Filters








26,510 Hits in 8.0 sec

Applying spatial distribution analysis techniques to classification of 3D medical images

Dragoljub Pokrajac, Vasileios Megalooikonomou, Aleksandar Lazarevic, Despina Kontos, Zoran Obradovic
2005 Artificial Intelligence in Medicine  
The later technique could still be a method of choice when the distributions differ significantly, since it is faster and less complex.  ...  Conclusion: Performed experiments demonstrated that the approaches based on the KL divergence and the ML method provide superior accuracy compared to the Mahalanobis distance.  ...  In addition, the authors express their gratitude to the anonymous reviewers whose comments significantly improved the structure and overall quality of the paper.  ... 
doi:10.1016/j.artmed.2004.07.001 pmid:15811790 fatcat:64ysxglcyrby7glgn4he5rhbcu

Subjective probability [chapter]

2008 Nonbayesian Decision Theory  
The later technique could still be a method of choice when the distributions differ significantly, since it is faster and less complex.  ...  Conclusion: Performed experiments demonstrated that the approaches based on the KL divergence and the ML method provide superior accuracy compared to the Mahalanobis distance.  ...  In addition, the authors express their gratitude to the anonymous reviewers whose comments significantly improved the structure and overall quality of the paper.  ... 
doi:10.1007/978-1-4020-8699-1_6 fatcat:wsmau6v4nndd5euqqzrovedkbi

Subjective Probability

R. L. GREGORY
1957 Nature  
The later technique could still be a method of choice when the distributions differ significantly, since it is faster and less complex.  ...  Conclusion: Performed experiments demonstrated that the approaches based on the KL divergence and the ML method provide superior accuracy compared to the Mahalanobis distance.  ...  In addition, the authors express their gratitude to the anonymous reviewers whose comments significantly improved the structure and overall quality of the paper.  ... 
doi:10.1038/180158a0 fatcat:m7uekfmtb5echej5wccoio4ide

An adaptive partitioning approach for mining discriminant regions in 3D image data

Vasileios Megalooikonomou, Despina Kontos, Dragoljub Pokrajac, Aleksandar Lazarevic, Zoran Obradovic
2007 Journal of Intelligent Information Systems  
Mining discriminative spatial patterns in image data is an emerging subject of interest in medical imaging, meteorology, engineering, biology, and other fields.  ...  In this paper, we propose a novel approach for detecting spatial regions that are highly discriminative among different classes of three dimensional (3D) image data.  ...  Acknowledgements The authors would like to thank A. Saykin for providing the fMRI dataset and clinical expertise.  ... 
doi:10.1007/s10844-007-0043-2 fatcat:w4t4zt5n75b3vjnvjf7urbcjui

Computationally Intelligent Methods for Mining 3D Medical Images [chapter]

Despina Kontos, Vasileios Megalooikonomou, Fillia Makedon
2004 Lecture Notes in Computer Science  
We present novel intelligent tools for mining 3D medical images.  ...  We apply quantitative characterization techniques to extract k-dimensional signatures from the highly discriminative ROIs. Finally, we use neural networks for classification.  ...  Acknowledgement The authors would like to thank A. Saykin for providing the fMRI data set and clinical expertise and J. Ford for performing some of the preprocessing of this data set.  ... 
doi:10.1007/978-3-540-24674-9_9 fatcat:f44lzhgo2bcflay4fg7rtc376u

Fast and effective characterization of 3D region of interest in medical image data

Despina Kontos, Vasileios Megalooikonomou, J. Michael Fitzpatrick, Milan Sonka
2004 Medical Imaging 2004: Image Processing  
A necessary step prior to classification is efficient extraction of discriminative features. For this purpose, we apply a characterization technique especially designed for spatial ROIs.  ...  The main idea of this technique is to extract a k-dimensional feature vector using concentric spheres in 3D (or circles in 2D) radiating out of the ROIís center of mass.  ...  ACKNOWLEDGEMENT The authors would like to thank A. Saykin for providing the fMRI data set and clinical expertise and J. Ford for performing some of the preprocessing of this data set.  ... 
doi:10.1117/12.534459 dblp:conf/miip/KontosM04 fatcat:vza5lcpyfvbh7ettulm6gsjuqi

A Multi-Volume Visualization Framework for Spatial Aligned Volumes after 3D/3D Image Registration

Hui Tang, Jean-Louis Dillenseger, Xu Dong Bao, Li Min Luo
2009 2009 First International Conference on Information Science and Engineering  
A new method for the visualization of spatial aligned volumes after 3D/3D image registration is presented in this paper.  ...  Then, a statistical vectorial volume classification method based on neighborhood weighted Gaussian mixture model is applied to analyze the vectorial volume and get material distribution information.  ...  Conclusions With the development of 3D/3D medical image registration methods, more and more application meets the requirement of the visualization of spatial-aligned volumes.  ... 
doi:10.1109/icise.2009.77 fatcat:fg3gkq76pbg7vlkqpuftd7vyea

Information Extraction Techniques in Hyperspectral Imaging Biomedical Applications [chapter]

Samuel Ortega, Martin Halicek, Himar Fabelo, Eduardo Quevedo, Baowei Fei, Gustavo Marrero Callico
2020 Multimedia Information Retrieval [Working Title]  
One of the most relevant challenges in medical HSI is the information extraction, where image processing methods are used to extract useful information for disease detection and diagnosis.  ...  Hyperspectral imaging (HSI) is a technology able to measure information about the spectral reflectance or transmission of light from the surface.  ...  Conflict of interest The authors declare that there are no conflicts of interest related to this chapter. © 2020 The Author(s). Licensee IntechOpen.  ... 
doi:10.5772/intechopen.93960 fatcat:beqkyox6mzhwpg62ncjj2je3ki

