“Improved Feature Extraction and Classification Techniques for Multispectral Brain Magnetic Resonance Images”

Magnetic Resonance Imaging (MRI) is a multi sequence medical imaging technique in which stacks of images are acquired with different tissue contrasts. Simultaneous observation and quantitative analysis of normal brain tissues and small abnormalities from these large numbers of different sequences is a great challenge in clinical applications. Multispectral MRI analysis can simplify the job considerably by combining unlimited number of available co-registered sequences in a single suite. However, poor performance of the multispectral system with conventional image classification and segmentation methods makes it inappropriate for clinical analysis. Recent works in multispectral brain MRI analysis attempted to resolve this issue by improved feature extraction approaches, such as transform based methods, fuzzy approaches, algebraic techniques and so forth. Transform based feature extraction methods like Independent Component Analysis (ICA) and its extensions have been effectively used in recent studies to improve the performance of multispectral brain MRI analysis. However, these global transforms were found to be inefficient and inconsistent in identifying less frequently occurred features like small lesions, from large amount of MR data. The present thesis focuses on the improvement in ICA based feature extraction techniques to enhance the performance of multispectral brain MRI analysis. Methods using spectral clustering and wavelet transforms are proposed to resolve the inefficiency of ICA in identifying small abnormalities, and problems due to ICA over-completeness. Effectiveness of the new methods in brain tissue classification and segmentation is confirmed by a detailed quantitative and qualitative analysis with synthetic and clinical, normal and abnormal, data. In comparison to conventional classification techniques, proposed algorithms provide better performance in classification of normal brain tissues and significant small abnormalities.

Development of Techniques for the Automatic Extraction and Grade Detection of Glioma Tumors from Conventional Brain Magnetic Resonant Images

Cerebral glioma is the most prevalent primary brain tumor, which are classified broadly into low and high grades according to the degree of malignancy. High grade gliomas are highly malignant which possess a poor prognosis, and the patients survive less than eighteen months after diagnosis. Low grade gliomas are slow growing, least malignant and has better response to therapy. To date, histological grading is used as the standard technique for diagnosis, treatment planning and survival prediction. The main objective of this thesis is to propose novel methods for automatic extraction of low and high grade glioma and other brain tissues, grade detection techniques for glioma using conventional magnetic resonance imaging (MRI) modalities and 3D modelling of glioma from segmented tumor slices in order to assess the growth rate of tumors. Two new methods are developed for extracting tumor regions, of which the second method, named as Adaptive Gray level Algebraic set Segmentation Algorithm (AGASA) can also extract white matter and grey matter from T1 FLAIR an T2 weighted images. The methods were validated with manual Ground truth images, which showed promising results. The developed methods were compared with widely used Fuzzy c-means clustering technique and the robustness of the algorithm with respect to noise is also checked for different noise levels. Image texture can provide significant information on the (ab)normality of tissue, and this thesis expands this idea to tumour texture grading and detection. Based on the thresholds of discriminant first order and gray level cooccurrence matrix based second order statistical features three feature sets were formulated and a decision system was developed for grade detection of glioma from conventional T2 weighted MRI modality.The quantitative performance analysis using ROC curve showed 99.03% accuracy for distinguishing between advanced (aggressive) and early stage (non-aggressive) malignant glioma. The developed brain texture analysis techniques can improve the physician’s ability to detect and analyse pathologies leading to a more reliable diagnosis and treatment of disease. The segmented tumors were also used for volumetric modelling of tumors which can provide an idea of the growth rate of tumor; this can be used for assessing response to therapy and patient prognosis.

Level Identification of Brain MR Images using Histogram of a LBP variant

Axial brain slices containing similar anatomical structures are retrieved using features derived from the histogram of Local binary pattern (LBP). A rotation invariant description of texture in terms of texture patterns and their strength is obtained with the incorporation of local variance to the LBP, called Modified LBP (MOD-LBP). In this paper, we compare Histogram based Features of LBP (HF/LBP), against Histogram based Features of MOD-LBP (HF/MOD-LBP) in retrieving similar axial brain images. We show that replacing local histogram with a local distance transform based similarity metric further improves the performance of MOD-LBP based image retrieval

Spectral clustering independent component analysis for tissue classification from brain MRI

