MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

Parkinson's disease (PD) is a progressive neurodegenerative disorder caused mainly by lack of dopamine in the brain. Dopamine is a neurotransmitter involved in movement, motivation, memory, and other functions; its level is decreased in PD brain as a result of dopaminergic cell death. Dopamine loss in PD brain is a cause of motor deficiency and, possibly, a reason of the cognitive deficit observed in some PD patients. PD is mostly not recognized in its early stage because of a long latency between the first damage to dopaminergic cells and the onset of clinical symptoms. Therefore, it is very important to find reliable molecular biomarkers that can distinguish PD from other conditions, monitor its progression, or give an indication of a positive response to a therapeutic intervention. PD biomarkers can be subdivided into four main types: clinical, imaging, biochemical, and genetic. For a long time protein biomarkers, dopamine metabolites, amino acids, etc. in blood, serum, cerebrospinal liquid (CSF) were considered the most promising. Among the candidate biomarkers that have been tested, various forms of α-synuclein (α-syn), i.e., soluble, aggregated, post-translationally modified, etc. were considered potentially the most efficient. However, the encouraging recent results suggest that microRNA-based analysis may bring considerable progress, especially if it is combined with α-syn data. Another promising analysis is the advanced metabolite profiling of body fluids, called "metabolomics" which may uncover metabolic fingerprints specific for various stages of PD. Conventional pharmacological treatment of PD is based on the replacement of dopamine using dopamine precursors (levodopa, L-DOPA, L-3,4 dihydroxyphenylalanine), dopamine agonists (amantadine, apomorphine) and MAO-B inhibitors (selegiline, rasagiline), which can be used alone or in combination with each other. Potential risk factors include environmental toxins, drugs, pesticides, brain microtrauma, focal cerebrovascular damage, and genomic defects. This review covers molecules that might act as the biomarkers of PD. Then, PD risk factors (including genetics and non-genetic factors) and PD treatment options are discussed.

/pdf/parkinson-s-disease-biomarkers-treatment-and-risk-factors-4omj5b5bfk.pdf

Parkinson's Disease: Biomarkers, Treatment, and Risk Factors.

As a multi-factorial degenerative disease, Parkinson’s disease (PD) leads to tremor, gait rigidity, and hypokinesia, thus hampering normal living. As this disease is usually detected in the later stages when neurons have degenerated completely, cure is on hold, ultimately leading to death due to the lack of early diagnostic techniques. Thus, biomarkers are required to detect the disease in the early stages when prevention is possible. Various biomarkers providing early diagnosis of the disease include those of imaging, cerebrospinal fluid, oxidative stress, neuroprotection, and inflammation. Also, biomarkers, alone or in combination, are used in the diagnosis and evolution of PD. This review encompasses various biomarkers available for PD and discusses recent advances in their development.

Biomarkers for Parkinson’s Disease: Recent Advancement

Machine Learning Models and Algorithms for Big Data ClassificationMatConvNet Deep Learning and iOS Mobile App Design for Pattern Recognition: Emerging Research and OpportunitiesAdvances in Cybernetics, Cognition, and Machine Learning for Communication TechnologiesDATA MINING, BIG DATA ANALYTICS and DEEP LEARNING with MATLABSUPERVISED LEARNING TECHNIQUES. TIME SERIES FORECASTING. EXAMPLES WITH NEURAL NETWORKS AND MATLABPractical MATLAB Deep LearningMachine Learning With MatlabHet doelOns feilbare denkenMATLAB Deep LearningDeep Learning and Dynamic Neural Networks With MatlabA Practical Approach for Machine Learning and Deep Learning AlgorithmsApplied Biomedical Engineering Using Artificial Intelligence and Cognitive ModelsDeep Learning Neural NetworksDeep Learning for BeginnersUNSUPERVISED LEARNING TECHNIQUES: PATTERN RECOGNITION. EXAMPLES WITH MATLABNeural Networks with MATLABBIG DATA AND DEEP LEARNING. EXAMPLES WITH MATLABMachine Learning and Neural Networks. Examples with MATLABInnovative Data Communication Technologies and ApplicationDeep Learning with Matlab. Deep NetworksARTIFICIAL INTELLIGENCE with MATLAB. DEEP LEARNING ARCHITECTURESLarge Scale Machine Learning with PythonMachine Learning With Neural Networks Using MATLABKeras 2.x ProjectsComputational Methods for Deep LearningNeural Networks and Learning MachinesMATLAB Machine LearningDeep Learning Using MATLAB. Neural Network ApplicationsMachine Learning for Predictive AnalysisAdvancement of Machine Intelligence in Interactive Medical Image AnalysisMACHINE LEARNING with NEURAL NETWORKSMachine LearningPython Machine LearningNeural Networks with RDEEP LEARNING WITH MATLAB. NEURAL NETWORKS BY EXAMPLESPython Machine Learning CookbookDeep Learning with MATLABResearching of the Deep Neural Network for Amber Gemstone ClassificationAnywhere-Anytime Signals and Systems Laboratory

