Artificial Intelligence to Detect Meibomian Gland Dysfunction From in-vivo Laser Confocal Microscopy
Background: In recent years, deep learning has been widely used in a variety of ophthalmic diseases. As a common ophthalmic disease, meibomian gland dysfunction (MGD) has a unique phenotype in in-vivo laser confocal microscope imaging (VLCMI). The purpose of our study was to investigate a deep learn...
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Frontiers Media S.A.
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/4083ee8267a34952a837031f0b8f1a05 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:4083ee8267a34952a837031f0b8f1a05 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:4083ee8267a34952a837031f0b8f1a052021-12-01T01:15:47ZArtificial Intelligence to Detect Meibomian Gland Dysfunction From in-vivo Laser Confocal Microscopy2296-858X10.3389/fmed.2021.774344https://doaj.org/article/4083ee8267a34952a837031f0b8f1a052021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fmed.2021.774344/fullhttps://doaj.org/toc/2296-858XBackground: In recent years, deep learning has been widely used in a variety of ophthalmic diseases. As a common ophthalmic disease, meibomian gland dysfunction (MGD) has a unique phenotype in in-vivo laser confocal microscope imaging (VLCMI). The purpose of our study was to investigate a deep learning algorithm to differentiate and classify obstructive MGD (OMGD), atrophic MGD (AMGD) and normal groups.Methods: In this study, a multi-layer deep convolution neural network (CNN) was trained using VLCMI from OMGD, AMGD and healthy subjects as verified by medical experts. The automatic differential diagnosis of OMGD, AMGD and healthy people was tested by comparing its image-based identification of each group with the medical expert diagnosis. The CNN was trained and validated with 4,985 and 1,663 VLCMI images, respectively. By using established enhancement techniques, 1,663 untrained VLCMI images were tested.Results: In this study, we included 2,766 healthy control VLCMIs, 2,744 from OMGD and 2,801 from AMGD. Of the three models, differential diagnostic accuracy of the DenseNet169 CNN was highest at over 97%. The sensitivity and specificity of the DenseNet169 model for OMGD were 88.8 and 95.4%, respectively; and for AMGD 89.4 and 98.4%, respectively.Conclusion: This study described a deep learning algorithm to automatically check and classify VLCMI images of MGD. By optimizing the algorithm, the classifier model displayed excellent accuracy. With further development, this model may become an effective tool for the differential diagnosis of MGD.Ye-Ye ZhangYe-Ye ZhangHui ZhaoJin-Yan LinShi-Nan WuXi-Wang LiuXi-Wang LiuHong-Dan ZhangHong-Dan ZhangYi ShaoWei-Feng YangWei-Feng YangWei-Feng YangFrontiers Media S.A.articledeep learningmeibomian gland dysfunctionconvolution neural networkin-vivo confocal microscopyDenseNet CNNMedicine (General)R5-920ENFrontiers in Medicine, Vol 8 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
deep learning meibomian gland dysfunction convolution neural network in-vivo confocal microscopy DenseNet CNN Medicine (General) R5-920 |
| spellingShingle |
deep learning meibomian gland dysfunction convolution neural network in-vivo confocal microscopy DenseNet CNN Medicine (General) R5-920 Ye-Ye Zhang Ye-Ye Zhang Hui Zhao Jin-Yan Lin Shi-Nan Wu Xi-Wang Liu Xi-Wang Liu Hong-Dan Zhang Hong-Dan Zhang Yi Shao Wei-Feng Yang Wei-Feng Yang Wei-Feng Yang Artificial Intelligence to Detect Meibomian Gland Dysfunction From in-vivo Laser Confocal Microscopy |
| description |
Background: In recent years, deep learning has been widely used in a variety of ophthalmic diseases. As a common ophthalmic disease, meibomian gland dysfunction (MGD) has a unique phenotype in in-vivo laser confocal microscope imaging (VLCMI). The purpose of our study was to investigate a deep learning algorithm to differentiate and classify obstructive MGD (OMGD), atrophic MGD (AMGD) and normal groups.Methods: In this study, a multi-layer deep convolution neural network (CNN) was trained using VLCMI from OMGD, AMGD and healthy subjects as verified by medical experts. The automatic differential diagnosis of OMGD, AMGD and healthy people was tested by comparing its image-based identification of each group with the medical expert diagnosis. The CNN was trained and validated with 4,985 and 1,663 VLCMI images, respectively. By using established enhancement techniques, 1,663 untrained VLCMI images were tested.Results: In this study, we included 2,766 healthy control VLCMIs, 2,744 from OMGD and 2,801 from AMGD. Of the three models, differential diagnostic accuracy of the DenseNet169 CNN was highest at over 97%. The sensitivity and specificity of the DenseNet169 model for OMGD were 88.8 and 95.4%, respectively; and for AMGD 89.4 and 98.4%, respectively.Conclusion: This study described a deep learning algorithm to automatically check and classify VLCMI images of MGD. By optimizing the algorithm, the classifier model displayed excellent accuracy. With further development, this model may become an effective tool for the differential diagnosis of MGD. |
| format |
article |
| author |
Ye-Ye Zhang Ye-Ye Zhang Hui Zhao Jin-Yan Lin Shi-Nan Wu Xi-Wang Liu Xi-Wang Liu Hong-Dan Zhang Hong-Dan Zhang Yi Shao Wei-Feng Yang Wei-Feng Yang Wei-Feng Yang |
| author_facet |
Ye-Ye Zhang Ye-Ye Zhang Hui Zhao Jin-Yan Lin Shi-Nan Wu Xi-Wang Liu Xi-Wang Liu Hong-Dan Zhang Hong-Dan Zhang Yi Shao Wei-Feng Yang Wei-Feng Yang Wei-Feng Yang |
| author_sort |
Ye-Ye Zhang |
| title |
Artificial Intelligence to Detect Meibomian Gland Dysfunction From in-vivo Laser Confocal Microscopy |
| title_short |
Artificial Intelligence to Detect Meibomian Gland Dysfunction From in-vivo Laser Confocal Microscopy |
| title_full |
Artificial Intelligence to Detect Meibomian Gland Dysfunction From in-vivo Laser Confocal Microscopy |
| title_fullStr |
Artificial Intelligence to Detect Meibomian Gland Dysfunction From in-vivo Laser Confocal Microscopy |
| title_full_unstemmed |
Artificial Intelligence to Detect Meibomian Gland Dysfunction From in-vivo Laser Confocal Microscopy |
| title_sort |
artificial intelligence to detect meibomian gland dysfunction from in-vivo laser confocal microscopy |
| publisher |
Frontiers Media S.A. |
| publishDate |
2021 |
| url |
https://doaj.org/article/4083ee8267a34952a837031f0b8f1a05 |
| work_keys_str_mv |
AT yeyezhang artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy AT yeyezhang artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy AT huizhao artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy AT jinyanlin artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy AT shinanwu artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy AT xiwangliu artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy AT xiwangliu artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy AT hongdanzhang artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy AT hongdanzhang artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy AT yishao artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy AT weifengyang artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy AT weifengyang artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy AT weifengyang artificialintelligencetodetectmeibomianglanddysfunctionfrominvivolaserconfocalmicroscopy |
| _version_ |
1718406017900871680 |