A spectral angle based feature extraction method, Spectral Clustering Independent Component Analysis (SC-ICA), is proposed in this work to improve the brain tissue classification from Magnetic Resonance Images (MRI). SC-ICA provides equal priority to global and local features; thereby it tries to resolve the inefficiency of conventional approaches in abnormal tissue extraction. First, input multispectral MRI is divided into different clusters by a spectral distance based clustering. Then, Independent Component Analysis (ICA) is applied on the clustered data, in conjunction with Support Vector Machines (SVM) for brain tissue analysis. Normal and abnormal datasets, consisting of real and synthetic T1-weighted, T2-weighted and proton density/fluid-attenuated inversion recovery images, were used to evaluate the performance of the new method. Comparative analysis with ICA based SVM and other conventional classifiers established the stability and efficiency of SC-ICA based classification, especially in reproduction of small abnormalities. Clinical abnormal case analysis demonstrated it through the highest Tanimoto Index/accuracy values, 0.75/98.8%, observed against ICA based SVM results, 0.17/96.1%, for reproduced lesions. Experimental results recommend the proposed method as a promising approach in clinical and pathological studies of brain diseases

Texture Description of low grade and high grade Glioma using Statistical features in Brain MRIs

Low grade and High grade Gliomas are tumors that originate in the glial cells. The main challenge in brain tumor diagnosis is whether a tumor is benign or malignant, primary or metastatic and low or high grade. Based on the patient's MRI, a radiologist could not differentiate whether it is a low grade Glioma or a high grade Glioma. Because both of these are almost visually similar, autopsy confirms the diagnosis of low grade with high-grade and infiltrative features. In this paper, textural description of Grade I and grade III Glioma are extracted using First order statistics and Gray Level Co-occurance Matrix Method (GLCM). Textural features are extracted from 16X16 sub image of the segmented Region of Interest(ROI) .In the proposed method, first order statistical features such as contrast, Intensity , Entropy, Kurtosis and spectral energy and GLCM features extracted were showed promising results. The ranges of these first order statistics and GLCM based features extracted are highly discriminant between grade I and Grade III. In this study which gives statistical textural information of grade I and grade III Glioma which is very useful for further classification and analysis and thus assisting Radiologist in greater extent.

How are Three-Deminsional Objects Represented in the Brain?

We discuss a variety of object recognition experiments in which human subjects were presented with realistically rendered images of computer-generated three-dimensional objects, with tight control over stimulus shape, surface properties, illumination, and viewpoint, as well as subjects' prior exposure to the stimulus objects. In all experiments recognition performance was: (1) consistently viewpoint dependent; (2) only partially aided by binocular stereo and other depth information, (3) specific to viewpoints that were familiar; (4) systematically disrupted by rotation in depth more than by deforming the two-dimensional images of the stimuli. These results are consistent with recently advanced computational theories of recognition based on view interpolation.

Brain Tumour, Mood Disorder and Encephalopathy. Discusion of the Clinical Case Presented in Volume 6, Number 2

We report a case of a 65 years old female patient, who was admitted to the hospital with non specific neurological symptoms and who had preliminary imagenological findings of an extra-axial tumor mass (a meningioma of the sphenoid’s wing), which was taken to complete surgical removal. Afterwards, she developed progressive neurologic deterioration until her death. The final diagnosis was acute spongiform encephalophaty, and was obtained by cerebral biopsy. Spongiform encephalopathy was described, almost a century ago, as the Creutzfeldt-Jakob Disease, poorly diagnosed in our environment because of its low frequency and uncommon onset, which starts with a mood disorder followed by a phase of dementia and a final fatal outcome. The gold standard for the diagnosis is based on a biopsy or an autopsy of the brain, with immunohistochemical stains for the prionic abnormal protein.

Brain Tumour, Mood Disorder and Encephalopathy. Discusion of the Clinical Case Presented in Volume 6, Number 2

We report a case of a 65 years old female patient, who was admitted to the hospital with non specific neurological symptoms and who had preliminary imagenological findings of an extra-axial tumor mass (a meningioma of the sphenoid’s wing), which was taken to complete surgical removal. Afterwards, she developed progressive neurologic deterioration until her death. The final diagnosis was acute spongiform encephalophaty, and was obtained by cerebral biopsy. Spongiform encephalopathy was described, almost a century ago, as the Creutzfeldt-Jakob Disease, poorly diagnosed in our environment because of its low frequency and uncommon onset, which starts with a mood disorder followed by a phase of dementia and a final fatal outcome. The gold standard for the diagnosis is based on a biopsy or an autopsy of the brain, with immunohistochemical stains for the prionic abnormal protein.