MATLAB Deep Learning With Machine Learning Neural Networks and Artificial Intelligence 1st ed Edition

Transcranial B-mode sonography (TCS) of brain parenchyma is being increasingly used as a diagnostic tool in movement disorders. Compared to other neuroimaging modalities such as magnetic resonance imaging (MRI) and computed tomography, TCS can be performed today with portable machines and has the advantages of noninvasiveness and high resistance to movement artifacts. In distinct brain disorders TCS detects abnormalities that cannot be visualized or can only be visualized with significant effort with other imaging methods. In the field of movement disorders, TCS has been established mainly as a tool for the early and differential diagnosis of Parkinson’s disease. The postoperative position control of deep brain stimulation electrodes, especially in the subthalamic nucleus, can reliably and safely be performed with TCS. The present update review summarizes the current methodological standards and defines quality criteria of adequate TCS imaging and assessment of diagnostically relevant deep brain structures such as substantia nigra, brainstem raphe, basal ganglia and ventricles. Finally, an overview is given on recent technological advances including TCS-MRI fusion imaging and upcoming technologies of digitized image analysis aiming at a more investigator-independent assessment of deep brain structures on TCS.

/pdf/transcranial-sonography-tcs-of-brain-parenchyma-in-movement-a5sficx03v.pdf

Transcranial Sonography (TCS) of Brain Parenchyma in Movement Disorders: Quality Standards, Diagnostic Applications and Novel Technologies

BACKGROUND AND PURPOSE: Increased echogenicity of the substantia nigra is a typical transcranial sonography finding in Parkinson disease. Experimental software for digital analysis of the echogenic substantia nigra area has been developed. The aim of this study was to compare the evaluation of substantia nigra echogenicity by using digital analysis with a manual measurement in patients with Parkinson disease and healthy volunteers. MATERIALS AND METHODS: One hundred thirteen healthy volunteers were enrolled in the derivation cohort, and 50 healthy volunteers and 30 patients with Parkinson disease, in the validation cohort. The substantia nigra was imaged from the right and left temporal bone window by using transcranial sonography. All subjects were examined twice by using different sonographic machines by an experienced sonographer. DICOM images of the substantia nigra were encoded; then, digital analysis and manual measurement of the substantia nigra were performed. The 90th percentile of the derivation cohort values was used as a cut-point for the evaluation of the hyperechogenic substantia nigra in the validation cohort. The Spearman coefficient was used for assessment of the correlation between both measurements. The Cohen κ coefficient was used for the assessment of the correlation between both measurements and Parkinson disease diagnosis. RESULTS: The Spearman coefficient between measurements by using different machines was 0.686 for digital analysis and 0.721 for manual measurement ( P P CONCLUSIONS: The present study showed comparable results when measuring the substantia nigra features conventionally and by using the developed software.

