An Automated Grading System Based on Topological Features for the Evaluation of Corneal Fluorescein Staining in Dry Eye Disease
Background: Corneal fluorescein staining is a key biomarker in evaluating dry eye disease. However, subjective scales of corneal fluorescein staining are lacking in consistency and increase the difficulties of an accurate diagnosis for clinicians. This study aimed to propose an automatic machine lea...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/23/3533 |
| _version_ | 1827592411732246528 |
|---|---|
| author | Jun Feng Zi-Kai Ren Kai-Ni Wang Hao Guo Yi-Ran Hao Yuan-Chao Shu Lei Tian Guang-Quan Zhou Ying Jie |
| author_facet | Jun Feng Zi-Kai Ren Kai-Ni Wang Hao Guo Yi-Ran Hao Yuan-Chao Shu Lei Tian Guang-Quan Zhou Ying Jie |
| author_sort | Jun Feng |
| collection | DOAJ |
| description | Background: Corneal fluorescein staining is a key biomarker in evaluating dry eye disease. However, subjective scales of corneal fluorescein staining are lacking in consistency and increase the difficulties of an accurate diagnosis for clinicians. This study aimed to propose an automatic machine learning-based method for corneal fluorescein staining evaluation by utilizing prior information about the spatial connection and distribution of the staining region. Methods: We proposed an end-to-end automatic machine learning-based classification model that consists of staining region identification, feature signature construction, and machine learning-based classification, which fully scrutinizes the multiscale topological features together with conventional texture and morphological features. The proposed model was evaluated using retrospective data from Beijing Tongren Hospital. Two masked ophthalmologists scored images independently using the Sjögren’s International Collaborative Clinical Alliance Ocular Staining Score scale. Results: A total of 382 images were enrolled in the study. A signature with six topological features, two textural features, and two morphological features was constructed after feature extraction and selection. Support vector machines showed the best classification performance (accuracy: 82.67%, area under the curve: 96.59%) with the designed signature. Meanwhile, topological features contributed more to the classification, compared with other features. According to the distribution and correlation with features and scores, topological features performed better than others. Conclusions: An automatic machine learning-based method was advanced for corneal fluorescein staining evaluation. The topological features in presenting the spatial connectivity and distribution of staining regions are essential for an efficient corneal fluorescein staining evaluation. This result implies the clinical application of topological features in dry-eye diagnosis and therapeutic effect evaluation. |
| first_indexed | 2024-03-09T01:53:12Z |
| format | Article |
| id | doaj.art-b9261db93b564530971492e9d0770ad3 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T01:53:12Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-b9261db93b564530971492e9d0770ad32023-12-08T15:13:26ZengMDPI AGDiagnostics2075-44182023-11-011323353310.3390/diagnostics13233533An Automated Grading System Based on Topological Features for the Evaluation of Corneal Fluorescein Staining in Dry Eye DiseaseJun Feng0Zi-Kai Ren1Kai-Ni Wang2Hao Guo3Yi-Ran Hao4Yuan-Chao Shu5Lei Tian6Guang-Quan Zhou7Ying Jie8Beijing Ophthalmology and Visual Science Key Lab, Beijing Institute of Ophthalmology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing 100730, ChinaSchool of Biological Science and Medical Engineering, Southeast University, Nanjing 210096, ChinaSchool of Biological Science and Medical Engineering, Southeast University, Nanjing 210096, ChinaSchool of Biological Science and Medical Engineering, Southeast University, Nanjing 210096, ChinaBeijing Ophthalmology and Visual Science Key Lab, Beijing Institute of Ophthalmology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing 100730, ChinaCollege of Control Science and Engineering, Zhejiang University, Hangzhou 310027, ChinaBeijing Ophthalmology and Visual Science Key Lab, Beijing Institute of Ophthalmology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing 100730, ChinaSchool of Biological Science and Medical Engineering, Southeast University, Nanjing 210096, ChinaBeijing Ophthalmology and Visual Science Key Lab, Beijing Institute of Ophthalmology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing 100730, ChinaBackground: Corneal fluorescein staining is a key biomarker in evaluating dry eye disease. However, subjective scales of corneal fluorescein staining are lacking in consistency and increase the difficulties of an accurate diagnosis for clinicians. This study aimed to propose an automatic machine learning-based method for corneal fluorescein staining evaluation by utilizing prior information about the spatial connection and distribution of the staining region. Methods: We proposed an end-to-end automatic machine learning-based classification model that consists of staining region identification, feature signature construction, and machine learning-based classification, which fully scrutinizes the multiscale topological features together with conventional texture and morphological features. The proposed model was evaluated using retrospective data from Beijing Tongren Hospital. Two masked ophthalmologists scored images independently using the Sjögren’s International Collaborative Clinical Alliance Ocular Staining Score scale. Results: A total of 382 images were enrolled in the study. A signature with six topological features, two textural features, and two morphological features was constructed after feature extraction and selection. Support vector machines showed the best classification performance (accuracy: 82.67%, area under the curve: 96.59%) with the designed signature. Meanwhile, topological features contributed more to the classification, compared with other features. According to the distribution and correlation with features and scores, topological features performed better than others. Conclusions: An automatic machine learning-based method was advanced for corneal fluorescein staining evaluation. The topological features in presenting the spatial connectivity and distribution of staining regions are essential for an efficient corneal fluorescein staining evaluation. This result implies the clinical application of topological features in dry-eye diagnosis and therapeutic effect evaluation.https://www.mdpi.com/2075-4418/13/23/3533dry-eye diseasecorneal fluorescein stainingtopological featuresmachine learning |
| spellingShingle | Jun Feng Zi-Kai Ren Kai-Ni Wang Hao Guo Yi-Ran Hao Yuan-Chao Shu Lei Tian Guang-Quan Zhou Ying Jie An Automated Grading System Based on Topological Features for the Evaluation of Corneal Fluorescein Staining in Dry Eye Disease Diagnostics dry-eye disease corneal fluorescein staining topological features machine learning |
| title | An Automated Grading System Based on Topological Features for the Evaluation of Corneal Fluorescein Staining in Dry Eye Disease |
| title_full | An Automated Grading System Based on Topological Features for the Evaluation of Corneal Fluorescein Staining in Dry Eye Disease |
| title_fullStr | An Automated Grading System Based on Topological Features for the Evaluation of Corneal Fluorescein Staining in Dry Eye Disease |
| title_full_unstemmed | An Automated Grading System Based on Topological Features for the Evaluation of Corneal Fluorescein Staining in Dry Eye Disease |
| title_short | An Automated Grading System Based on Topological Features for the Evaluation of Corneal Fluorescein Staining in Dry Eye Disease |
| title_sort | automated grading system based on topological features for the evaluation of corneal fluorescein staining in dry eye disease |
| topic | dry-eye disease corneal fluorescein staining topological features machine learning |
| url | https://www.mdpi.com/2075-4418/13/23/3533 |
| work_keys_str_mv | AT junfeng anautomatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT zikairen anautomatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT kainiwang anautomatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT haoguo anautomatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT yiranhao anautomatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT yuanchaoshu anautomatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT leitian anautomatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT guangquanzhou anautomatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT yingjie anautomatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT junfeng automatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT zikairen automatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT kainiwang automatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT haoguo automatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT yiranhao automatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT yuanchaoshu automatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT leitian automatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT guangquanzhou automatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease AT yingjie automatedgradingsystembasedontopologicalfeaturesfortheevaluationofcornealfluoresceinstainingindryeyedisease |