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

Md Noor, Siti Salwa and Michael, Kaleena and Marshall, Stephen and Ren, Jinchang (2017) Hyperspectral image enhancement and mixture deep-learning classification of corneal epithelium injury. Sensors, 17 (11). 2644. ISSN 1424-8220 (https://doi.org/10.3390/s17112644)

[thumbnail of Salwa-Md-Noor-etal-Sensors-2017-Hyperspectral-image-enhancement-and-mixture-deep]
Text. Filename: Salwa_Md_Noor_etal_Sensors_2017_Hyperspectral_image_enhancement_and_mixture_deep.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo

Download (4MB)| Preview


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.


Md Noor, Siti Salwa ORCID logoORCID: https://orcid.org/0000-0001-5288-7510, Michael, Kaleena, Marshall, Stephen ORCID logoORCID: https://orcid.org/0000-0001-7079-5628 and Ren, Jinchang ORCID logoORCID: https://orcid.org/0000-0001-6116-3194;