Hyperspectral image enhancement and mixture deep-learning classification of corneal epithelium injury

Siti Salwa Md Noor, Kaleena Michael, Stephen Marshall, Jinchang Ren

Research output: Contribution to journalArticle

20 Citations (Scopus)
69 Downloads (Pure)

Abstract

In our preliminary study, the reflectance signatures obtained from hyperspectral imaging (HSI) of normal and abnormal corneal epithelium tissues of porcine show similar morphology with subtle differences. Here we present image enhancement algorithms that can be used to improve the interpretability of data into clinically relevant information to facilitate diagnostics. A total of 25 corneal epithelium images without the application of eye staining were used. Three image feature extraction approaches were applied for image classification: (i) image feature classification from histogram using a support vector machine with a Gaussian radial basis function (SVM-GRBF); (ii) physical image feature classification using deep-learning Convolutional Neural Networks (CNNs) only, and (iii) the combined classification of CNNs and SVM-Linear. The performance results indicate that our chosen image features from the histogram and length-scale parameter were able to classify with up to 100% accuracy; particularly, at CNNs and CNNs-SVM, by employing 80% of the data sample for training and 20% for testing. Thus, in the assessment of corneal epithelium injuries, HSI has high potential as a method that could surpass current technologies regarding speed, objectivity, and reliability.
Original languageEnglish
Article number2644
Number of pages24
JournalSensors
Volume17
Issue number11
Early online date16 Nov 2017
DOIs
Publication statusPublished - 24 Nov 2017

Keywords

  • corneal epithelium
  • hyperspectral imaging
  • support vector machine
  • convolutional neural networks
  • image enhancement

Fingerprint Dive into the research topics of 'Hyperspectral image enhancement and mixture deep-learning classification of corneal epithelium injury'. Together they form a unique fingerprint.

Cite this