|
|
Medical image segmentation based on graph cut with shape prior
Kozlová, Dominika ; Jan, Jiří (referee) ; Jakubíček, Roman (advisor)
This thesis deals with a graph-based image segmentation and its improvement by using the information about the shape of the object for creating specific graph architecture (template). There are described basics of the graph theory, which is the basis of the graph segmentation methods. Designed segmentation algorithm was realized in 2D with graphical user interface in MATLAB. For segmentation of volume data, the method was extended into 3D. Implemented method was tested on simulated data and on real CT and MRI images of vertebra and brain. Obtained results were evaluated and compared with the original method without using the template.
|
|
|
Detection of specific anatomical structures in CT data via convolutional neural networks
Kozlová, Dominika ; Jan, Jiří (referee) ; Jakubíček, Roman (advisor)
This thesis deals with the issue of detection of anatomical structures in medical images using convolutional neural networks (CNN). At first there are described methods of machine learning, convolutional neural networks and selected methods for detection using CNN. In this work was created a database of annotated CT images of ten anatomical structures (head, heart, aorta, left and right lung, spine, liver, left and right kidney, spleen). A method for detecting these structures was designed, that contains two approaches of region proposals from image, CNN and postprocessing to obtain the detection result. The designed algorithm was implemented in the Python programming language using the TensorFlow library. Obtained results of validation of the network and the detection results are presented and discussed in the last chapter.
|
|
|
Detection Of Anatomical Structures In Ct Data
Using Convolutional Neural Networks
Kozlová, Dominika
This paper deals with a detection of anatomical structures in medical images using convolutional neural networks (CNN). The designed algorithm contains 2 methods for region proposals and CNN for their classification into categories. Output of the CNN is then postprocessed to obtain the detection result. Categories for detection are head, spine, heart, left and right lung, aorta, liver, left and right kidney, spleen and background. For training and validation of the network were created 2 sets of CT data with annotated areas of selected structures.
|
|
|
Medical Image Segmentation Based on Graph Cut with Shape Prior
Kozlová, Dominika
This paper deals with a graph-based image segmentation and its improvement by using the information about the shape of the object for creating specific graph architecture (template). Improved method allows the cut to prefer more complicated structures, especially when the image contains a lot of noise and the object is hardly indistinguishable from the background. Algorithm was tested on simulated data and real CT and MRI images of vertebra and brain in 2D. Method was also extended to 3D further purposes.
|
|
|
Detection of specific anatomical structures in CT data via convolutional neural networks
Kozlová, Dominika ; Jan, Jiří (referee) ; Jakubíček, Roman (advisor)
This thesis deals with the issue of detection of anatomical structures in medical images using convolutional neural networks (CNN). At first there are described methods of machine learning, convolutional neural networks and selected methods for detection using CNN. In this work was created a database of annotated CT images of ten anatomical structures (head, heart, aorta, left and right lung, spine, liver, left and right kidney, spleen). A method for detecting these structures was designed, that contains two approaches of region proposals from image, CNN and postprocessing to obtain the detection result. The designed algorithm was implemented in the Python programming language using the TensorFlow library. Obtained results of validation of the network and the detection results are presented and discussed in the last chapter.
|
|
|
Medical image segmentation based on graph cut with shape prior
Kozlová, Dominika ; Jan, Jiří (referee) ; Jakubíček, Roman (advisor)
This thesis deals with a graph-based image segmentation and its improvement by using the information about the shape of the object for creating specific graph architecture (template). There are described basics of the graph theory, which is the basis of the graph segmentation methods. Designed segmentation algorithm was realized in 2D with graphical user interface in MATLAB. For segmentation of volume data, the method was extended into 3D. Implemented method was tested on simulated data and on real CT and MRI images of vertebra and brain. Obtained results were evaluated and compared with the original method without using the template.
|
guest ::
RSS feed.