, Zhaoyun
Liu, Xiaoli
Li, Xin
Nie, Chen
Li, Yang
Fully Convolutional Neural Network Deep Learning Model Fully in Patients with Type 2 Diabetes Complicated with Peripheral Neuropathy by High-Frequency Ultrasound Image
title Fully Convolutional Neural Network Deep Learning Model Fully in Patients with Type 2 Diabetes Complicated with Peripheral Neuropathy by High-Frequency Ultrasound Image
title_full Fully Convolutional Neural Network Deep Learning Model Fully in Patients with Type 2 Diabetes Complicated with Peripheral Neuropathy by High-Frequency Ultrasound Image
title_fullStr Fully Convolutional Neural Network Deep Learning Model Fully in Patients with Type 2 Diabetes Complicated with Peripheral Neuropathy by High-Frequency Ultrasound Image
title_full_unstemmed Fully Convolutional Neural Network Deep Learning Model Fully in Patients with Type 2 Diabetes Complicated with Peripheral Neuropathy by High-Frequency Ultrasound Image
title_short Fully Convolutional Neural Network Deep Learning Model Fully in Patients with Type 2 Diabetes Complicated with Peripheral Neuropathy by High-Frequency Ultrasound Image
title_sort fully convolutional neural network deep learning model fully in patients with type 2 diabetes complicated with peripheral neuropathy by high-frequency ultrasound image
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8970954/
https://www.ncbi.nlm.nih.gov/pubmed/35371289
http://dx.doi.org/10.1155/2022/5466173
work_keys_str_mv AT liuxiaoqiang fullyconvolutionalneuralnetworkdeeplearningmodelfullyinpatientswithtype2diabetescomplicatedwithperipheralneuropathybyhighfrequencyultrasoundimage
AT zhouhongyan fullyconvolutionalneuralnetworkdeeplearningmodelfullyinpatientswithtype2diabetescomplicatedwithperipheralneuropathybyhighfrequencyultrasoundimage
AT wangzhaoyun fullyconvolutionalneuralnetworkdeeplearningmodelfullyinpatientswithtype2diabetescomplicatedwithperipheralneuropathybyhighfrequencyultrasoundimage
AT liuxiaoli fullyconvolutionalneuralnetworkdeeplearningmodelfullyinpatientswithtype2diabetescomplicatedwithperipheralneuropathybyhighfrequencyultrasoundimage
AT lixin fullyconvolutionalneuralnetworkdeeplearningmodelfullyinpatientswithtype2diabetescomplicatedwithperipheralneuropathybyhighfrequencyultrasoundimage
AT niechen fullyconvolutionalneuralnetworkdeeplearningmodelfullyinpatientswithtype2diabetescomplicatedwithperipheralneuropathybyhighfrequencyultrasoundimage
AT liyang fullyconvolutionalneuralnetworkdeeplearningmodelfullyinpatientswithtype2diabetescomplicatedwithperipheralneuropathybyhighfrequencyultrasoundimage