Literature DB >> 34352302

Differentiation of Active Corneal Infections from Healed Scars Using Deep Learning.

Mo Tiwari1, Chris Piech1, Medina Baitemirova2, Namperumalsamy V Prajna3, Muthiah Srinivasan3, Prajna Lalitha3, Natacha Villegas4, Niranjan Balachandar1, Janice T Chua5, Travis Redd6, Thomas M Lietman7, Sebastian Thrun1, Charles C Lin8.   

Abstract

PURPOSE: To develop and evaluate an automated, portable algorithm to differentiate active corneal ulcers from healed scars using only external photographs.
DESIGN: A convolutional neural network was trained and tested using photographs of corneal ulcers and scars. PARTICIPANTS: De-identified photographs of corneal ulcers were obtained from the Steroids for Corneal Ulcers Trial (SCUT), Mycotic Ulcer Treatment Trial (MUTT), and Byers Eye Institute at Stanford University.
METHODS: Photographs of corneal ulcers (n = 1313) and scars (n = 1132) from the SCUT and MUTT were used to train a convolutional neural network (CNN). The CNN was tested on 2 different patient populations from eye clinics in India (n = 200) and the Byers Eye Institute at Stanford University (n = 101). Accuracy was evaluated against gold standard clinical classifications. Feature importances for the trained model were visualized using gradient-weighted class activation mapping. MAIN OUTCOME MEASURES: Accuracy of the CNN was assessed via F1 score. The area under the receiver operating characteristic (ROC) curve (AUC) was used to measure the precision-recall trade-off.
RESULTS: The CNN correctly classified 115 of 123 active ulcers and 65 of 77 scars in patients with corneal ulcer from India (F1 score, 92.0% [95% confidence interval (CI), 88.2%-95.8%]; sensitivity, 93.5% [95% CI, 89.1%-97.9%]; specificity, 84.42% [95% CI, 79.42%-89.42%]; ROC: AUC, 0.9731). The CNN correctly classified 43 of 55 active ulcers and 42 of 46 scars in patients with corneal ulcers from Northern California (F1 score, 84.3% [95% CI, 77.2%-91.4%]; sensitivity, 78.2% [95% CI, 67.3%-89.1%]; specificity, 91.3% [95% CI, 85.8%-96.8%]; ROC: AUC, 0.9474). The CNN visualizations correlated with clinically relevant features such as corneal infiltrate, hypopyon, and conjunctival injection.
CONCLUSIONS: The CNN classified corneal ulcers and scars with high accuracy and generalized to patient populations outside of its training data. The CNN focused on clinically relevant features when it made a diagnosis. The CNN demonstrated potential as an inexpensive diagnostic approach that may aid triage in communities with limited access to eye care.
Copyright © 2021 American Academy of Ophthalmology. Published by Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Artificial intelligence; Corneal scar; Corneal ulcer; Deep learning; Infectious keratitis

Mesh:

Year:  2021        PMID: 34352302      PMCID: PMC8792172          DOI: 10.1016/j.ophtha.2021.07.033

Source DB:  PubMed          Journal:  Ophthalmology        ISSN: 0161-6420            Impact factor:   12.079


  12 in total

1.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.

Authors:  Varun Gulshan; Lily Peng; Marc Coram; Martin C Stumpe; Derek Wu; Arunachalam Narayanaswamy; Subhashini Venugopalan; Kasumi Widner; Tom Madams; Jorge Cuadros; Ramasamy Kim; Rajiv Raman; Philip C Nelson; Jessica L Mega; Dale R Webster
Journal:  JAMA       Date:  2016-12-13       Impact factor: 56.272

Review 2.  Update on the Management of Infectious Keratitis.

