Hyperspectral Image Enhancement and Mixture Deep-Learning Classification of Corneal Epithelium Injuries.

Hyperspectral Image Enhancement and Mixture Deep-Learning Classification of Corneal Epithelium Injuries.
复制标题

DOI:
10.3390/s17112644
复制
发表时间:
2017-11-16
期刊:
Sensors (Basel, Switzerland)
影响因子:
--
通讯作者:
Ren J
Ren J
中科院分区:
其他
文献类型:
--
作者:
Noor SSM;Michael K;Marshall S;Ren J

文献摘要

参考文献

被引文献

相似文献

在我们的初步研究中,从正常和异常的猪角膜上皮组织的高光谱成像(HSI)获得的反射特征显示出相似的形态特征,但有细微的差异。在这里,我们提出了图像增强算法,可以用来提高数据到临床相关信息的可解释性,以便于诊断。共使用了25张未应用眼部染色的角膜上皮细胞图像。将三种图像特征提取方法应用于图像分类:(1)基于高斯径向基函数的支持向量机(SVM-GRBF)的直方图特征分类;(2)仅使用深度学习卷积神经网络(CNN)进行物理图像特征分类;(3)CNN与支持向量机-线性相结合的分类方法。性能结果表明,我们从直方图和长度尺度参数中选择的图像特征能够达到100%的分类精度;特别是在CNNS和CNNS-SVM上,使用80%的数据样本进行训练,20%用于测试。因此,在评估角膜上皮损伤方面,HSI作为一种在速度、客观性和可靠性方面超过现有技术的方法具有很高的潜力。
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.
DOI: 10.1016/j.exer.2008.02.006
发表时间: 2008-05-01
影响因子: 3.4
作者:
Elsheikh, Ahmed;Alhasso, Daad;Rama, Paolo
通讯作者: Rama, Paolo
DOI: 10.1038/sj.eye.6701784
发表时间: 2006-01-01
期刊: EYE
影响因子: 3.9
作者:
Lee, GA;Chiang, MYM;Shah, P
通讯作者: Shah, P
高光谱成像的最新发展,用于评估食品质量和安全性。
DOI: 10.3390/s140407248
发表时间: 2014-04-22
期刊: Sensors (Basel, Switzerland)
影响因子: --
作者:
Huang H;Liu L;Ngadi MO
通讯作者: Ngadi MO
DOI: 10.1016/j.sjopt.2011.11.001
发表时间: 2012-01-01
影响因子: 0.4
作者:
Grewal, Dilraj Singh;Grewal, Satinder Pal Singh
通讯作者: Grewal, Satinder Pal Singh
DOI: 10.1006/cgip.1993.1024
发表时间: 1993-09-01
期刊: CVGIP-GRAPHICAL MODELS AND IMAGE PROCESSING
影响因子: --
作者:
ADAMS, R
通讯作者: ADAMS, R