Fast and effective characterization for classification and similarity searches of 2D and 3D spatial region data

Despina Kontos, Vasileios Megalooikonomou
2005 Pattern Recognition  
Similarity searches on artificial data demonstrate that our technique, although straightforward, compares favorably to mathematical morphology, while being two orders of magnitude faster.  ...  The method efficiently constructs a kdimensional feature vector using concentric spheres in 3D (circles in 2D) radiating out of a region's center of mass.  ...  Acknowledgements The authors would like to thank A. Saykin for providing the fMRI data set and clinical expertise, J. Ford for performing part of the preprocessing of this dataset, and H.  ... 
doi:10.1016/j.patcog.2005.04.020 pmid:16565747 pmcid:PMC1413499 fatcat:7fvqdlad6vh6zngrqg2rt2hide

3D Medical Volume Segmentation Using Hybrid Multiresolution Statistical Approaches

Shadi AlZu'bi, Abbes Amira
2010 Advances in Artificial Intelligence  
Multiresolution Analysis (MRA) enables the preservation of an image according to certain levels of resolution or blurring.  ...  This paper focuses on the implementation of efficient medical volume segmentation techniques.  ...  Many feature selection techniques have been tested in medical images, and the best results were achieved using the grey-scale values of the medical image pixels to generate the probability distribution  ... 
doi:10.1155/2010/520427 fatcat:y47agikf3nasvck2rgvuggn66q

Extraction of Discriminative Functional MRI Activation Patterns and an Application to Alzheimer's Disease [chapter]

Despina Kontos, Vasileios Megalooikonomou, Dragoljub Pokrajac, Alexandar Lazarevic, Zoran Obradovic, Orest B. Boyko, James Ford, Filia Makedon, Andrew J. Saykin
2004 Lecture Notes in Computer Science  
The goal is to efficiently identify spatial regions that are associated with non-spatial variables through adaptive recursive partitioning of the 3D space into a number of hyperrectangles utilizing statistical  ...  Given: Oct-tree T corresponding to the spatial domain D; Two sets S Y = {S 1,Y ,...S n1,Y }, S N = {S 1,N ,...S n2,N } containing region data for samples belonging to classes Y and N respectively.  ...  Some initial attempts to apply the technique on brain images have been reported in [10] .  ... 
doi:10.1007/978-3-540-30136-3_89 fatcat:ifptjikrkbdoba44xxpimjbahq

Intelligent Techniques in Medical Volume Visualization

Yassmin Abdallah, Abdelaziz Abdelhamid, Taha Elarif, Abdel-Badeeh M. Salem
2015 Procedia Computer Science  
The past few decades have witnessed an increasing number of new techniques being developed for practical clinical image display.  ...  This paper presents the recent intelligent techniques and algorithms used for medical data visualization. These techniques cover filtering, segmentation, classification and visualization.  ...  •Does not utilise spatial information. Medical Image Classification Techniques Mapping images into predefine classes is called image classification.  ... 
doi:10.1016/j.procs.2015.09.129 fatcat:4hmfq2jowffe5jxqzrfkhsnwm4

The Usage of Modern Data Science in Segmentation and Classification: Machine Learning and Microscopy

Matthew Andrew, Sreenivas Bhattiprolu, Daniel Butnaru, Joaquin Correa
2017 Microscopy and Microanalysis  
While these technologies have transformed many areas of data science ranging from medical diagnosis to stock market analysis, frequently image analysis for microscopy (outside some specific areas of application  ...  These higher dimensional spaces may be (spatially and / or temporally correlated) images acquired in different imaging modalities (i.e. using different detectors, energies or techniques to extract different  ...  While these technologies have transformed many areas of data science ranging from medical diagnosis to stock market analysis, frequently image analysis for microscopy (outside some specific areas of application  ... 
doi:10.1017/s1431927617001465 fatcat:wyuggtewuvdulhcx2osx5dolbm

Applying 3D U-Net Architecture to the Task of Multi-Organ Segmentation in Computed Tomography

Pavlo Radiuk
2020 Applied Computer Systems  
AbstractThe achievement of high-precision segmentation in medical image analysis has been an active direction of research over the past decade.  ...  Convolutional architectures have been mostly applied to homogeneous medical datasets with separate organs.  ...  This technique, called "supervised learning", has enhanced biomedical and radiological visualisation [5] , and significantly refined leading-edge approaches in medical image analysis [6] .  ... 
doi:10.2478/acss-2020-0005 fatcat:e77qbkxn4ncw5pahmujzwrttma

A Survey on Deep Learning for Neuroimaging-Based Brain Disorder Analysis

Li Zhang, Mingliang Wang, Mingxia Liu, Daoqiang Zhang
2020 Frontiers in Neuroscience  
Deep learning has recently been used for the analysis of neuroimages, such as structural magnetic resonance imaging (MRI), functional MRI, and positron emission tomography (PET), and it has achieved significant  ...  We first provide a comprehensive overview of deep learning techniques and popular network architectures by introducing various types of deep neural networks and recent developments.  ...  The classification is one of the first tasks in which deep learning giving a major contribution to medical image analysis. This task aims to classify medical images into two or more classes.  ... 
doi:10.3389/fnins.2020.00779 pmid:33117114 pmcid:PMC7578242 fatcat:tzdcq3kyyrefvn7vxgdj5lnhju
« Previous Showing results 1 — 15 out of 26,510 results