http://www.ajnr.org/content/ajnr/early/2014/07/24/ajnr.A4049.full.pdf

Transcranial Sonography of the Substantia Nigra: Digital Image Analysis

Aims. Recent studies report increased echogenicity of the substantia nigra (SN) in patients with Parkinson’s disease (PD) using transcranial sonography (TCS). However, the main limitation to TCS is its dependence on the sonographer’s experience. Experimental software for quantitative evaluation of the echogenic SN area was thus developed by us. The aim of this study was to test the reliability of the data using developed B-Mode Assist software in patients with parkinsonism and in healthy volunteers. Methods. The SN was imaged from the right temporal bone window in mesencephalic plane using TCS. DICOM images of SN were saved, converted into JPEG format, encoded and processed. Two observers performed 3 automatic evaluations of the SN area (measurements of SN area in each gray scale intensity inside the region of interest) by counting the standard deviation of all 6 measurements using developed software. The average value of all 3 measurements of each observer was used for computing Cohen’s kappa coefficient to determine inter-observer correlations. Cohen’s kappa coefficients as an intra-observer correlation for observer 1 and observer 2 were counted from the first 2 measurements of both observers. Results. In total, 92 images were evaluated using this software. The mean of the standard deviations was 3.87; Cohen’s kappa for intra-observer agreement of two observers were 0.947, and 0.943, resp.; Cohen’s kappa for inter-observers agreement was 0.880. The agreement between visual and automatic detection of SN pathology was in 97.8% images. The sensitivity, specificity, positive and negative predictive values of automatic measurement were 100, 96.2, 95.1, 100%, resp. Conclusions. The results show very reliable measurement of SN features using designed application with “almost perfect” inter-observer and intra-observer agreements.

/pdf/a-new-program-for-highly-reproducible-automatic-evaluation-clxy6zeara.pdf

A new program for highly reproducible automatic evaluation of the substantia nigra from transcranial sonographic images

This paper shows how to classify the medical ultrasound images by using artificial intelligence with experimental software with MATLAB. The main goal is a classification of ROI substantia nigra in midbrain. This classification of the images is useful to detection Parkinson's disease. This work is based on image processing and is realized with the help of artificial intelligence which has been experimentally simulated in MATLAB software environment. This method is well applicable with Neural Network Toolbox in MATLAB.

/pdf/ultrasound-medical-image-recognition-with-artificial-36aywh8ozw.pdf

Ultrasound medical image recognition with artificial intelligence for Parkinson's disease classification

This paper describes how to recognize substantia nigra (SN) area in ultrasound brain-stem images. The main goal is the classification of ROI SN in midbrain. The classification of images is useful to detection Parkinson's disease (PD), defects in SN. Work is based on image processing and is realized with the help of artificial neural networks and solve is realized with MATLAB, with Image Processing and Neural Network Toolboxes.

http://www.wseas.us/e-library/conferences/2011/Meloneras/ACELAE/ACELAE-23.pdf

The image recognition of brain-stem ultrasound images with using a neural network based on PCA

Purpose: Transcranial B-mode sonography (TCS) of brain parenchyma is increasingly used as a diagnostic tool for movement disorders. Accordingly, experimental B-Mode Assist software was developed to enable digitized analysis of the echogenicity of predefined brain regions. The aim of the study was to assess the reproducibility of digitized TCS image analysis of the insula. Materials and Methods: A total of 130 patients with an indication for neurosonological examination were screened for participation in the study. The insula was imaged from the right temporal bone window using Virtual Navigator and TCS-MRI (magnetic resonance imaging) fusion imaging. All subjects were examined three times by two experienced sonographers. Corresponding images of the insula in the axial thalamic plane were encoded and digitally analyzed. Interclass correlation coefficient (ICC) and Spearman’s rank correlation coefficient were used for the assessment of intra- and inter-reader as well as intra- and inter-investigator reliabilities. Results: TCS images of 114 patients were evaluated (21 patients with TIA, 53 patients with headache, 18 patients with essential tremor, 22 patients with neurodegerative disease). 16 patients were excluded from analysis due to insufficient bone window. The intra-reader, inter-reader, intra-investigator and inter-investigator ICCs/Spearman’s rank correlation coefficients were 0.995/0.993, 0.937/0.921, 0.969/0.961 and 0.875/0.858, resp. Conclusion: The present study demonstrates a high reliability to reproduce echogenicity values of the insula using digitized image analysis and TCS-MRI fusion images with almost perfect intra-reader, inter-reader, intra-investigator and inter-investigator agreement.

Jiri Blahuta

Papers

Transcranial Sonography of the Substantia Nigra: Digital Image Analysis

A new program for highly reproducible automatic evaluation of the substantia nigra from transcranial sonographic images

Ultrasound medical image recognition with artificial intelligence for Parkinson's disease classification

The image recognition of brain-stem ultrasound images with using a neural network based on PCA

Transcranial Sonography of the Insula: Digitized Image Analysis of Fusion Images with Magnetic Resonance.