AI assistance enhances histopathologic distinction between sebaceous and squamous cell carcinoma of the eyelid
Abstract Sebaceous gland carcinoma (SGC) and some poorly differentiated squamous cell carcinomas (SC) of the eyelid may have overlapping clinical and histopathologic features, leading to potential misdiagnosis and delayed treatment. The authors developed a deep learning (DL)-based pathological analy...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-025-01775-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849334280655732736 |
|---|---|
| author | Jialu Geng Kai Zhang Li Dong Shiqi Hui Qian Zhang Zhixi Li Ruiheng Zhang Xue Jiang Mingyang Wang Shuantao Sun Hong Zhang Yunyun Yang Xinji Yang Yingshi Piao Dongmei Li |
| author_facet | Jialu Geng Kai Zhang Li Dong Shiqi Hui Qian Zhang Zhixi Li Ruiheng Zhang Xue Jiang Mingyang Wang Shuantao Sun Hong Zhang Yunyun Yang Xinji Yang Yingshi Piao Dongmei Li |
| author_sort | Jialu Geng |
| collection | DOAJ |
| description | Abstract Sebaceous gland carcinoma (SGC) and some poorly differentiated squamous cell carcinomas (SC) of the eyelid may have overlapping clinical and histopathologic features, leading to potential misdiagnosis and delayed treatment. The authors developed a deep learning (DL)-based pathological analysis framework to classify SGC and SC automatically. In total, 282 whole slide images (WSIs) were used for training, validating and inner testing the DL framework and 36 WSIs were obtained from another hospital as an external testing dataset. In WSI level, the diagnostic accuracy of SGC and SC achieved 84.85% and 75.12%, respectively, in the internal testing set and reached 22.22% and 77.78%, respectively, in the external testing set. The accuracy of the pathologists could be improved with the AI framework (60.0 ± 9.8% vs. 76.8 ± 9.6%). This AI-based automatic pathological diagnostic framework achieved the performance of a well-experienced pathologist and can assist pathologists in making diagnoses more accurately, especially for non-ophthalmic pathologists. |
| format | Article |
| id | doaj-art-ef6eabcb09834a3faf94ba76dbdabe4d |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-ef6eabcb09834a3faf94ba76dbdabe4d2025-08-20T03:45:36ZengNature Portfolionpj Digital Medicine2398-63522025-07-01811810.1038/s41746-025-01775-zAI assistance enhances histopathologic distinction between sebaceous and squamous cell carcinoma of the eyelidJialu Geng0Kai Zhang1Li Dong2Shiqi Hui3Qian Zhang4Zhixi Li5Ruiheng Zhang6Xue Jiang7Mingyang Wang8Shuantao Sun9Hong Zhang10Yunyun Yang11Xinji Yang12Yingshi Piao13Dongmei Li14 Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology＆Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Key Laboratory of Intelligent Diagnosis, Treatment and Prevention of Blinding Eye Diseases, Beijing Tongren Hospital, Capital Medical UniversityGyenno Science Co. Ltd. Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology＆Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Key Laboratory of Intelligent Diagnosis, Treatment and Prevention of Blinding Eye Diseases, Beijing Tongren Hospital, Capital Medical University Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology＆Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Key Laboratory of Intelligent Diagnosis, Treatment and Prevention of Blinding Eye Diseases, Beijing Tongren Hospital, Capital Medical UniversityDepartment of Pathology, Beijing Tongren Hospital Affiliated with Capital Medical University, Beijing Key Laboratory of Head and Neck Pathology DiagnosisState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology＆Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Key Laboratory of Intelligent Diagnosis, Treatment and Prevention of Blinding Eye Diseases, Beijing Tongren Hospital, Capital Medical University Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology＆Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Key Laboratory of Intelligent Diagnosis, Treatment and Prevention of Blinding Eye Diseases, Beijing Tongren Hospital, Capital Medical University Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology＆Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Key Laboratory of Intelligent Diagnosis, Treatment and Prevention of Blinding Eye Diseases, Beijing Tongren Hospital, Capital Medical UniversitySenior Department of Ophthalmology, The Third Medical Center of Chinese PLA General HospitalDepartment of Pathology, Beijing Tongren Hospital Affiliated with Capital Medical University, Beijing Key Laboratory of Head and Neck Pathology DiagnosisDepartment of Pathology, Beijing Tongren Hospital Affiliated with Capital Medical University, Beijing Key Laboratory of Head and Neck Pathology DiagnosisSenior Department of Ophthalmology, The Third Medical Center of Chinese PLA General HospitalDepartment of Pathology, Beijing Tongren Hospital Affiliated with Capital Medical University, Beijing Key Laboratory of Head and Neck Pathology Diagnosis Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology＆Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Key Laboratory of Intelligent Diagnosis, Treatment and Prevention of Blinding Eye Diseases, Beijing Tongren Hospital, Capital Medical UniversityAbstract Sebaceous gland carcinoma (SGC) and some poorly differentiated squamous cell carcinomas (SC) of the eyelid may have overlapping clinical and histopathologic features, leading to potential misdiagnosis and delayed treatment. The authors developed a deep learning (DL)-based pathological analysis framework to classify SGC and SC automatically. In total, 282 whole slide images (WSIs) were used for training, validating and inner testing the DL framework and 36 WSIs were obtained from another hospital as an external testing dataset. In WSI level, the diagnostic accuracy of SGC and SC achieved 84.85% and 75.12%, respectively, in the internal testing set and reached 22.22% and 77.78%, respectively, in the external testing set. The accuracy of the pathologists could be improved with the AI framework (60.0 ± 9.8% vs. 76.8 ± 9.6%). This AI-based automatic pathological diagnostic framework achieved the performance of a well-experienced pathologist and can assist pathologists in making diagnoses more accurately, especially for non-ophthalmic pathologists.https://doi.org/10.1038/s41746-025-01775-z |
| spellingShingle | Jialu Geng Kai Zhang Li Dong Shiqi Hui Qian Zhang Zhixi Li Ruiheng Zhang Xue Jiang Mingyang Wang Shuantao Sun Hong Zhang Yunyun Yang Xinji Yang Yingshi Piao Dongmei Li AI assistance enhances histopathologic distinction between sebaceous and squamous cell carcinoma of the eyelid npj Digital Medicine |
| title | AI assistance enhances histopathologic distinction between sebaceous and squamous cell carcinoma of the eyelid |
| title_full | AI assistance enhances histopathologic distinction between sebaceous and squamous cell carcinoma of the eyelid |
| title_fullStr | AI assistance enhances histopathologic distinction between sebaceous and squamous cell carcinoma of the eyelid |
| title_full_unstemmed | AI assistance enhances histopathologic distinction between sebaceous and squamous cell carcinoma of the eyelid |
| title_short | AI assistance enhances histopathologic distinction between sebaceous and squamous cell carcinoma of the eyelid |
| title_sort | ai assistance enhances histopathologic distinction between sebaceous and squamous cell carcinoma of the eyelid |
| url | https://doi.org/10.1038/s41746-025-01775-z |
| work_keys_str_mv | AT jialugeng aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT kaizhang aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT lidong aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT shiqihui aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT qianzhang aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT zhixili aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT ruihengzhang aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT xuejiang aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT mingyangwang aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT shuantaosun aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT hongzhang aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT yunyunyang aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT xinjiyang aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT yingshipiao aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid AT dongmeili aiassistanceenhanceshistopathologicdistinctionbetweensebaceousandsquamouscellcarcinomaoftheeyelid |