Artificial intelligence to detect malignant eyelid tumors from photographic images
Abstract Malignant eyelid tumors can invade adjacent structures and pose a threat to vision and even life. Early identification of malignant eyelid tumors is crucial to avoiding substantial morbidity and mortality. However, differentiating malignant eyelid tumors from benign ones can be challenging...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-03-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-022-00571-3 |
| _version_ | 1797429510412435456 |
|---|---|
| author | Zhongwen Li Wei Qiang Hongyun Chen Mengjie Pei Xiaomei Yu Layi Wang Zhen Li Weiwei Xie Xuefang Wu Jiewei Jiang Guohai Wu |
| author_facet | Zhongwen Li Wei Qiang Hongyun Chen Mengjie Pei Xiaomei Yu Layi Wang Zhen Li Weiwei Xie Xuefang Wu Jiewei Jiang Guohai Wu |
| author_sort | Zhongwen Li |
| collection | DOAJ |
| description | Abstract Malignant eyelid tumors can invade adjacent structures and pose a threat to vision and even life. Early identification of malignant eyelid tumors is crucial to avoiding substantial morbidity and mortality. However, differentiating malignant eyelid tumors from benign ones can be challenging for primary care physicians and even some ophthalmologists. Here, based on 1,417 photographic images from 851 patients across three hospitals, we developed an artificial intelligence system using a faster region-based convolutional neural network and deep learning classification networks to automatically locate eyelid tumors and then distinguish between malignant and benign eyelid tumors. The system performed well in both internal and external test sets (AUCs ranged from 0.899 to 0.955). The performance of the system is comparable to that of a senior ophthalmologist, indicating that this system has the potential to be used at the screening stage for promoting the early detection and treatment of malignant eyelid tumors. |
| first_indexed | 2024-03-09T09:15:10Z |
| format | Article |
| id | doaj.art-c096b2bff66446778af2b2065fb12f82 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-09T09:15:10Z |
| publishDate | 2022-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-c096b2bff66446778af2b2065fb12f822023-12-02T07:32:13ZengNature Portfolionpj Digital Medicine2398-63522022-03-01511910.1038/s41746-022-00571-3Artificial intelligence to detect malignant eyelid tumors from photographic imagesZhongwen Li0Wei Qiang1Hongyun Chen2Mengjie Pei3Xiaomei Yu4Layi Wang5Zhen Li6Weiwei Xie7Xuefang Wu8Jiewei Jiang9Guohai Wu10Ningbo Eye Hospital, Wenzhou Medical UniversityNingbo Eye Hospital, Wenzhou Medical UniversityZunyi First People’s Hospital, Zunyi Medical UniversitySchool of Computer Science and Technology, Xi’an University of Posts and TelecommunicationsNingbo Eye Hospital, Wenzhou Medical UniversityNingbo Eye Hospital, Wenzhou Medical UniversityNingbo Eye Hospital, Wenzhou Medical UniversityNingbo Eye Hospital, Wenzhou Medical UniversityGuizhou Provincial People’s Hospital, Guizhou UniversitySchool of Electronic Engineering, Xi’an University of Posts and TelecommunicationsNingbo Eye Hospital, Wenzhou Medical UniversityAbstract Malignant eyelid tumors can invade adjacent structures and pose a threat to vision and even life. Early identification of malignant eyelid tumors is crucial to avoiding substantial morbidity and mortality. However, differentiating malignant eyelid tumors from benign ones can be challenging for primary care physicians and even some ophthalmologists. Here, based on 1,417 photographic images from 851 patients across three hospitals, we developed an artificial intelligence system using a faster region-based convolutional neural network and deep learning classification networks to automatically locate eyelid tumors and then distinguish between malignant and benign eyelid tumors. The system performed well in both internal and external test sets (AUCs ranged from 0.899 to 0.955). The performance of the system is comparable to that of a senior ophthalmologist, indicating that this system has the potential to be used at the screening stage for promoting the early detection and treatment of malignant eyelid tumors.https://doi.org/10.1038/s41746-022-00571-3 |
| spellingShingle | Zhongwen Li Wei Qiang Hongyun Chen Mengjie Pei Xiaomei Yu Layi Wang Zhen Li Weiwei Xie Xuefang Wu Jiewei Jiang Guohai Wu Artificial intelligence to detect malignant eyelid tumors from photographic images npj Digital Medicine |
| title | Artificial intelligence to detect malignant eyelid tumors from photographic images |
| title_full | Artificial intelligence to detect malignant eyelid tumors from photographic images |
| title_fullStr | Artificial intelligence to detect malignant eyelid tumors from photographic images |
| title_full_unstemmed | Artificial intelligence to detect malignant eyelid tumors from photographic images |
| title_short | Artificial intelligence to detect malignant eyelid tumors from photographic images |
| title_sort | artificial intelligence to detect malignant eyelid tumors from photographic images |
| url | https://doi.org/10.1038/s41746-022-00571-3 |
| work_keys_str_mv | AT zhongwenli artificialintelligencetodetectmalignanteyelidtumorsfromphotographicimages AT weiqiang artificialintelligencetodetectmalignanteyelidtumorsfromphotographicimages AT hongyunchen artificialintelligencetodetectmalignanteyelidtumorsfromphotographicimages AT mengjiepei artificialintelligencetodetectmalignanteyelidtumorsfromphotographicimages AT xiaomeiyu artificialintelligencetodetectmalignanteyelidtumorsfromphotographicimages AT layiwang artificialintelligencetodetectmalignanteyelidtumorsfromphotographicimages AT zhenli artificialintelligencetodetectmalignanteyelidtumorsfromphotographicimages AT weiweixie artificialintelligencetodetectmalignanteyelidtumorsfromphotographicimages AT xuefangwu artificialintelligencetodetectmalignanteyelidtumorsfromphotographicimages AT jieweijiang artificialintelligencetodetectmalignanteyelidtumorsfromphotographicimages AT guohaiwu artificialintelligencetodetectmalignanteyelidtumorsfromphotographicimages |