Filamentous Fungal Keratitis in Taiwan: Based on Molecular Diagnosis

Hung, Ning; Yeh, Lung‐Kun; Hui‐Kang, David; Lin, Hsin-Chiung; Tan, Hsin-Yuan; Chen, Hung-Chi; Sun, Pei‐Lun; Hsiao, Ching-Hsi

doi:10.1167/tvst.9.8.32

Cited by 12 publications

(14 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early diagnosis of FK is important but challenging. No pathognomonic features can wholly support a physician’s diagnosis, and delayed diagnosis can increase the difficulty of FK management, often necessitating surgical intervention and resulting in poor visual outcomes [ 5 ]. Culture-based methods are the current cornerstone for FK diagnosis; however, a time lag exists between patient presentation and diagnosis.…”

Section: Discussionmentioning

confidence: 99%

“…It is considered an epidemic, particularly within South Asia, Southeast Asia, and East Asia, and in regions where fungal keratitis (FK) accounts for more than 50% of all MK cases [ 4 ]. The management of FK is challenging and may require surgical intervention, and FK has been reported to have poor visual outcomes [ 5 , 6 ]. Hence, early diagnosis is essential for avoiding devastating vision-threatening outcomes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using Slit-Lamp Images for Deep Learning-Based Identification of Bacterial and Fungal Keratitis: Model Development and Validation with Different Convolutional Neural Networks

et al. 2021

Self Cite

View full text Add to dashboard Cite

In this study, we aimed to develop a deep learning model for identifying bacterial keratitis (BK) and fungal keratitis (FK) by using slit-lamp images. We retrospectively collected slit-lamp images of patients with culture-proven microbial keratitis between 1 January 2010 and 31 December 2019 from two medical centers in Taiwan. We constructed a deep learning algorithm consisting of a segmentation model for cropping cornea images and a classification model that applies different convolutional neural networks (CNNs) to differentiate between FK and BK. The CNNs included DenseNet121, DenseNet161, DenseNet169, DenseNet201, EfficientNetB3, InceptionV3, ResNet101, and ResNet50. The model performance was evaluated and presented as the area under the curve (AUC) of the receiver operating characteristic curves. A gradient-weighted class activation mapping technique was used to plot the heat map of the model. By using 1330 images from 580 patients, the deep learning algorithm achieved the highest average accuracy of 80.0%. Using different CNNs, the diagnostic accuracy for BK ranged from 79.6% to 95.9%, and that for FK ranged from 26.3% to 65.8%. The CNN of DenseNet161 showed the best model performance, with an AUC of 0.85 for both BK and FK. The heat maps revealed that the model was able to identify the corneal infiltrations. The model showed a better diagnostic accuracy than the previously reported diagnostic performance of both general ophthalmologists and corneal specialists.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Using Slit-Lamp Images for Deep Learning-Based Identification of Bacterial and Fungal Keratitis: Model Development and Validation with Different Convolutional Neural Networks

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is considered an epidemic, particularly within South Asia, Southeast Asia, and East Asia and in regions where fungal keratitis (FK) accounts for more than 50% of all MK cases [4]. The management of FK is challenging and may require surgical intervention, and FK has been reported to have poor visual outcomes [5,6]. Hence, early diagnosis is essential for avoiding devastating vision-threatening outcomes.…”

Section: Introductionmentioning

confidence: 99%

Using Slit-Lamp Images for Deep Learning–Based Identification of Bacterial and Fungal Keratitis

Hung¹,

Kang²,

Shih³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In this study, we aimed to develop a deep learning model for identifying bacterial keratitis (BK) and fungal keratitis (FK) by using slit-lamp images. We retrospectively collected slit-lamp images of patients with culture-proven microbial keratitis between January 1, 2010, and December 31, 2019, from two medical centers in Taiwan. We constructed a deep learning algorithm, consisting of a segmentation model for cropping cornea images and a classification model that applies convolutional neural networks to differentiate between FK and BK. The model performance was evaluated and presented as the area under the curve (AUC) of the receiver operating characteristic curves. A gradient-weighted class activation mapping technique was used to plot the heatmap of the model. By using 1330 images from 580 patients, the deep learning algorithm achieved an average diagnostic accuracy of 80.00%. The diagnostic accuracy for BK ranged from 79.59% to 95.91% and that for FK ranged from 26.31% to 63.15%. DenseNet169 showed the best model performance, with an AUC of 0.78 for both BK and FK. The heat maps revealed that the model was able to identify the corneal infiltrations. The model showed better diagnostic accuracy than the previously reported diagnostic performance of both general ophthalmologists and corneal specialists.

show abstract

“…[2] An increase in its occurrence has been conveyed in recent years, but in terms of diagnosis and treatment, the disease is still a challenge. [4][5][6][7] Among the prevalent causes of fungal keratitis worldwide are Aspergillus and Fusarium. Aspergillus has the worst prognosis in general, but it shows a positive response to antifungal drugs.…”

Section: Introductionmentioning

confidence: 99%

Incidence of fungal keratitis in Libya: An epidemiological study

Atia

Ashour

Alfaigh³

2021

AUJMSR

View full text Add to dashboard Cite

Objectives: The aim of this study was to assess the occurrence of eye fungal infection among patients attending the eye hospital in Tripoli city, Libya. Materials and Methods: Seventy-one patients with ocular fungal infections were subjected to clinical and microbiological investigations. They were selected from patients attending the Tripoli Eye Hospital. The specimens of the external ocular infections were collected using sterile swab and inoculated to different culture media. Data were presented as count and percentages. Results: The current findings showed that Aspergillus was the most common causative agent, being responsible for 91.54% of the all cases, followed by Candida albicans (8.46%). Conclusion: Occurrence of fungal keratitis gradually increased in the years after 2009, especially after 2013. Knowledge of the pathological course and clinical features of fungal keratitis will undoubtedly bead in early diagnosis and treatment, with reduction in ocular morbidity.

show abstract

Filamentous Fungal Keratitis in Taiwan: Based on Molecular Diagnosis

Cited by 12 publications

References 47 publications

Using Slit-Lamp Images for Deep Learning-Based Identification of Bacterial and Fungal Keratitis: Model Development and Validation with Different Convolutional Neural Networks

Using Slit-Lamp Images for Deep Learning-Based Identification of Bacterial and Fungal Keratitis: Model Development and Validation with Different Convolutional Neural Networks

Using Slit-Lamp Images for Deep Learning–Based Identification of Bacterial and Fungal Keratitis

Incidence of fungal keratitis in Libya: An epidemiological study

Contact Info

Product

Resources

About