Analysis of Varicose Veins of Lower Extremities Based on Vascular Endothelial Cell Inflammation Images and Multi-Scale Deep Learning
The doctor determines whether there are lesions in the human body through the diagnosis of medical images, and classifies and identifies the lesions. Therefore, the automatic classification and recognition of medical images has received extensive attention. Since the inflammatory phenomenon of vascu...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8907827/ |
id |
doaj-fedbf2ecb58e4c049f769e70c343dd2f |
---|---|
record_format |
Article |
spelling |
doaj-fedbf2ecb58e4c049f769e70c343dd2f2021-03-30T00:25:31ZengIEEEIEEE Access2169-35362019-01-01717434517435810.1109/ACCESS.2019.29547088907827Analysis of Varicose Veins of Lower Extremities Based on Vascular Endothelial Cell Inflammation Images and Multi-Scale Deep LearningRuizong Zhu0https://orcid.org/0000-0001-9136-224XHuiping Niu1https://orcid.org/0000-0002-1451-4286Ningning Yin2https://orcid.org/0000-0002-3911-4836Tianjiao Wu3https://orcid.org/0000-0002-0866-5782Yapei Zhao4https://orcid.org/0000-0003-3688-5026Department of Clinical Laboratory, Dingzhou People’s Hospital, Dingzhou, ChinaEndoscopy Center, The Second Hospital of Hebei Medical University, Shijiazhuang, ChinaDepartment of Ultrasound, The Second Hospital of Hebei Medical University, Shijiazhuang, ChinaDepartment of Ultrasound, The Second Hospital of Hebei Medical University, Shijiazhuang, ChinaDepartment of Ultrasound, The Second Hospital of Hebei Medical University, Shijiazhuang, ChinaThe doctor determines whether there are lesions in the human body through the diagnosis of medical images, and classifies and identifies the lesions. Therefore, the automatic classification and recognition of medical images has received extensive attention. Since the inflammatory phenomenon of vascular endothelial cells is closely related to the varicose veins of the lower extremities, in order to realize the automatic classification and recognition of varicose veins of the lower extremities, this paper proposes a varicose vein recognition algorithm based on vascular endothelial cell inflammation images and multi-scale deep learning, called MSDCNN. First, we obtained images of vascular endothelial cells in patients with varicose veins of the lower extremities and normal subjects. Second, multiple convolutional layers extract multi-scale features of vascular endothelial cell images. Then, the MFM activation function is used instead of the ReLU activation function to introduce a competitive mechanism that extracts more features that are compact and reduces network layer parameters. Finally, the network uses a 3 × 3 convolution kernel to improve the network feature extraction capability and use the 1 × 1 convolution kernel for dimensionality reduction to further streamline network parameters. The experimental results tell us that the network has the advantages of high recognition accuracy, fast running speed, few network parameters, and is suitable for small-embedded devices.https://ieeexplore.ieee.org/document/8907827/Vascular endothelial cellsinflammationmulti-scale deep learningvaricose veins of the lower extremities |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ruizong Zhu Huiping Niu Ningning Yin Tianjiao Wu Yapei Zhao |
spellingShingle |
Ruizong Zhu Huiping Niu Ningning Yin Tianjiao Wu Yapei Zhao Analysis of Varicose Veins of Lower Extremities Based on Vascular Endothelial Cell Inflammation Images and Multi-Scale Deep Learning IEEE Access Vascular endothelial cells inflammation multi-scale deep learning varicose veins of the lower extremities |
author_facet |
Ruizong Zhu Huiping Niu Ningning Yin Tianjiao Wu Yapei Zhao |
author_sort |
Ruizong Zhu |
title |
Analysis of Varicose Veins of Lower Extremities Based on Vascular Endothelial Cell Inflammation Images and Multi-Scale Deep Learning |
title_short |
Analysis of Varicose Veins of Lower Extremities Based on Vascular Endothelial Cell Inflammation Images and Multi-Scale Deep Learning |
title_full |
Analysis of Varicose Veins of Lower Extremities Based on Vascular Endothelial Cell Inflammation Images and Multi-Scale Deep Learning |
title_fullStr |
Analysis of Varicose Veins of Lower Extremities Based on Vascular Endothelial Cell Inflammation Images and Multi-Scale Deep Learning |
title_full_unstemmed |
Analysis of Varicose Veins of Lower Extremities Based on Vascular Endothelial Cell Inflammation Images and Multi-Scale Deep Learning |
title_sort |
analysis of varicose veins of lower extremities based on vascular endothelial cell inflammation images and multi-scale deep learning |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
The doctor determines whether there are lesions in the human body through the diagnosis of medical images, and classifies and identifies the lesions. Therefore, the automatic classification and recognition of medical images has received extensive attention. Since the inflammatory phenomenon of vascular endothelial cells is closely related to the varicose veins of the lower extremities, in order to realize the automatic classification and recognition of varicose veins of the lower extremities, this paper proposes a varicose vein recognition algorithm based on vascular endothelial cell inflammation images and multi-scale deep learning, called MSDCNN. First, we obtained images of vascular endothelial cells in patients with varicose veins of the lower extremities and normal subjects. Second, multiple convolutional layers extract multi-scale features of vascular endothelial cell images. Then, the MFM activation function is used instead of the ReLU activation function to introduce a competitive mechanism that extracts more features that are compact and reduces network layer parameters. Finally, the network uses a 3 × 3 convolution kernel to improve the network feature extraction capability and use the 1 × 1 convolution kernel for dimensionality reduction to further streamline network parameters. The experimental results tell us that the network has the advantages of high recognition accuracy, fast running speed, few network parameters, and is suitable for small-embedded devices. |
topic |
Vascular endothelial cells inflammation multi-scale deep learning varicose veins of the lower extremities |
url |
https://ieeexplore.ieee.org/document/8907827/ |
work_keys_str_mv |
AT ruizongzhu analysisofvaricoseveinsoflowerextremitiesbasedonvascularendothelialcellinflammationimagesandmultiscaledeeplearning AT huipingniu analysisofvaricoseveinsoflowerextremitiesbasedonvascularendothelialcellinflammationimagesandmultiscaledeeplearning AT ningningyin analysisofvaricoseveinsoflowerextremitiesbasedonvascularendothelialcellinflammationimagesandmultiscaledeeplearning AT tianjiaowu analysisofvaricoseveinsoflowerextremitiesbasedonvascularendothelialcellinflammationimagesandmultiscaledeeplearning AT yapeizhao analysisofvaricoseveinsoflowerextremitiesbasedonvascularendothelialcellinflammationimagesandmultiscaledeeplearning |
_version_ |
1724188402268504064 |