A "Trojan horse" strategy to reverse drug-resistance in brain tumors

Los gliomas malignos representan una de las formas más agresivas de los tumores del sistema nervioso central (SNC). De acuerdo con la clasificación de los tumores cerebrales de la Organización Mundial de la Salud (OMS), los astrocitomas han sido categorizados en cuatro grados, determinados por la patología subyacente. Es así como los gliomas malignos (o de alto grado) incluyen el glioma anaplásico (grado III) así como el glioblastoma multiforme (GBM, grado IV),estos últimos los más agresivos con el peor pronóstico (1). El manejo terapéutico de los tumores del SNC se basa en la cirugía, la radioterapia y la quimioterapia, dependiendo de las características del tumor, el estadio clínico y la edad (2),(3), sin embargo ninguno de los tratamientos estándar es completamente seguro y compatible con una calidad de vida aceptable (3), (4). En general, la quimioterapia es la primera opción en los tumores diseminados, como el glioblastoma invasivo y el meduloblastoma de alto riesgo o con metástasis múltiple, pero el pronóstico en estos pacientes es muy pobre (2),(3). Solamente nuevas terapias dirigidas (2) como las terapias anti-angiogénicas (4); o terapias génicas muestran un beneficio real en grupos limitados de pacientes con defectos moleculares específicos conocidos (4). De este modo, se hace necesario el desarrollo de nuevas terapias farmacológicas para atacar los tumores cerebrales. Frente a las terapias los gliomas malignos son con frecuencia quimioresistentes, y esta resistencia parece depender de al menos dos mecanismos: en primer lugar, la pobre penetración de muchas drogas anticáncer a través de la barrera hematoencefálica (BBB: Blood Brain Barrier), la barrera del fluido sangre-cerebroespinal (BCSFB: Blood-cerebrospinal fluid barrier) y la barrera sangre-tumor (BTB: blood-tumor barrier). Dicha resistencia se debe a la interacción de la droga con varios transportadores o bombas de eflujo de droga ABC (ABC: ATP-binding cassette) que se sobre expresan en las células endoteliales o epiteliales de estas barreras. En segundo lugar, estos transportadores de eflujo de drogas ABC propios de las células tumorales confieren un fenotipo conocido como resistencia a multidrogas (MDR: multidrug resistance), el cual es característico de varios tumores sólidos. Este fenotipo también está presente en los tumores del SNC y su papel en gliomas es objeto de investigación (5). Por consiguiente el suministro de medicamentos a través de la BBB es uno de los problemas vitales en los tratamientos de terapia dirigida. Estudios recientes han demostrado que algunas moléculas pequeñas utilizadas en estas terapias son sustratos de la glicoproteína P (Pgp: P-gycoprotein), así como también de otras bombas de eflujo como las proteínas relacionadas con la resistencia a multidrogas (MRPs: multidrug resistance-related proteins (MRPs) o la proteína relacionada con cáncer de seno (BCRP: breast-cancer resistance related protein)) que no permiten que las drogas de este tipo alcancen el tumor (1). Un sustrato de Pgp y BCRP es la DOXOrubicina (DOXO), un fármaco utilizado en la terapia anti cáncer, el cual es muy eficaz para atacar las células del tumor cerebral in vitro, pero con un uso clínico limitado por la poca entrega a través de la barrera hematoencefálica (BBB) y por la resistencia propia de los tumores. Por otra parte las células de BBB y las células del tumor cerebral tienen también proteínas superficiales, como el receptor de la lipoproteína de baja densidad (LDLR), que podría utilizarse como blanco terapéutico en BBB y tumores cerebrales. Es asi como la importancia de este estudio se basa en la generación de estrategias terapéuticas que promuevan el paso de las drogas a través de la barrera hematoencefalica y tumoral, y a su vez, se reconozcan mecanismos celulares que induzcan el incremento en la