Posted on

Explainable 3D convolutional neural network using GMM encoding

Abstract:     The aim of this paper is to propose a novel method to explain, interpret, and support the decision-making process of deep Convolutional Neural Network (CNN). This is achieved by analyzing neuron activations of trained 3D-CNN on selected layers via Gaussian Mixture Model (GMM)   …  more

 

Posted on

Segmentation of anatomical organs in medical data – Master Thesis : Bc. Martin Tamajka

Download: Master Thesis-  Martin Tamajka: Segmentation of anatomical organs in medical data

Annotation:

2016, May
Medical image segmentation is an important part of medical practice. Primarily as far as radiologists are concerned it simplifies their everyday tasks and allows them to use their time more effective, because in most cases radiologists only have a certain amount of time they can spend examining patient’s data. Computer aided diagnosis is also a powerful instrument in elimination of possible human failure.
In this work, we propose a novel approach to human organs segmentation. We primarily concentrate on segmentation of human brain from MR volume. Our method is based on oversegmenting 3D volume to supervoxels using SLIC algorithm. Individual supervoxels are described by features based on intensity distribution of contained voxels and on position within the brain. Supervoxels are classified by neural networks which are trained to classify supervoxels to individual tissues. In order to give our method additional precision, we use information about the shape and inner structure of the organ. In general we propose a 6-step segmentation method based on classification.
We compared our results with those of state-of-the-art methods and we can conclude that the results are clearly comparable.
Apart from the global focus of this thesis, our goal is to apply engineering skills and best practices to implement proposed method and necessary tools in such a way that they can be easily extended and maintained in the future.

Posted on

Automatic brain segmentation method based on supervoxels

Martin Tamajka, Wanda Benesova

Abstract:

In this work, we present a fully automatic brain segmentation method based on supervoxels (ABSOS). We propose novel features used for classification, that are based on distance and angle in different planes between supervoxel and brain center. These novel features are combined with other prominent features. The presented method is based on machine learning and incorporates also a skull stripping (cranium removing) in the preprocessing step. Neural network – multilayer perceptron (MLP) was trained for the classification process. In this paper we also present thorough analysis, which supports choice of rather small supervoxels, preferring homogeneity over compactness, and value of intensity threshold parameter used in preprocessing for skull stripping. In order to decrease computational complexity and increase segmentation performance we incorporate prior knowledge of typical background intensities acquired in analysis of subjects.

Published in:

2016 International Conference on Systems, Signals and Image Processing (IWSSIP)

Date of Conference:

23-25 May 2016

 

Posted on

Segmentation of Brain Tumors from MRI using Adaptive Thresholding and Graph Cut Algorithm

Development of methods for automatic brain tumor segmentation remains one of the most challenging tasks in processing of medical data. Exact segmentation could improve the diagnostics, as for example the time evaluation of the tumor volume. However, manual segmentation in magnetic resonance data is a time-consuming task. We present a method of automatic tumor segmentation in magnetic resonance images which consists of several steps. In the first step high intense cranium is removed. In the next step parameters of the image are derived using the method “Mixture of Gaussians”. These parameters control the morphological reconstruction (proposed by Luc Vincent 1993). The morphological reconstruction produces binary mask which is used in the last step of the segmentation: graph cut segmentation. First results of this method are presented in this paper.

Source code