|
|
A Classification Methods for Retinal Nerve Fibre Layer Analysis
Zapletal, Petr ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
This thesis is deal with classification for retinal nerve fibre layer. Texture features from six texture analysis methods are used for classification. All methods calculate feature vector from inputs images. This feature vector is characterized for every cluster (class). Classification is realized by three supervised learning algorithms and one unsupervised learning algorithm. The first testing algorithm is called Ho-Kashyap. The next is Bayess classifier NDDF (Normal Density Discriminant Function). The third is the Nearest Neighbor algorithm k-NN and the last tested classifier is algorithm K-means, which belongs to clustering. For better compactness of this thesis, three methods for selection of training patterns in supervised learning algorithms are implemented. The methods are based on Repeated Random Subsampling Cross Validation, K-Fold Cross Validation and Leave One Out Cross Validation algorithms. All algorithms are quantitatively compared in the sense of classication error evaluation.
|
|
|
Textural Analysis of Nerve Fibre Layer in Retinal Images
Novotný, Adam ; Jan, Jiří (referee) ; Odstrčilík, Jan (advisor)
This work describes completely new approach to detection of retinal nerve fibre layer (RNFL) loss in colour fundus images. Such RNFL losses indicate eye glaucoma illness and an early diagnosis of RNFL changes is very important for successful treatment. Method is presented with the purpose of supporting glaucoma diagnosis in ophthalmology. The proposed textural analysis method utilizes local binary patterns (LBP). This approach is characterized especially by computational simplicity and insensitivity to monotonic changes of illumination. Image histograms of LBP distributions are used to gain several textural features aimed to classify healthy or glaucomatous tissue of the retina. The method was experimentally tested using fundus images of glaucomatous patients with focal RNFL loss. The results show that the proposed method can be used in order to supporting diagnosis of glaucoma with satisfactory efficiency.
|
|
|
Textural Analysis of Nerve Fibre Layer in Retinal Images
Novotný, Adam ; Jan, Jiří (referee) ; Odstrčilík, Jan (advisor)
This work describes completely new approach to detection of retinal nerve fibre layer (RNFL) loss in colour fundus images. Such RNFL losses indicate eye glaucoma illness and an early diagnosis of RNFL changes is very important for successful treatment. Method is presented with the purpose of supporting glaucoma diagnosis in ophthalmology. The proposed textural analysis method utilizes local binary patterns (LBP). This approach is characterized especially by computational simplicity and insensitivity to monotonic changes of illumination. Image histograms of LBP distributions are used to gain several textural features aimed to classify healthy or glaucomatous tissue of the retina. The method was experimentally tested using fundus images of glaucomatous patients with focal RNFL loss. The results show that the proposed method can be used in order to supporting diagnosis of glaucoma with satisfactory efficiency.
|
|
|
A Classification Methods for Retinal Nerve Fibre Layer Analysis
Zapletal, Petr ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
This thesis is deal with classification for retinal nerve fibre layer. Texture features from six texture analysis methods are used for classification. All methods calculate feature vector from inputs images. This feature vector is characterized for every cluster (class). Classification is realized by three supervised learning algorithms and one unsupervised learning algorithm. The first testing algorithm is called Ho-Kashyap. The next is Bayess classifier NDDF (Normal Density Discriminant Function). The third is the Nearest Neighbor algorithm k-NN and the last tested classifier is algorithm K-means, which belongs to clustering. For better compactness of this thesis, three methods for selection of training patterns in supervised learning algorithms are implemented. The methods are based on Repeated Random Subsampling Cross Validation, K-Fold Cross Validation and Leave One Out Cross Validation algorithms. All algorithms are quantitatively compared in the sense of classication error evaluation.
|
guest ::
