Literature DB >> 33609928

A deep learning approach to identify blepharoptosis by convolutional neural networks.

Ju-Yi Hung1, Chandrashan Perera2, Ke-Wei Chen3, David Myung2, Hsu-Kuang Chiu4, Chiou-Shann Fuh5, Cherng-Ru Hsu6, Shu-Lang Liao7, Andrea Lora Kossler8.   

Abstract

PURPOSE: Blepharoptosis is a known cause of reversible vision loss. Accurate assessment can be difficult, especially amongst non-specialists. Existing automated techniques disrupt clinical workflow by requiring user input, or placement of reference markers. Neural networks are known to be effective in image classification tasks. We aim to develop an algorithm that can accurately identify blepharoptosis from a clinical photo.
METHODS: A total of 500 clinical photographs from patients with and without blepharoptosis were sourced from a tertiary ophthalmic center in Taiwan. Images were labeled by two oculoplastic surgeons, with an independent third oculoplastic surgeon to adjudicate disagreements. These images were used to train a series of convolutional neural networks (CNNs) to ascertain the best CNN architecture for this particular task.
RESULTS: Of the models that trained on the dataset, most were able to identify ptosis images with reasonable accuracy. We found the best performing model to use the DenseNet121 architecture without pre-training which achieved a sensitivity of 90.1 % with a specificity of 82.4 %, compared to the worst performing model which was used a Resnet34 architecture with pre-training, achieving a sensitivity of 74.1 %, and specificity of 63.6 %. Models with and without pre-training performed similarly (mean accuracy 82.6 % vs. 85.8 % respectively, p = 0.06), though models with pre-training took less time to train (1-minute vs. 16 min, p < 0.01).
CONCLUSIONS: We report the use of AI to accurately diagnose blepharoptosis from a clinical photograph with no external reference markers or user input requirement. Most current-generation CNN architectures performed reasonably on this task, with the DenseNet121, and Resnet18 architectures without pre-training performing best in our dataset.
Copyright © 2021 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Artificial intelligence; Automated identification; Blepharoptosis; Deep learning models; High accuracy; Novel medical image dataset

Year:  2021        PMID: 33609928     DOI: 10.1016/j.ijmedinf.2021.104402

Source DB:  PubMed          Journal:  Int J Med Inform        ISSN: 1386-5056            Impact factor:   4.046


  2 in total

1.  Developing an iOS application that uses machine learning for the automated diagnosis of blepharoptosis.

Authors:  Hitoshi Tabuchi; Daisuke Nagasato; Hiroki Masumoto; Mao Tanabe; Naofumi Ishitobi; Hiroki Ochi; Yoshie Shimizu; Yoshiaki Kiuchi
Journal:  Graefes Arch Clin Exp Ophthalmol       Date:  2021-11-04       Impact factor: 3.117

2.  An Outperforming Artificial Intelligence Model to Identify Referable Blepharoptosis for General Practitioners.

Authors:  Ju-Yi Hung; Ke-Wei Chen; Chandrashan Perera; Hsu-Kuang Chiu; Cherng-Ru Hsu; David Myung; An-Chun Luo; Chiou-Shann Fuh; Shu-Lang Liao; Andrea Lora Kossler
Journal:  J Pers Med       Date:  2022-02-15
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.