expresión de los transportadores ABC, de manera que puedan ser utilizados como blancos terapéuticos.Este estudio demostró que el uso de una nueva estrategia basada en el “Caballo de Troya”, donde se combina la droga DOXOrubicina, la cual es introducida dentro de un liposoma, salvaguarda la droga de manera que se evita su reconocimiento por parte de los transportadores ABC tanto de la BBB como de las células del tumor. La construcción del liposoma permitió utilizar el receptor LDLR de las células asegurando la entrada a través de la BBB y hacia las células tumorales a través de un proceso de endocitosis. Este mecanismo fue asociado al uso de estatinas o drogas anticolesterol las cuales favorecieron la expresión de LDLR y disminuyeron la actividad de los transportadores ABC por nitración de los mismos, incrementando la eficiencia de nuestro Caballo de Troya. Por consiguiente demostramos que el uso de una nueva estrategia o formulación denominada ApolipoDOXO más el uso de estatinas favorece la administración de fármacos a través de la BBB, venciendo la resistencia del tumor y reduciendo los efectos colaterales dosis dependiente de la DOXOrubicina. Además esta estrategia del "Caballo de Troya", es un nuevo enfoque terapéutico que puede ser considerado como una nueva estrategia para aumentar la eficacia de diferentes fármacos en varios tumores cerebrales y garantiza una alta eficiencia incluso en un medio hipóxico,característico de las células cancerosas, donde la expresión del transportador Pgp se vió aumentada. Teniendo en cuenta la relación entre algunas vías de señalización reconocidas como moduladores de la actividad de Pgp, este estudio presenta no solo la estrategia del Caballo de Troya, sino también otra propuesta terapéutica relacionada con el uso de Temozolomide más DOXOrubicina. Esta estrategia demostró que el temozolomide logra penetrar la BBB por que interviene en la via de señalización de la Wnt/GSK3/β-catenina, la cual modula la expresión del transportador Pgp. Se demostró que el TMZ disminuye la proteína y el mRNA de Wnt3 permitiendo plantear la hipótesis de que la droga al disminuir la transcripción del gen Wnt3 en células de BBB, incrementa la activación de la vía fosforilando la β-catenina y conduciendo a disminuir la β-catenina nuclear y por tanto su unión al promotor del gen mdr1. Con base en los resultados este estudio permitió el reconocimiento de tres mecanismos básicos relacionados con la expresión de los transportadores ABC y asociados a las estrategias empleadas: el primero fue el uso de las estatinas, el cual condujo a la nitración de los transportadores disminuyendo su actividad por la via del factor de transcripción NFκB; el segundo a partir del uso del temozolomide, el cual metila el gen de Wnt3 reduciendo la actividad de la via de señalización de la la β-catenina, disminuyendo la expresión del transportador Pgp. El tercero consistió en la determinación de la relación entre el eje RhoA/RhoA quinasa como un modulador de la via (no canónica) GSK3/β-catenina. Se demostró que la proteína quinasa RhoA promovió la activación de la proteína PTB1, la cual al fosforilar a GSK3 indujo la fosforilación de la β-catenina, lo cual dio lugar a su destrucción por el proteosoma, evitando su unión al promotor del gen mdr1 y por tanto reduciendo su expresión. En conclusión las estrategias propuestas en este trabajo incrementaron la citotoxicidad de las células tumorales al aumentar la permeabilidad no solo de la barrera hematoencefálica, sino también de la propia barrera tumoral. Igualmente, la estrategia del “Caballo de Troya” podría ser útil para la terapia de otras enfermedades asociadas al sistema nervioso central. Por otra parte estos estudios indican que el reconocimiento de mecanismos asociados a la expresión de los transportadores ABC podría constituir una herramienta clave en el desarrollo de nuevas terapias anticáncer.

