A deep learning based fine-grained classification algorithm for grading of visual impairment in cataract patients
DOI:
Author:
Affiliation:

1.School of electronics engineering, Xi&39;2.&39;3.an university of posts & telecommunications,;4.School of electronics engineering, Xi’an university of posts and telecommunications;5.School of Ophthalmology & Optometry and Eye Hospital, Wenzhou Medical University;6.school of electronics engineering, Xi’an university of posts and telecommunications;7.Ningbo Eye Hospital, Wenzhou Medical University,

Clc Number:

Fund Project:

The National Natural Science Foundation of China (General Program, Key Program, Major Research Plan)

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    Recent advancements in artificial intelligence (AI) have shown promising potential for the automated screening and grading of cataracts. However, the different types of visual impairment caused by cataracts exhibit similar pheno-types, posing significant challenges for accurately assessing the severity of visual impairment. To address this issue, we propose a dense convolution combined with attention mechanism and multi-level classifier (DAMC_Net) for visual impairment grading. First, the double attention mechanism is utilized to enable the DAMC_Net to focus on lesions-related regions. Then, a hierarchical multi-level classifier is constructed to enhance the recognition ability in distinguishing the severities of visual impairment while maintaining a better screening rate for normal samples. In addition, a cost-sensitive method is applied to address the problem of higher false-negative rate caused by the im-balanced dataset. Experimental results demonstrated that the DAMC_Net outperformed ResNet50 and Dense-Net121 models, with sensitivity improvements of 6.0% and 3.4% on the category of mild visual impairment caused by cataracts (MVICC), and 2.1% and 4.3% on the category of moderate to severe visual impairment caused by cataracts (MSVICC), respectively. The comparable performance on two external test datasets was achieved, further verifying the effectiveness and generalizability of the DAMC_Net.

    Reference
    Related
    Cited by
Get Citation
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:March 20,2023
  • Revised:June 12,2023
  • Adopted:June 16,2023
  • Online:
  • Published: