A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images
PURPOSE: 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.
METHODS: 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.
RESULTS: 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).
CONCLUSIONS: 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.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
Zur Gesamtaufnahme - volume:16 |
---|---|
Enthalten in: |
PloS one - 16(2021), 6 vom: 04., Seite e0252653 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Xu, Fan [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 17.11.2021 Date Revised 17.11.2021 published: Electronic-eCollection Citation Status MEDLINE |
---|
doi: |
10.1371/journal.pone.0252653 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM326300929 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM326300929 | ||
003 | DE-627 | ||
005 | 20231225194309.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1371/journal.pone.0252653 |2 doi | |
028 | 5 | 2 | |a pubmed24n1087.xml |
035 | |a (DE-627)NLM326300929 | ||
035 | |a (NLM)34081736 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Xu, Fan |e verfasserin |4 aut | |
245 | 1 | 2 | |a A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images |
264 | 1 | |c 2021 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 17.11.2021 | ||
500 | |a Date Revised 17.11.2021 | ||
500 | |a published: Electronic-eCollection | ||
500 | |a Citation Status MEDLINE | ||
520 | |a PURPOSE: 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 | ||
520 | |a METHODS: 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 | ||
520 | |a RESULTS: 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) | ||
520 | |a CONCLUSIONS: 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 | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
700 | 1 | |a Qin, Yikun |e verfasserin |4 aut | |
700 | 1 | |a He, Wenjing |e verfasserin |4 aut | |
700 | 1 | |a Huang, Guangyi |e verfasserin |4 aut | |
700 | 1 | |a Lv, Jian |e verfasserin |4 aut | |
700 | 1 | |a Xie, Xinxin |e verfasserin |4 aut | |
700 | 1 | |a Diao, Chunli |e verfasserin |4 aut | |
700 | 1 | |a Tang, Fen |e verfasserin |4 aut | |
700 | 1 | |a Jiang, Li |e verfasserin |4 aut | |
700 | 1 | |a Lan, Rushi |e verfasserin |4 aut | |
700 | 1 | |a Cheng, Xiaohui |e verfasserin |4 aut | |
700 | 1 | |a Xiao, Xiaolin |e verfasserin |4 aut | |
700 | 1 | |a Zeng, Siming |e verfasserin |4 aut | |
700 | 1 | |a Chen, Qi |e verfasserin |4 aut | |
700 | 1 | |a Cui, Ling |e verfasserin |4 aut | |
700 | 1 | |a Li, Min |e verfasserin |4 aut | |
700 | 1 | |a Tang, Ningning |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t PloS one |d 2006 |g 16(2021), 6 vom: 04., Seite e0252653 |w (DE-627)NLM167327399 |x 1932-6203 |7 nnns |
773 | 1 | 8 | |g volume:16 |g year:2021 |g number:6 |g day:04 |g pages:e0252653 |
856 | 4 | 0 | |u http://dx.doi.org/10.1371/journal.pone.0252653 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 16 |j 2021 |e 6 |b 04 |h e0252653 |