A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images.
<h4>Purpose</h4>Infiltration of activated dendritic cells and inflammatory cells in cornea represents an important marker for defining corneal inflammation. Deep transfer learning has presented a promising potential and is gaining more importance in computer assisted diagnosis. This stud...
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Public Library of Science (PLoS)
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/baa509686dac43f688c3bf9d7ea6501d |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:baa509686dac43f688c3bf9d7ea6501d |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:baa509686dac43f688c3bf9d7ea6501d2021-12-02T20:11:06ZA deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images.1932-620310.1371/journal.pone.0252653https://doaj.org/article/baa509686dac43f688c3bf9d7ea6501d2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0252653https://doaj.org/toc/1932-6203<h4>Purpose</h4>Infiltration of activated dendritic cells and inflammatory cells in cornea represents an important marker for defining corneal inflammation. Deep transfer learning has presented a promising potential and is gaining more importance in computer assisted diagnosis. This study aimed to develop deep transfer learning models for automatic detection of activated dendritic cells and inflammatory cells using in vivo confocal microscopy images.<h4>Methods</h4>A total of 3453 images was used to train the models. External validation was performed on an independent test set of 558 images. A ground-truth label was assigned to each image by a panel of cornea specialists. We constructed a deep transfer learning network that consisted of a pre-trained network and an adaptation layer. In this work, five pre-trained networks were considered, namely VGG-16, ResNet-101, Inception V3, Xception, and Inception-ResNet V2. The performance of each transfer network was evaluated by calculating the area under the curve (AUC) of receiver operating characteristic, accuracy, sensitivity, specificity, and G mean.<h4>Results</h4>The best performance was achieved by Inception-ResNet V2 transfer model. In the validation set, the best transfer system achieved an AUC of 0.9646 (P<0.001) in identifying activated dendritic cells (accuracy, 0.9319; sensitivity, 0.8171; specificity, 0.9517; and G mean, 0.8872), and 0.9901 (P<0.001) in identifying inflammatory cells (accuracy, 0.9767; sensitivity, 0.9174; specificity, 0.9931; and G mean, 0.9545).<h4>Conclusions</h4>The deep transfer learning models provide a completely automated analysis of corneal inflammatory cellular components with high accuracy. The implementation of such models would greatly benefit the management of corneal diseases and reduce workloads for ophthalmologists.Fan XuYikun QinWenjing HeGuangyi HuangJian LvXinxin XieChunli DiaoFen TangLi JiangRushi LanXiaohui ChengXiaolin XiaoSiming ZengQi ChenLing CuiMin LiNingning TangPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 6, p e0252653 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Fan Xu Yikun Qin Wenjing He Guangyi Huang Jian Lv Xinxin Xie Chunli Diao Fen Tang Li Jiang Rushi Lan Xiaohui Cheng Xiaolin Xiao Siming Zeng Qi Chen Ling Cui Min Li Ningning Tang A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images. |
| description |
<h4>Purpose</h4>Infiltration of activated dendritic cells and inflammatory cells in cornea represents an important marker for defining corneal inflammation. Deep transfer learning has presented a promising potential and is gaining more importance in computer assisted diagnosis. This study aimed to develop deep transfer learning models for automatic detection of activated dendritic cells and inflammatory cells using in vivo confocal microscopy images.<h4>Methods</h4>A total of 3453 images was used to train the models. External validation was performed on an independent test set of 558 images. A ground-truth label was assigned to each image by a panel of cornea specialists. We constructed a deep transfer learning network that consisted of a pre-trained network and an adaptation layer. In this work, five pre-trained networks were considered, namely VGG-16, ResNet-101, Inception V3, Xception, and Inception-ResNet V2. The performance of each transfer network was evaluated by calculating the area under the curve (AUC) of receiver operating characteristic, accuracy, sensitivity, specificity, and G mean.<h4>Results</h4>The best performance was achieved by Inception-ResNet V2 transfer model. In the validation set, the best transfer system achieved an AUC of 0.9646 (P<0.001) in identifying activated dendritic cells (accuracy, 0.9319; sensitivity, 0.8171; specificity, 0.9517; and G mean, 0.8872), and 0.9901 (P<0.001) in identifying inflammatory cells (accuracy, 0.9767; sensitivity, 0.9174; specificity, 0.9931; and G mean, 0.9545).<h4>Conclusions</h4>The deep transfer learning models provide a completely automated analysis of corneal inflammatory cellular components with high accuracy. The implementation of such models would greatly benefit the management of corneal diseases and reduce workloads for ophthalmologists. |
| format |
article |
| author |
Fan Xu Yikun Qin Wenjing He Guangyi Huang Jian Lv Xinxin Xie Chunli Diao Fen Tang Li Jiang Rushi Lan Xiaohui Cheng Xiaolin Xiao Siming Zeng Qi Chen Ling Cui Min Li Ningning Tang |
| author_facet |
Fan Xu Yikun Qin Wenjing He Guangyi Huang Jian Lv Xinxin Xie Chunli Diao Fen Tang Li Jiang Rushi Lan Xiaohui Cheng Xiaolin Xiao Siming Zeng Qi Chen Ling Cui Min Li Ningning Tang |
| author_sort |
Fan Xu |
| title |
A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images. |
| title_short |
A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images. |
| title_full |
A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images. |
| title_fullStr |
A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images. |
| title_full_unstemmed |
A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images. |
| title_sort |
deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images. |
| publisher |
Public Library of Science (PLoS) |
| publishDate |
2021 |
| url |
https://doaj.org/article/baa509686dac43f688c3bf9d7ea6501d |
| work_keys_str_mv |
AT fanxu adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT yikunqin adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT wenjinghe adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT guangyihuang adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT jianlv adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT xinxinxie adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT chunlidiao adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT fentang adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT lijiang adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT rushilan adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT xiaohuicheng adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT xiaolinxiao adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT simingzeng adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT qichen adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT lingcui adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT minli adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT ningningtang adeeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT fanxu deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT yikunqin deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT wenjinghe deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT guangyihuang deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT jianlv deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT xinxinxie deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT chunlidiao deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT fentang deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT lijiang deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT rushilan deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT xiaohuicheng deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT xiaolinxiao deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT simingzeng deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT qichen deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT lingcui deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT minli deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages AT ningningtang deeptransferlearningframeworkfortheautomatedassessmentofcornealinflammationoninvivoconfocalmicroscopyimages |
| _version_ |
1718374969528811520 |