David Cárdenas-Peña

Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge

Algorithms for computer-aided diagnosis of dementia based on structural MRI have demonstrated high performance in the literature, but are difficult to compare as different data sets and methodology were used for evaluation. In addition, it is unclear how the algorithms would perform on previously unseen data, and thus, how they would perform in clinical practice when there is no real opportunity to adapt the algorithm to the data at hand. To address these comparability, generalizability and clinical applicability issues, we organized a grand challenge that aimed to objectively compare algorithms based on a clinically representative multi-center data set. Using clinical practice as the starting point, the goal was to reproduce the clinical diagnosis. Therefore, we evaluated algorithms for multi-class classification of three diagnostic groups: patients with probable Alzheimers disease, patients with mild cognitive impairment and healthy controls. The diagnosis based on clinical criteria was used as reference standard, as it was the best available reference despite its known limitations. For evaluation, a previously unseen test set was used consisting of 354 T1-weighted MRI scans with the diagnoses blinded. Fifteen research teams participated with a total of 29 algorithms. The algorithms were trained on a small training set (n=30) and optionally on data from other sources (e.g., the Alzheimers Disease Neuroimaging Initiative, the Australian Imaging Biomarkers and Lifestyle flagship study of aging). The best performing algorithm yielded an accuracy of 63.0% and an area under the receiver-operating-characteristic curve (AUC) of 78.8%. In general, the best performances were achieved using feature extraction based on voxel-based morphometry or a combination of features that included volume, cortical thickness, shape and intensity. The challenge is open for new submissions via the web-based framework: http://caddementia.grand-challenge.org.

Evaluation of segmentation methods on head and neck CT: Auto‐segmentation challenge 2015

Purpose Automated delineation of structures and organs is a key step in medical imaging. However, due to the large number and diversity of structures and the large variety of segmentation algorithms, a consensus is lacking as to which automated segmentation method works best for certain applications. Segmentation challenges are a good approach for unbiased evaluation and comparison of segmentation algorithms. Methods In this work, we describe and present the results of the Head and Neck Auto‐Segmentation Challenge 2015, a satellite event at the Medical Image Computing and Computer Assisted Interventions (MICCAI) 2015 conference. Six teams participated in a challenge to segment nine structures in the head and neck region of CT images: brainstem, mandible, chiasm, bilateral optic nerves, bilateral parotid glands, and bilateral submandibular glands. Results This paper presents the quantitative results of this challenge using multiple established error metrics and a well‐defined ranking system. The strengths and weaknesses of the different auto‐segmentation approaches are analyzed and discussed. Conclusions The Head and Neck Auto‐Segmentation Challenge 2015 was a good opportunity to assess the current state‐of‐the‐art in segmentation of organs at risk for radiotherapy treatment. Participating teams had the possibility to compare their approaches to other methods under unbiased and standardized circumstances. The results demonstrate a clear tendency toward more general purpose and fewer structure‐specific segmentation algorithms.

Unsupervised Kernel Function Building Using Maximization of Information Potential Variability

We propose a kernel function estimation strategy to support machine learning tasks by analyzing the input samples using Renyi’s Information Metrics. Specifically, we aim to identify a Reproducing Kernel Hilbert Space spanning the most widely the information force among data points by the maximization of the information potential variability of Parzen-based pdf estimation. So, a Gaussian kernel bandwidth updating rule is obtained as a function of the forces induced by a given dataset. Our proposal is tested on synthetic and real-world datasets related to clustering and classification tasks. Obtained results show that presented approach allows to compute RKHS’s favoring data groups separability, attaining suitable learning performances in comparison with state of the art algorithms.

Local binary fitting energy solution by graph cuts for MRI segmentation

This paper proposes a new solution for local binary fitting energy minimization based on graph cuts for automatic brain structure segmentation on magnetic resonance images. The approach establishes an effective way to embed the energy formulation into a directed graph, such that the energy is minimized by maximizing the graph flow. Proposed and conventional solutions are compared by segmenting the well-known BrainWeb synthetic brain Magnetic Resonance Imaging database. Achieved results show an improvement on the computational cost (about 10 times shorter) while maintaining the segmentation accuracy (96%).

Selection of time-variant features for earthquake classification at the Nevado-del-Ruiz volcano

Seismic event recognition is an important task for hazard assessment, eruption prediction and risk mitigation, since it can be used to determine the state of a volcano. Usually, expert technicians read features extracted from the seismogram, such as, cepstral derived coefficients, energy centroids, instant frequency, instant envelop, among others. However, there are few studies about the selection of important features for classifying several types of seismic events, i.e., taking into account the temporal contribution of each considered feature. This paper presents a feature selection strategy based on a relevance measure of time-variant features for seismic event classification. In this research, features are selected as those with the maximal information preserved within the time analysis. Since features selection stage is performed by incremental training, a simple k-nearest neighbor classification rule is used to properly determine the dimension of the final feature set. The employed feature extraction and feature selection methodologies are tested on an isolated event recognition task. The database used to test the methodology is composed of the following classes: volcano-tectonic, long period earthquakes, tremors and hybrid events. Data was recorded at the seismic monitoring stations located at the Nevado-del-Ruiz volcano, Colombia. Using a classifier based on hidden Markov models, accomplished results exhibit a performance improvement from 78% to 88% using the proposed methodology in comparison to the state-of-the-art feature sets.

