Search results for "ALGORITHMS"
showing 10 items of 1716 documents
A smart and operator independent system to delineate tumours in Positron Emission Tomography scans
2018
Abstract Positron Emission Tomography (PET) imaging has an enormous potential to improve radiation therapy treatment planning offering complementary functional information with respect to other anatomical imaging approaches. The aim of this study is to develop an operator independent, reliable, and clinically feasible system for biological tumour volume delineation from PET images. Under this design hypothesis, we combine several known approaches in an original way to deploy a system with a high level of automation. The proposed system automatically identifies the optimal region of interest around the tumour and performs a slice-by-slice marching local active contour segmentation. It automa…
Driver mutations and differential sensitivity to targeted therapies: a new approach to the treatment of lung adenocarcinoma
2010
The adenocarcinoma of the lung has recently shown peculiar molecular characteristics, which relate with both carcinogenesis and response to targeted drugs. Several molecular alterations have been defined as "driver mutations". These are responsible for both the initiation and maintenance of the malignancy. The epidermal growth factor receptor (EGFR) pathway is the main regulator of cell function and cancer development. It has a widely defined role in the occurrence of driver mutations. Up till now EGFR gene mutations, KRAS gene mutations and EML4-ALK fusion genes are the most widely recognized alterations involved in both the biology and the clinical management of lung adenocarcinoma. In th…
MULTI-SCALE ANALYSIS OF LUNG COMPUTED TOMOGRAPHY IMAGES
2007
A computer-aided detection (CAD) system for the identification of lung internal nodules in low-dose multi-detector helical Computed Tomography (CT) images was developed in the framework of the MAGIC-5 project. The three modules of our lung CAD system, a segmentation algorithm for lung internal region identification, a multi-scale dot-enhancement filter for nodule candidate selection and a multi-scale neural technique for false positive finding reduction, are described. The results obtained on a dataset of low-dose and thin-slice CT scans are shown in terms of free response receiver operating characteristic (FROC) curves and discussed.
Finite-time Lyapunov dimension and hidden attractor of the Rabinovich system
2015
The Rabinovich system, describing the process of interaction between waves in plasma, is considered. It is shown that the Rabinovich system can exhibit a {hidden attractor} in the case of multistability as well as a classical {self-excited attractor}. The hidden attractor in this system can be localized by analytical-numerical methods based on the {continuation} and {perpetual points}. For numerical study of the attractors' dimension the concept of {finite-time Lyapunov dimension} is developed. A conjecture on the Lyapunov dimension of self-excited attractors and the notion of {exact Lyapunov dimension} are discussed. A comparative survey on the computation of the finite-time Lyapunov expon…
Machine learning and ontology in eCoaching for personalized activity level monitoring and recommendation generation.
2022
AbstractLeading a sedentary lifestyle may cause numerous health problems. Therefore, passive lifestyle changes should be given priority to avoid severe long-term damage. Automatic health coaching system may help people manage a healthy lifestyle with continuous health state monitoring and personalized recommendation generation with machine learning (ML). This study proposes a semantic ontology model to annotate the ML-prediction outcomes and personal preferences to conceptualize personalized recommendation generation with a hybrid approach. We use a transfer learning approach to improve ML model training and its performance, and an incremental learning approach to handle daily growing data …
Proceedings - International Workshop on Computer Architecture for Machine Perception, CAMP
2005
This volume contains the proceedings of the 2005 IEEE International Workshop on Computer Architecture for Machine Perception. CAMP05 is the seventh in the series of workshops which began with CAMP91 in Paris and followed by CAMP93 in New Orleans, CAMP95 in Como, CAMP97 in Boston, CAMP00 in Padova, CAMP03 in New Orleans. The CAMP workshops represent a continuation of the very successful IEEE CAPAMI (Computer Architectures for Pattern Analysis and Machine Intelligence) workshops held during the 1970's and 1980's. Besides the traditional topics of highly parallel architectures, distributed computing, real time systems, VLSI architectures and image analysis algorithms, this edition of the works…
Particle Swarm Optimization as a New Measure of Machine Translation Efficiency
2018
The present work proposes a new approach to measuring efficiency of evolutionary algorithm-based Machine Translation. We implement some attributes of evolutionary algorithms performing cosine similarity objective function of a Particle Swarm Optimization (PSO) algorithm then, we evaluate an English text set for translation precision into the Spanish text as a simulated benchmark, and explore the backward process. Our results show that PSO algorithm can be used for translation of multiple language sentences with one identifier only, in other words the technology presented is language-pair independent. Specifically, we indicate that our cosine similarity objective function improves the veloci…
Coupled stochastic dynamics of magnetic moment and anisotropy axis of a magnetic nanoparticle
2012
An algorithm is developed for numerical simulation of coupled stochastic dynamics of magnetic moment and magnetic anisotropy axis of a nanoparticle. Time-correlation functions of the magnetic moment and its components longitudinal and transverse to the magnetic anisotropy axis are calculated by averaging along the stochastic trajectory. The longitudinal and transverse relaxation times are found by fitting the time correlation functions. Existing theoretical relations derived by the effective field approach in the limit of small fields are confirmed. The time-correlation functions of magnetic moments of nanoparticles in dependence on their properties are calculated numerically for arbitrary …
Effects of different cellulose derivatives on drug release mechanism studied at a preformulation stage
2003
As a matter of fact, in vitro dissolution is well known to be the method of choice for the pharmaceutical industry to develop effective medicines. However, many experiments must be performed all along a new product life and they represent an overcharge of work for researchers. The purpose of this paper was to assess the relevance of new parameters obtained during preformulation stage by Nuclear Magnetic Resonance (NMR) experiments to better understand drug release mechanism. This study was carried out with three cellulose derivatives currently used as carrier matrices (Microcrystalline cellulose (MCC), Hydroxypropylmethyl cellulose (HPMC) and Ethyl cellulose (EC)). Granules and tablets were…
A combined NMR, DFT, and X-ray investigation of some cinchona alkaloid O-ethers.
2008
Structures and conformational behavior of several cinchona alkaloid O-ethers in the solid state (X-ray), in solution (NMR and DFT), and in the gas phase (DFT) were investigated. In the crystal, O-phenylcinchonidine adopts the Open(3) conformation similar to cinchonidine, whereas the O-methyl ether derivatives of both cinchonidine and cinchonine are packed in the Closed(1) conformation. Dynamic equilibria in solutions of the alkaloids were revealed by combined experimental-theoretical spin simulation/iteration techniques for the first time. In the (1)H NMR spectra in CDCl3 and toluene-d8 at room temperature, Closed(1) conformation was observed for the O-silyl ethers as a separate set of sign…