PlumX Metrics
Embed PlumX Metrics

Nature-inspired computing and machine learning based classification approach for glaucoma in retinal fundus images

Multimedia Tools and Applications, ISSN: 1573-7721, Vol: 82, Issue: 27, Page: 42851-42899
2023
  • 19
    Citations
  • 0
    Usage
  • 20
    Captures
  • 1
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

  • Citations
    19
    • Citation Indexes
      19
  • Captures
    20
  • Mentions
    1
    • News Mentions
      1
      • News
        1

Most Recent News

Researchers' Work from GLA University Focuses on Glaucoma (Nature-inspired Computing and Machine Learning Based Classification Approach for Glaucoma In Retinal Fundus Images)

2023 JUN 09 (NewsRx) -- By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News -- A new study on

Article Description

Glaucoma, commonly known as the silent thief of sight, is the second most common cause of blindness in humans, and the number of cases is steadily increasing. Conventional diagnostic methods utilized by ophthalmologists include the assessment of intraocular pressure using tonometry, pachymetry, etc. Yet, each of these evaluations is time-consuming, requires human involvement, and is prone to subjective errors. In order to overcome these hurdles, practitioners are studying retinal pictures for glaucoma diagnosis within the field of medical imaging. In addition, computer-assisted diagnosis (CAD) systems can be created to solve these obstacles by using machine learning approaches to classify retinal pictures as "healthy" or "infected." This work presents a reduced set of structural and nonstructural features(characteristics) to characterize pictures of the retinal fundus. The grey level co-occurrence matrix (GLCM), the grey level run length matrix (GLRM), the first order statistical matrix (FOS), the wavelet, and the structural features (like disc damage likelihood scale (DDLS) and cup to disc ratio (CDR)) are extracted. This set of features is sent to three classical soft computing algorithms (Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC), and Binary Cuckoo Search (BCS)) and their two-layered model (PSO-ABC) to generate subset of reduced features (feature selection phase) that computes auspicious accuracy when sent to three machine learning classifiers (Random Forest (RF), Support Vector Machine (SVM), and Ensemble of RF, SVM, and Logistic Regression). According to our understanding, these four soft computing algorithms are rarely employed in this application field. For analyzing the performance of suggested strategy, the ORIGA, REFUGE, and their combinations are chosen as subject datasets. Standard statistical performance indicators, including accuracy, specificity, precision, and sensitivity, are calculated. The BCS delivers remarkable performance with a minimum of 91% accuracy and a maximum of 98.46% accuracy. PSO-ABC heavily decreases the original feature set, with minor accuracy sacrifices. The quantitative results are also compared in light of the most recent state-of-the-art published research. Owing to its exemplary performance, the suggested method will undoubtedly serve as a second opinion for ophthalmologists.

Bibliographic Details

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know