Authors:  Ariana Austin; Tom Lietman; Jennifer Rose-Nussbaumer
Journal:  Ophthalmology       Date:  2017-09-21       Impact factor: 12.079

3.  Teleophthalmic Approach for Detection of Corneal Diseases: Accuracy and Reliability.

Authors:  Maria A Woodward; David C Musch; Christopher T Hood; Jonathan B Greene; Leslie M Niziol; V Swetha E Jeganathan; Paul P Lee
Journal:  Cornea       Date:  2017-10       Impact factor: 2.651

4.  Natural Language-based Machine Learning Models for the Annotation of Clinical Radiology Reports.

Authors:  John Zech; Margaret Pain; Joseph Titano; Marcus Badgeley; Javin Schefflein; Andres Su; Anthony Costa; Joshua Bederson; Joseph Lehar; Eric Karl Oermann
Journal:  Radiology       Date:  2018-01-30       Impact factor: 11.105

5.  Detecting and interpreting myocardial infarction using fully convolutional neural networks.

Authors:  Nils Strodthoff; Claas Strodthoff
Journal:  Physiol Meas       Date:  2019-01-15       Impact factor: 2.833

6.  Dermatologist-level classification of skin cancer with deep neural networks.

Authors:  Andre Esteva; Brett Kuprel; Roberto A Novoa; Justin Ko; Susan M Swetter; Helen M Blau; Sebastian Thrun
Journal:  Nature       Date:  2017-01-25       Impact factor: 49.962

7.  Epidemiology of ulcerative keratitis in Northern California.

Authors:  Bennie H Jeng; David C Gritz; Abha B Kumar; Douglas S Holsclaw; Travis C Porco; Scott D Smith; John P Whitcher; Todd P Margolis; Ira G Wong
Journal:  Arch Ophthalmol       Date:  2010-08

8.  The mycotic ulcer treatment trial: a randomized trial comparing natamycin vs voriconazole.

Authors:  N Venkatesh Prajna; Tiruvengada Krishnan; Jeena Mascarenhas; Revathi Rajaraman; Lalitha Prajna; Muthiah Srinivasan; Anita Raghavan; Catherine E Oldenburg; Kathryn J Ray; Michael E Zegans; Stephen D McLeod; Travis C Porco; Nisha R Acharya; Thomas M Lietman
Journal:  JAMA Ophthalmol       Date:  2013-04       Impact factor: 7.389

9.  Seasonal trends of microbial keratitis in South India.

Authors:  Charles C Lin; Prajna Lalitha; Muthiah Srinivasan; N Venkatesh Prajna; Stephen D McLeod; Nisha R Acharya; Thomas M Lietman; Travis C Porco
Journal:  Cornea       Date:  2012-10       Impact factor: 2.651

10.  Automated Grading of Age-Related Macular Degeneration From Color Fundus Images Using Deep Convolutional Neural Networks.

Authors:  Philippe M Burlina; Neil Joshi; Michael Pekala; Katia D Pacheco; David E Freund; Neil M Bressler
Journal:  JAMA Ophthalmol       Date:  2017-11-01       Impact factor: 7.389

View more
  4 in total

Review 1.  Artificial intelligence and corneal diseases.

Authors:  Linda Kang; Dena Ballouz; Maria A Woodward
Journal:  Curr Opin Ophthalmol       Date:  2022-07-12       Impact factor: 4.299

2.  Clinical Characteristics and Outcomes of Fungal Keratitis in the United Kingdom 2011-2020: A 10-Year Study.

Authors:  Darren Shu Jeng Ting; Mohamed Galal; Bina Kulkarni; Mohamed S Elalfy; Damian Lake; Samer Hamada; Dalia G Said; Harminder S Dua
Journal:  J Fungi (Basel)       Date:  2021-11-12

3.  Achieving diagnostic excellence for infectious keratitis: A future roadmap.

Authors:  Darren S J Ting; James Chodosh; Jodhbir S Mehta
Journal:  Front Microbiol       Date:  2022-10-03       Impact factor: 6.064

Review 4.  Infectious keratitis: A review.

Authors:  Maria Cabrera-Aguas; Pauline Khoo; Stephanie L Watson
Journal:  Clin Exp Ophthalmol       Date:  2022-06-03       Impact factor: 4.383

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.