Search results for "ComputingMethodologies_PATTERNRECOGNITION"
showing 10 items of 296 documents
Benchmarking Wilms’ tumor in multisequence MRI data: why does current clinical practice fail? Which popular segmentation algorithms perform well?
2019
Wilms' tumor is one of the most frequent malignant solid tumors in childhood. Accurate segmentation of tumor tissue is a key step during therapy and treatment planning. Since it is difficult to obtain a comprehensive set of tumor data of children, there is no benchmark so far allowing evaluation of the quality of human or computer-based segmentations. The contributions in our paper are threefold: (i) we present the first heterogeneous Wilms' tumor benchmark data set. It contains multisequence MRI data sets before and after chemotherapy, along with ground truth annotation, approximated based on the consensus of five human experts. (ii) We analyze human expert annotations and interrater varia…
Learning the relevant image features with multiple kernels
2009
This paper proposes to learn the relevant features of remote sensing images for automatic spatio-spectral classification with the automatic optimization of multiple kernels. The method consists of building dedicated kernels for different sets of bands, contextual or textural features. The optimal linear combination of kernels is optimized through gradient descent on the support vector machine (SVM) objective function. Since a na¨ive implementation is computationally demanding, we propose an efficient model selection procedure based on kernel alignment. The result is a weight — learned from the data — for each kernel where both relevant and meaningless image features emerge after training. E…
Generating Hyperspectral Skin Cancer Imagery using Generative Adversarial Neural Network
2020
In this study we develop a proof of concept of using generative adversarial neural networks in hyperspectral skin cancer imagery production. Generative adversarial neural network is a neural network, where two neural networks compete. The generator tries to produce data that is similar to the measured data, and the discriminator tries to correctly classify the data as fake or real. This is a reinforcement learning model, where both models get reinforcement based on their performance. In the training of the discriminator we use data measured from skin cancer patients. The aim for the study is to develop a generator for augmenting hyperspectral skin cancer imagery. peerReviewed
CHAIMELEON Project: Creation of a Pan-European Repository of Health Imaging Data for the Development of AI-Powered Cancer Management Tools
2022
[EN] The CHAIMELEON project aims to set up a pan-European repository of health imaging data, tools and methodologies, with the ambition to set a standard and provide resources for future AI experimentation for cancer management. The project is a 4 year long, EU-funded project tackling some of the most ambitious research in the fields of biomedical imaging, artificial intelligence and cancer treatment, addressing the four types of cancer that currently have the highest prevalence worldwide: lung, breast, prostate and colorectal. To allow this, clinical partners and external collaborators will populate the repository with multimodality (MR, CT, PET/CT) imaging and related clinical data. Subse…
Technical Briefing: Hands-On Session on the Development of Trustworthy AI Software
2021
Following various real-world incidents involving both purely digital and cyber-physical Artificial Intelligence (AI) systems, AI Ethics has become a prominent topic of discussion in both research and practice, accompanied by various calls for trustworthy AI systems. Failures are often costly, and many of them stem from issues that could have been avoided during development. For example, AI ethics issues, such as data privacy are currently highly topical. However, implementing AI ethics in practice remains a challenge for organizations. Various guidelines have been published to aid companies in doing so, but these have not seen widespread adoption and may feel impractical. In this technical …
Wet Chemical Synthesis and a Combined X-ray and Mössbauer Study of the Formation of FeSb2 Nanoparticles
2011
Understanding how solids form is a challenging task, and few strategies allow for elucidation of reaction pathways that are useful for designing the synthesis of solids. Here, we report a powerful solution-mediated approach for formation of nanocrystals of the thermoelectrically promising FeSb(2) that uses activated metal nanoparticles as precursors. The small particle size of the reactants ensures minimum diffusion paths, low activation barriers, and low reaction temperatures, thereby eliminating solid-solid diffusion as the rate-limiting step in conventional bulk-scale solid-state synthesis. A time- and temperature-dependent study of formation of nanoparticular FeSb(2) by X-ray powder dif…
Automatic target recognition using 3D passive sensing and imaging with independent component analysis
2009
We present an overview of a method using Independent Component Analysis (ICA) and 3D Integral Imaging (II) technique to recognize 3D objects at different orientations. This method has been successfully applied to the recognition and classification of 3D scenes.
Three-dimensional object-distortion-tolerant recognition for integral imaging using independent component analysis
2009
Independent component analysis (ICA) aims at extracting unknown components from multivariate data assuming that the underlying components are mutually independent. This technique has been successfully applied to the recognition and classification of objects. We present a method that combines the benefits of ICA and the ability of the integral imaging technique to obtain 3D information for the recognition of 3D objects with different orientations. Our recognition is also possible when the 3D objects are partially occluded by intermediate objects.
Gait Analysis Using Multiple Kinect Sensors
2014
A gait analysis technique to model user presences in an office scenario is presented in this chapter. In contrast with other approaches, we use unobtrusive sensors, i.e., an array of Kinect devices, to detect some features of interest. In particular, the position and the spatio-temporal evolution of some skeletal joints are used to define a set of gait features, which can be either static (e.g., person height) or dynamic (e.g., gait cycle duration). Data captured by multiple Kinects is merged to detect dynamic features in a longer walk sequence. The approach proposed here was been evaluated by using three classifiers (SVM, KNN, Naive Bayes) on different feature subsets.
Learning vector quantization with alternative distance criteria
2003
An adaptive algorithm for training of a nearest neighbour (NN) classifier is developed in this paper. This learning rule has some similarity to the well-known LVQ method, but uses the nearest centroid neighbourhood concept to estimate optimal locations of the codebook vectors. The aim of this approach is to improve the performance of the standard LVQ algorithms when using a very small codebook. The behaviour of the learning technique proposed here is experimentally compared to those of the plain k-NN decision rule and the LVQ algorithms.