当前位置: X-MOL 学术Pattern Recogn. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A modified capsule network algorithm for oct corneal image segmentation
Pattern Recognition Letters ( IF 3.9 ) Pub Date : 2021-01-13 , DOI: 10.1016/j.patrec.2021.01.005
H. James Deva Koresh , Shanty Chacko , M. Periyanayagi

Cornea is the outmost layer of an eye helps to focuses the light rays towards the retinal layer of the eye. The irregular thickness of the corneal layer results in poor focus of light rays over the retinal layer and hence it results in blur vision. Lasik is a surgical procedure made for correcting the irregular thickness of the cornea to certain extent for making the light rays to fall exactly on the retinal layer. In order to undergo with a lasik procedure, an eye must have sufficient thickness of corneal layer to tolerate the medical procedure. Similarly, the corneal layers are can't be operated after certain extent. Therefore there is a need for pre-surgical planning by measuring the thickness availability of the corneal layer. The proposed work is engaged to identify the three major boundaries of the corneal layer using a capsule network based algorithm. The proposed work is segregated as preprocessing, classification and segmentation. A hybrid speckle noise reduction filter was employed in the preprocessing stage to minimize the noise presence in the corneal images. Then the images are moved further to train the ClassCaps algorithm to classify a better noiseless image from the group of test images. The modified SegCaps algorithm was utilized in this work to detect the three major boundaries of the cornea from the noiseless image output from the ClassCaps algorithm. The performance of the proposed algorithm was verified with the several classification and segmentation algorithm to prove its accuracy.



中文翻译:

八度角膜图像分割的改进胶囊网络算法

角膜是眼睛的最外层,有助于将光线聚焦到眼睛的视网膜层。角膜层的不规则厚度导致光线在视网膜层上的聚焦不良,因此导致视力模糊。Lasik是一种外科手术程序,用于将角膜的不规则厚度校正到一定程度,以使光线精确地落在视网膜层上。为了进行LASIK手术,眼睛必须具有足够厚度的角膜层以耐受医疗程序。同样,一定程度后不能操作角膜层。因此,需要通过测量角膜层的厚度可用性来进行手术前的计划。利用基于胶囊网络的算法,从事拟议工作以识别角膜层的三个主要边界。拟议的工作分为预处理,分类和细分。在预处理阶段使用了混合斑点降噪滤波器,以最大程度地减少角膜图像中的噪声。然后将图像进一步移动以训练ClassCaps算法,以从测试图像组中对更好的无噪声图像进行分类。在这项工作中使用了改进的SegCaps算法,以从ClassCaps算法输出的无噪声图像中检测出角膜的三个主要边界。通过几种分类分割算法验证了该算法的性能,证明了算法的准确性。分类和细分。在预处理阶段使用了混合斑点降噪滤波器,以最大程度地减少角膜图像中的噪声。然后将图像进一步移动以训练ClassCaps算法,以从测试图像组中对更好的无噪声图像进行分类。在这项工作中使用了改进的SegCaps算法,以从ClassCaps算法输出的无噪声图像中检测出角膜的三个主要边界。通过几种分类分割算法验证了该算法的性能,证明了算法的准确性。分类和细分。在预处理阶段使用了混合斑点降噪滤波器,以最大程度地减少角膜图像中的噪声。然后将图像进一步移动以训练ClassCaps算法,以从测试图像组中对更好的无噪声图像进行分类。在这项工作中使用了改进的SegCaps算法,以从ClassCaps算法输出的无噪声图像中检测出角膜的三个主要边界。通过几种分类分割算法验证了该算法的性能,证明了算法的准确性。然后将图像进一步移动以训练ClassCaps算法,以从测试图像组中对更好的无噪声图像进行分类。在这项工作中使用了改进的SegCaps算法,以从ClassCaps算法输出的无噪声图像中检测出角膜的三个主要边界。通过几种分类分割算法验证了该算法的性能,证明了算法的准确性。然后将图像进一步移动以训练ClassCaps算法,以从测试图像组中对更好的无噪声图像进行分类。在这项工作中使用了改进的SegCaps算法,以从ClassCaps算法输出的无噪声图像中检测出角膜的三个主要边界。通过几种分类分割算法验证了该算法的性能,证明了算法的准确性。

更新日期:2021-01-22
down
wechat
bug