Studies on Different CNN Algorithms for Face Skin Disease Classification Based on Clinical Images
Skin problems not only injure physical health but also induce psychological problems, especially for patients whose faces have been damaged or even disfigured. Using smart devices, most of the people are able to obtain convenient clinical images of their face skin condition. On the other hand, the c...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8720210/ |
| _version_ | 1818945334740516864 |
|---|---|
| author | Zhe Wu Shuang Zhao Yonghong Peng Xiaoyu He Xinyu Zhao Kai Huang Xian Wu Wei Fan Fangfang Li Mingliang Chen Jie Li Weihong Huang Xiang Chen Yi Li |
| author_facet | Zhe Wu Shuang Zhao Yonghong Peng Xiaoyu He Xinyu Zhao Kai Huang Xian Wu Wei Fan Fangfang Li Mingliang Chen Jie Li Weihong Huang Xiang Chen Yi Li |
| author_sort | Zhe Wu |
| collection | DOAJ |
| description | Skin problems not only injure physical health but also induce psychological problems, especially for patients whose faces have been damaged or even disfigured. Using smart devices, most of the people are able to obtain convenient clinical images of their face skin condition. On the other hand, the convolutional neural networks (CNNs) have achieved near or even better performance than human beings in the imaging field. Therefore, this paper studied different CNN algorithms for face skin disease classification based on the clinical images. First, from Xiangya-Derm, which is, to the best of our knowledge, China's largest clinical image dataset of skin diseases, we established a dataset that contains 2656 face images belonging to six common skin diseases [seborrheic keratosis (SK), actinic keratosis (AK), rosacea (ROS), lupus erythematosus (LE), basal cell carcinoma (BCC), and squamous cell carcinoma (SCC)]. We performed studies using five mainstream network algorithms to classify these diseases in the dataset and compared the results. Then, we performed studies using an independent dataset of the same disease types, but from other body parts, to perform transfer learning on our models. Comparing the performances, the models that used transfer learning achieved a higher average precision and recall for almost all structures. In the test dataset, which included 388 facial images, the best model achieved 92.9%, 89.2%, and 84.3% recalls for the LE, BCC, and SK, respectively, and the mean recall and precision reached 77.0% and 70.8%. |
| first_indexed | 2024-12-20T07:57:28Z |
| format | Article |
| id | doaj.art-35a3047222994c3c935865e528d811d8 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T07:57:28Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-35a3047222994c3c935865e528d811d82022-12-21T19:47:37ZengIEEEIEEE Access2169-35362019-01-017665056651110.1109/ACCESS.2019.29182218720210Studies on Different CNN Algorithms for Face Skin Disease Classification Based on Clinical ImagesZhe Wu0https://orcid.org/0000-0002-5371-4352Shuang Zhao1Yonghong Peng2https://orcid.org/0000-0002-5508-1819Xiaoyu He3Xinyu Zhao4Kai Huang5Xian Wu6Wei Fan7Fangfang Li8Mingliang Chen9Jie Li10Weihong Huang11https://orcid.org/0000-0002-7168-4943Xiang Chen12Yi Li13School of Automation, Central South University, Changsha, ChinaDepartment of Dermatology, Xiangya Hospital, Central South University, Changsha, ChinaFaculty of Computer Science, University of Sunderland, Sunderland, U.K.School of Automation, Central South University, Changsha, ChinaSchool of Automation, Central South University, Changsha, ChinaDepartment of Dermatology, Xiangya Hospital, Central South University, Changsha, ChinaTencent Medical AI Lab, Beijing, ChinaTencent Medical AI Lab, Beijing, ChinaDepartment of Dermatology, Xiangya Hospital, Central South University, Changsha, ChinaDepartment of Dermatology, Xiangya Hospital, Central South University, Changsha, ChinaDepartment of Dermatology, Xiangya Hospital, Central South University, Changsha, ChinaDepartment of Dermatology, Xiangya Hospital, Central South University, Changsha, ChinaDepartment of Dermatology, Xiangya Hospital, Central South University, Changsha, ChinaSchool of Automation, Central South University, Changsha, ChinaSkin problems not only injure physical health but also induce psychological problems, especially for patients whose faces have been damaged or even disfigured. Using smart devices, most of the people are able to obtain convenient clinical images of their face skin condition. On the other hand, the convolutional neural networks (CNNs) have achieved near or even better performance than human beings in the imaging field. Therefore, this paper studied different CNN algorithms for face skin disease classification based on the clinical images. First, from Xiangya-Derm, which is, to the best of our knowledge, China's largest clinical image dataset of skin diseases, we established a dataset that contains 2656 face images belonging to six common skin diseases [seborrheic keratosis (SK), actinic keratosis (AK), rosacea (ROS), lupus erythematosus (LE), basal cell carcinoma (BCC), and squamous cell carcinoma (SCC)]. We performed studies using five mainstream network algorithms to classify these diseases in the dataset and compared the results. Then, we performed studies using an independent dataset of the same disease types, but from other body parts, to perform transfer learning on our models. Comparing the performances, the models that used transfer learning achieved a higher average precision and recall for almost all structures. In the test dataset, which included 388 facial images, the best model achieved 92.9%, 89.2%, and 84.3% recalls for the LE, BCC, and SK, respectively, and the mean recall and precision reached 77.0% and 70.8%.https://ieeexplore.ieee.org/document/8720210/Deep learningCNNfacial skin diseasemedical image processing |
| spellingShingle | Zhe Wu Shuang Zhao Yonghong Peng Xiaoyu He Xinyu Zhao Kai Huang Xian Wu Wei Fan Fangfang Li Mingliang Chen Jie Li Weihong Huang Xiang Chen Yi Li Studies on Different CNN Algorithms for Face Skin Disease Classification Based on Clinical Images IEEE Access Deep learning CNN facial skin disease medical image processing |
| title | Studies on Different CNN Algorithms for Face Skin Disease Classification Based on Clinical Images |
| title_full | Studies on Different CNN Algorithms for Face Skin Disease Classification Based on Clinical Images |
| title_fullStr | Studies on Different CNN Algorithms for Face Skin Disease Classification Based on Clinical Images |
| title_full_unstemmed | Studies on Different CNN Algorithms for Face Skin Disease Classification Based on Clinical Images |
| title_short | Studies on Different CNN Algorithms for Face Skin Disease Classification Based on Clinical Images |
| title_sort | studies on different cnn algorithms for face skin disease classification based on clinical images |
| topic | Deep learning CNN facial skin disease medical image processing |
| url | https://ieeexplore.ieee.org/document/8720210/ |
| work_keys_str_mv | AT zhewu studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT shuangzhao studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT yonghongpeng studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT xiaoyuhe studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT xinyuzhao studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT kaihuang studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT xianwu studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT weifan studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT fangfangli studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT mingliangchen studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT jieli studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT weihonghuang studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT xiangchen studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages AT yili studiesondifferentcnnalgorithmsforfaceskindiseaseclassificationbasedonclinicalimages |