Real-time diagnosis of multi-category skin diseases based on IR-VGG
Malignant skin lesions have a very high cure rate in the early stage.In recent years, dermatological diagnosis research based on deep learning has been continuously promoted, with high diagnostic accuracy.However, computational resource consumption is huge and it relies on large computing equipment...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
China InfoCom Media Group
2021-09-01
|
| Series: | 物联网学报 |
| Subjects: | |
| Online Access: | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2021.00217/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841531199000936448 |
|---|---|
| author | Ling TAN Shanshan RONG Jingming XIA Sarker SAJIB Wenjie MA |
| author_facet | Ling TAN Shanshan RONG Jingming XIA Sarker SAJIB Wenjie MA |
| author_sort | Ling TAN |
| collection | DOAJ |
| description | Malignant skin lesions have a very high cure rate in the early stage.In recent years, dermatological diagnosis research based on deep learning has been continuously promoted, with high diagnostic accuracy.However, computational resource consumption is huge and it relies on large computing equipment in hospitals.In order to realize rapid and accurate diagnosis of skin diseases on Internet of things (IoT) mobile devices, a real-time diagnosis system of multiple categories of skin diseases based on inverted residual visual geometry group (IR-VGG) was proposed.The contour detection algorithm was used to segment the lesion area of skin image.The convolutional block of the first layer of VGG16 was replaced with reverse residual block to reduce the network parameter weight and memory overhead.The original image and the segmented lesion image was inputed into IR-VGG network, and the dermatological diagnosis results after global and local feature extraction were outputed.The experimental results show that the IR-VGG network structure can achieve 94.71% and 85.28% accuracy in Skindata-1 and Skindata-2 skin diseases data sets respectively, and can effectively reduce complexity, making it easier for the diagnostic system to make real-time skin diseases diagnosis on IoT mobile devices. |
| format | Article |
| id | doaj-art-bd98d780c1fa4dec874824985acdc8a5 |
| institution | Kabale University |
| issn | 2096-3750 |
| language | zho |
| publishDate | 2021-09-01 |
| publisher | China InfoCom Media Group |
| record_format | Article |
| series | 物联网学报 |
| spelling | doaj-art-bd98d780c1fa4dec874824985acdc8a52025-01-15T02:53:20ZzhoChina InfoCom Media Group物联网学报2096-37502021-09-01511512559648346Real-time diagnosis of multi-category skin diseases based on IR-VGGLing TANShanshan RONGJingming XIASarker SAJIBWenjie MAMalignant skin lesions have a very high cure rate in the early stage.In recent years, dermatological diagnosis research based on deep learning has been continuously promoted, with high diagnostic accuracy.However, computational resource consumption is huge and it relies on large computing equipment in hospitals.In order to realize rapid and accurate diagnosis of skin diseases on Internet of things (IoT) mobile devices, a real-time diagnosis system of multiple categories of skin diseases based on inverted residual visual geometry group (IR-VGG) was proposed.The contour detection algorithm was used to segment the lesion area of skin image.The convolutional block of the first layer of VGG16 was replaced with reverse residual block to reduce the network parameter weight and memory overhead.The original image and the segmented lesion image was inputed into IR-VGG network, and the dermatological diagnosis results after global and local feature extraction were outputed.The experimental results show that the IR-VGG network structure can achieve 94.71% and 85.28% accuracy in Skindata-1 and Skindata-2 skin diseases data sets respectively, and can effectively reduce complexity, making it easier for the diagnostic system to make real-time skin diseases diagnosis on IoT mobile devices.http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2021.00217/skin lesionsedge detection segmentationinverted residualdeep learningInternet of things mobile devices |
| spellingShingle | Ling TAN Shanshan RONG Jingming XIA Sarker SAJIB Wenjie MA Real-time diagnosis of multi-category skin diseases based on IR-VGG 物联网学报 skin lesions edge detection segmentation inverted residual deep learning Internet of things mobile devices |
| title | Real-time diagnosis of multi-category skin diseases based on IR-VGG |
| title_full | Real-time diagnosis of multi-category skin diseases based on IR-VGG |
| title_fullStr | Real-time diagnosis of multi-category skin diseases based on IR-VGG |
| title_full_unstemmed | Real-time diagnosis of multi-category skin diseases based on IR-VGG |
| title_short | Real-time diagnosis of multi-category skin diseases based on IR-VGG |
| title_sort | real time diagnosis of multi category skin diseases based on ir vgg |
| topic | skin lesions edge detection segmentation inverted residual deep learning Internet of things mobile devices |
| url | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2021.00217/ |
| work_keys_str_mv | AT lingtan realtimediagnosisofmulticategoryskindiseasesbasedonirvgg AT shanshanrong realtimediagnosisofmulticategoryskindiseasesbasedonirvgg AT jingmingxia realtimediagnosisofmulticategoryskindiseasesbasedonirvgg AT sarkersajib realtimediagnosisofmulticategoryskindiseasesbasedonirvgg AT wenjiema realtimediagnosisofmulticategoryskindiseasesbasedonirvgg |