Ionel-Bujorel Pavaloiu

3D dental reconstruction from CBCT data

We will present in this paper a method for the reconstruction of the oral 3D structure using Computed Tomography (CT) sections obtained from Cone Beam Computed Tomography (CBCT). A high-quality visualization of the dental tissues, based nowadays on fine 3D reconstruction, is essential for accurate diagnosis and treatments. Dental CBCT images present several major problems because of the noisiness and of the configuration of the system. We tried several algorithms in order to overcome these issues and to obtain a feasible and efficient method that can be used directly in the clinical procedures. Our approach includes novel procedures like the delimitation of the region of interest and the combination of registration and segmentation steps, which grant faster results and open the route to better representations.

Knowledge Based Segmentation for Fast 3D Dental Reconstruction from CBCT

We present in this paper a fast method for the reconstruction of the dental 3D structure using the images obtained from Cone Beam Computed Tomography (CBCT). A high-quality visualization of the dental tissues, including 3D reconstruction, is essential for the accurate diagnosis and treatment in dentistry. The segmentation for the dental CBCT images presents several major problems because of the noisiness of the images. We analyze the existing methods and propose one that uses the information for the dental structure and distribution to reduce the computational load and to provide good results in an automatic procedure.

Automatic segmentation for 3D dental reconstruction

Cone Beam Computed Tomography (CBCT) is one of the favorite imaging technologies in dentistry because if offers 3D images in conditions of reduced irradiation. High quality 3D imaging is essential for first-rate diagnostic and treatment, despite the rather low quality images, with low contrast and high noise. The paper presents an automatic method for 3D reconstruction of the oral cavity. We analyze the existing state of the art in the field and propose a segmentation method that uses the domain knowledge related to mouth and teeth to reduce the computational load and to provide good results in an automatic procedure. The method is based on a Canny type edge detector, that was found to offer better control than active contour methods.

Topic classification in Romanian blogosphere

In this paper we analyze the performance of several methods for classification applied to the Romanian blogosphere. Blogs are difficult to categorize by humans and machines alike, because they are written in a changeable style. In the early days of web, directories maintained by humans could not keep up millions the websites; likewise, blog directories cannot keep up with the explosive growth of the blogsphere. This paper investigates the efficacy of using machine learning to categorize blogs written in Romanian language belonging to the Romanian blogosphere. We design a text classification experiment to categorize Romanian blogs into nine topics. The baseline feature is unigrams weighed by TF-IDF. We analyze the corpus, features, and the result data.

Error minimization in Phase-Based Neurons

Complex-Valued Neural Networks are extensions of the classical Neural Networks. They have complex-valued weights, accept complex inputs and have more computational power than the classical ones. We discuss in this paper the training for Phase-Based Neurons, neural processing elements similar to Universal Binary Neurons, that uses as weights and bias complex numbers with unit magnitude, the phase being the only tunable parameter.

Teeth labeling from CBCT data using the Circular Hough Transform

In this paper, we explore the possibilities to detect and label straightforward the teeth in Cone Beam Computed Tomography images, without performing complex segmentation procedures on teeth. We are using the Circular Hough Transform (CHT) to find the teeth positions, segmentation using intensity level to determine the mandible and deformable templates to find the best fit position for the teeth on the mandible. The dental arch is split into 16 regions and the teeth are labeled by their position in a given region.

Improved GROMACS algorithms using the MPI parallelization

Molecular dynamics (MD) studies the structure of molecular systems which are subject to certain constraints and forces. The simulation of particles is a tool for examining atomic systems during a period of nanoseconds in which the trajectory of atoms and the state of the system is analyzed. GROMACS is a package which supports molecular dynamics simulations and energy minimization, being started the University of Groningen. Usually molecular dynamics simulations are time consuming, sometimes taking weeks and even months. In order to obtain the output of the simulation in less time, parallelization is used through the use of MPI (Message Passing Interface). The article presents the MPI parallelization of a novel thermostat algorithm for molecular dynamics and experimental results.

Neural network based edge detection for CBCT segmentation

Edge detection is an important task in image processing, many times as part of the segmentation process. When segmentation is performed in medical imaging, one of the preferred tools is neural networks, because of their capabilities of adaptive learning and non-linear mapping. We present in this paper the neural network tools used for edge detection and we propose one that is able to perform edge detection in dental Cone Beam Computer Tomography (CBCT) images, a necessary step for the teeth 3D reconstruction.

Automatic contour detection from dental CBCT DICOM data

The algorithm described in this paper is part of a program supporting the process of teeth contour detection, segmentation and 3D reconstruction. The data is taken from dental conical tomographies. Automatic contour detection starts by filtering the image according to an adaptive threshold. The region of interest is established and the tooth contour is determined using the possible edge directions. The applied method is innovative for the contour detection, because it exploits the domain knowledge, where each tooth (incisor, canine, premolar, molar) has a certain shape. For touching teeth, the delimitation is automatically performed by drawing a line using the Bresenham algorithm. The algorithm will further contribute to the determination and treatment of teeth pathologies.

Feedforward multilayer phase-based neural networks

Complex-Valued Neural Networks (CVNNs) are Artificial Neural Networks (ANNs) which function using complex numbers - they have complex-valued parameters and accept complex-valued inputs. Phase-Based Neurons (PBNs) are simple CVNNs that use for the internal weights complex numbers with the modulus 1, the only adaptable parameters being the phases of the weights. We present in this paper some limitations of the Continuous Phase-Based Neuron (CPBN) and describe the structure of a Feedforward Multilayer Phase-Based Neural Network (MLPBN) and its training using an adaptation of the backpropagation algorithm.