scholarly journals Fungal Keratitis - Improving Diagnostics by Confocal Microscopy

2013 ◽  
Vol 4 (3) ◽  
pp. 303-310 ◽  
Author(s):  
Esben Nielsen ◽  
Steffen Heegaard ◽  
Jan Ulrik Prause ◽  
Anders Ivarsen ◽  
Klaus Leth Mortensen ◽  
...  
2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Jaya D. Chidambaram ◽  
Namperumalsamy V. Prajna ◽  
Srikanthi Palepu ◽  
Shruti Lanjewar ◽  
Manisha Shah ◽  
...  

2011 ◽  
Vol 14 (1) ◽  
pp. 1-9 ◽  
Author(s):  
Eric C. Ledbetter ◽  
Nita L. Irby ◽  
Sung G. Kim

2016 ◽  
Vol 27 (1) ◽  
pp. 10-15 ◽  
Author(s):  
Ágnes Füst ◽  
Jeannette Tóth ◽  
Gyula Simon ◽  
László Imre ◽  
Zoltán Z. Nagy

Purpose To report on the presence of 4 different structures visualized by confocal microscopy in patients whose clinical presentation suggested infection by Acanthamoeba. Methods Data and charts of 28 consecutive patients were analyzed in a retrospective study. Four types of structures were recognized by confocal microscopy performed with HRT II Rostock Cornea Module: trophozoites, double-walled cysts, signet rings, and bright spots. The 28 patients (mean age 30.8 years, range 17-61 years, 10 male, 18 female) were divided into 4 groups according to the diagnosis established later by microscopic examination of smear, culture, response to therapy, and the course of keratitis. The 4 groups were Acanthamoeba keratitis (AK), Acanthamoeba suspect (AK-suspect), bacterial keratitis (BK), and fungal keratitis (FK). Results The rate of patients in AK, AK-suspect, FK, and BK groups where bright spots were found were 100%, 100%, 40%, and 55%, respectively. The sensitivity of presence of bright spots in the in vivo confocal microscopy in Acanthamoeba keratitis was 100% (95% confidence interval [CI] 73.5% to 100.00%) and specificity was 50% (CI 24.7% to 75.4%). When cases where the only signs of Acanthamoeba were bright spots were excluded, and only those cases were counted where any of cysts, trophozoites, or signet rings were also found, the sensitivity was 67% (95% CI 34. 9% to 90.1%) and the specificity was 94% (95% CI 69.8% to 99.8%). Conclusions The relatively high rate of bright spots in non- Acanthamoeba keratitis challenges the assumption that bright spots seen by confocal microscopy are a specific indication of Acanthamoeba keratitis.


2006 ◽  
Vol 91 (5) ◽  
pp. 588-591 ◽  
Author(s):  
E. Brasnu ◽  
T. Bourcier ◽  
B. Dupas ◽  
S. Degorge ◽  
T. Rodallec ◽  
...  

Cornea ◽  
2010 ◽  
Vol 29 (12) ◽  
pp. 1346-1352 ◽  
Author(s):  
Yuki Takezawa ◽  
Atsushi Shiraishi ◽  
Eriko Noda ◽  
Yuko Hara ◽  
Masahiko Yamaguchi ◽  
...  

2017 ◽  
Vol 101 (8) ◽  
pp. 1119-1123 ◽  
Author(s):  
Jaya Devi Chidambaram ◽  
Namperumalsamy Venkatesh Prajna ◽  
Natasha Larke ◽  
David Macleod ◽  
Palepu Srikanthi ◽  
...  

Cornea ◽  
2009 ◽  
Vol 28 (1) ◽  
pp. 11-13 ◽  
Author(s):  
Sujata Das ◽  
Monica Samant ◽  
Prashant Garg ◽  
Pravin Krishna Vaddavalli ◽  
Geeta K Vemuganti

2019 ◽  
Vol 40 (2) ◽  
pp. 483-491 ◽  
Author(s):  
Seyed Ali Tabatabaei ◽  
Mohammad Soleimani ◽  
Seyed Mehdi Tabatabaei ◽  
Amir Houshang Beheshtnejad ◽  
Niloufar Valipour ◽  
...  

2021 ◽  
Vol 8 ◽  
Author(s):  
Fan Xu ◽  
Li Jiang ◽  
Wenjing He ◽  
Guangyi Huang ◽  
Yiyi Hong ◽  
...  

Background: Artificial intelligence (AI) has great potential to detect fungal keratitis using in vivo confocal microscopy images, but its clinical value remains unclarified. A major limitation of its clinical utility is the lack of explainability and interpretability.Methods: An explainable AI (XAI) system based on Gradient-weighted Class Activation Mapping (Grad-CAM) and Guided Grad-CAM was established. In this randomized controlled trial, nine ophthalmologists (three expert ophthalmologists, three competent ophthalmologists, and three novice ophthalmologists) read images in each of the conditions: unassisted, AI-assisted, or XAI-assisted. In unassisted condition, only the original IVCM images were shown to the readers. AI assistance comprised a histogram of model prediction probability. For XAI assistance, explanatory maps were additionally shown. The accuracy, sensitivity, and specificity were calculated against an adjudicated reference standard. Moreover, the time spent was measured.Results: Both forms of algorithmic assistance increased the accuracy and sensitivity of competent and novice ophthalmologists significantly without reducing specificity. The improvement was more pronounced in XAI-assisted condition than that in AI-assisted condition. Time spent with XAI assistance was not significantly different from that without assistance.Conclusion: AI has shown great promise in improving the accuracy of ophthalmologists. The inexperienced readers are more likely to benefit from the XAI system. With better interpretability and explainability, XAI-assistance can boost ophthalmologist performance beyond what is achievable by the reader alone or with black-box AI assistance.


Sign in / Sign up

Export Citation Format

Share Document