A Monte Carlo-Based Fiber Tracking Algorithm using Diffusion Tensor MRI

Diffusion tensor magnetic resonance imaging, which measures directional information of water diffusion in the brain, has emerged as a powerful tool for human brain studies. In this paper, we introduce a new Monte Carlo-based fiber tracking approach to estimate brain connectivity. One of the main characteristics of this approach is that all parameters of the algorithm are automatically determined at each point using the entropy of the eigenvalues of the diffusion tensor. Experimental results show the good performance of the proposed approach

Time-based prospective memory in children with autism spectrum disorder

In this study, for the first time, prospective memory was investigated in 11 school-aged children with autism spectrum disorders and 11 matched neurotypical controls. A computerised time-based prospective memory task was embedded in a visuospatial working memory test and required participants to remember to respond to certain target times. Controls had significantly more correct prospective memory responses than the autism spectrum group. Moreover, controls checked the time more often and increased time-monitoring more steeply as the target times approached. These differences in time-checking may suggest that prospective memory in autism spectrum disorders is affected by reduced self-initiated processing as indicated by reduced task monitoring.

Toward construction of an inexpensive brain computer interface for goal oriented applications

The paper describes the implementation of an offline, low-cost Brain Computer Interface (BCI) alternative to more expensive commercial models. Using inexpensive general purpose clinical EEG acquisition hardware (Truscan32, Deymed Diagnostic) as the base unit, a synchronisation module was constructed to allow the EEG hardware to be operated precisely in time to allow for recording of automatically time stamped EEG signals. The synchronising module allows the EEG recordings to be aligned in stimulus time locked fashion for further processing by the classifier to establish the class of the stimulus, sample by sample. This allows for the acquisition of signals from the subject’s brain for the goal oriented BCI application based on the oddball paradigm. An appropriate graphical user interface (GUI) was constructed and implemented as the method to elicit the required responses (in this case Event Related Potentials or ERPs) from the subject.

Single-trial event-related potential analysis for brain-computer interfaces

Abstract. Different types of mental activity are utilised as an input in Brain-Computer Interface (BCI) systems. One such activity type is based on Event-Related Potentials (ERPs). The characteristics of ERPs are not visible in single-trials, thus averaging over a number of trials is necessary before the signals become usable. An improvement in ERP-based BCI operation and system usability could be obtained if the use of single-trial ERP data was possible. The method of Independent Component Analysis (ICA) can be utilised to separate single-trial recordings of ERP data into components that correspond to ERP characteristics, background electroencephalogram (EEG) activity and other components with non- cerebral origin. Choice of specific components and their use to reconstruct “denoised” single-trial data could improve the signal quality, thus allowing the successful use of single-trial data without the need for averaging. This paper assesses single-trial ERP signals reconstructed using a selection of estimated components from the application of ICA on the raw ERP data. Signal improvement is measured using Contrast-To-Noise measures. It was found that such analysis improves the signal quality in all single-trials.

Eye tracking and gaze based interaction within immersive virtual environments

Our eyes are input sensors which Provide our brains with streams of visual data. They have evolved to be extremely efficient, and they will constantly dart to-and-fro to rapidly build up a picture of the salient entities in a viewed scene. These actions are almost subconscious. However, they can provide telling signs of how the brain is decoding the visuals and call indicate emotional responses, prior to the viewer becoming aware of them. In this paper we discuss a method of tracking a user's eye movements, and Use these to calculate their gaze within an immersive virtual environment. We investigate how these gaze patterns can be captured and used to identify viewed virtual objects, and discuss how this can be used as a, natural method of interacting with the Virtual Environment. We describe a flexible tool that has been developed to achieve this, and detail initial validating applications that prove the concept.

Prediction of Parkinson’s Disease tremor onset using a radial basis function neural network based on particle swarm optimization

Deep Brain Stimulation (DBS) has been successfully used throughout the world for the treatment of Parkinson's disease symptoms. To control abnormal spontaneous electrical activity in target brain areas DBS utilizes a continuous stimulation signal. This continuous power draw means that its implanted battery power source needs to be replaced every 18–24 months. To prolong the life span of the battery, a technique to accurately recognize and predict the onset of the Parkinson's disease tremors in human subjects and thus implement an on-demand stimulator is discussed here. The approach is to use a radial basis function neural network (RBFNN) based on particle swarm optimization (PSO) and principal component analysis (PCA) with Local Field Potential (LFP) data recorded via the stimulation electrodes to predict activity related to tremor onset. To test this approach, LFPs from the subthalamic nucleus (STN) obtained through deep brain electrodes implanted in a Parkinson patient are used to train the network. To validate the network's performance, electromyographic (EMG) signals from the patient's forearm are recorded in parallel with the LFPs to accurately determine occurrences of tremor, and these are compared to the performance of the network. It has been found that detection accuracies of up to 89% are possible. Performance comparisons have also been made between a conventional RBFNN and an RBFNN based on PSO which show a marginal decrease in performance but with notable reduction in computational overhead.