Centered Kernel Alignment Enhancing Neural Network Pretraining for MRI-Based Dementia Diagnosis

Dementia is a growing problem that affects elderly people worldwide. More accurate evaluation of dementia diagnosis can help during the medical examination. Several methods for computer-aided dementia diagnosis have been proposed using resonance imaging scans to discriminate between patients with Alzheimers disease (AD) or mild cognitive impairment (MCI) and healthy controls (NC). Nonetheless, the computer-aided diagnosis is especially challenging because of the heterogeneous and intermediate nature of MCI. We address the automated dementia diagnosis by introducing a novel supervised pretraining approach that takes advantage of the artificial neural network (ANN) for complex classification tasks. The proposal initializes an ANN based on linear projections to achieve more discriminating spaces. Such projections are estimated by maximizing the centered kernel alignment criterion that assesses the affinity between the resonance imaging data kernel matrix and the label target matrix. As a result, the performed linear embedding allows accounting for features that contribute the most to the MCI class discrimination. We compare the supervised pretraining approach to two unsupervised initialization methods (autoencoders and Principal Component Analysis) and against the best four performing classification methods of the 2014 CADDementia challenge. As a result, our proposal outperforms all the baselines (7% of classification accuracy and area under the receiver-operating-characteristic curve) at the time it reduces the class biasing.

A Kernel-Based Representation to Support 3D MRI Unsupervised Clustering

A new kernel-based image representation is proposed on this paper aiming to support clustering tasks on 3D magnetic resonances images. The approach establishes an effective way to encode inter-slice similarities, so that the main shape information is kept on a lower dimensional space. Additionally, a spectral clustering technique is employed to estimate a compact embedding space where natural groups are easily detectable. Proposed approach outperforms the conventional voxel-wise sum of squared differences on clustering the gender category. Additionally, a pair of eigenvectors describing accurately the subject age is found.

Supervised kernel approach for automated learning using General Stochastic Networks

Abstract Generative Stochastic Networks (GSN) for supervised tasks generalize the denoising autoencoders by fixing the deepest layer to the output variables (e.g. class) and estimate the input–output joint distribution as the stationary transition operator of a Markov chain. Because of multi-layer network architectures with stochastic neurons, GSN performance depends on the selected architecture and network training. Aiming to improve such a performance, we introduce a supervised kernel-based learning within a GSN framework. Firstly, the considered network model induces a temporal model working as a data filtering that extracts refined data representations. Then, we use the conventional exhaustive search strategy to fix the hidden layer size. Lastly, we propose a novel supervised layer-wise pre-training that initializes the fine tuning stage of the GSN with more discriminative projection matrices favoring the optimization of the non-convex cost function. Initial matrices are computed by maximizing the centered-kernel alignment (CKA) metric, measuring the affinity between projected samples and labels. We evaluate the proposal performance in comparison with Random, AutoEncoders, and Principal Component Analysis approaches. As a result, CKA-based pre-training approach captures the complex dependencies between parameters, increases the convergence speed in the learning stage, and unravels the data distribution to favor the class discrimination for five widely image collections used in classification tasks of image object recognition.

Supervised Brain Tissue Segmentation Using a Spatially Enhanced Similarity Metric

Many medical applications commonly make use of brain magnetic resonance images (MRI) as an information source since they provide a non-invasive view of the head morphology and functionality. Such information is given by the properties of head structures, which are extracted using segmentation techniques. Among them, multi-atlas-based methodologies are the most popular, allowing to consider prior spatial information about the distribution of brain structures. These approaches rely on a non-linear mapping of the information of the most relevant atlases to a query image. Nevertheless, methodology effectiveness is highly dependent on the mapping function and the atlas relevance criterion, being both of them based on the selection of an MRI similarity metric. Here, a new spatially weighting measure is proposed to enhance the multi-atlas-based segmentation results. The proposal is tested in an MRI segmentation database for state-of-the-art image metrics as means squares, histogram correlation coefficient, normalized mutual information, and neighborhood cross-correlation and compared against other spatial combination approaches. Achieved results show that our proposal outperforms baseline methods, providing a more suitable atlas selection.

Kernel Centered Alignment Supervised Metric for Multi-Atlas Segmentation

Recently multi-atlas based methods have been used for supporting brain structure segmentation. These approaches encode the shape variability on a given population and provide prior information. However, the accuracy on the segmentation depend on the capability of the each atlas on the dataset to propagate the labels to the target image. In this sense, the selection of the most relevant atlases becomes an important task. In this paper, a new locally-weighted criterion is proposed to highlight spatial correspondences between images, aiming to enhance multi-atlas based segmentation results. Our proposal combines the spatial correspondences by a linear weighted combination and uses the kernel centered alignment criterion to find the best weight combination. The proposal is tested in an MRI segmentation task for state of the art image metrics as Mean Squares and Mutual Information and it is compared against other weighting criterion methods. Obtained results show that our approach outperforms the baseline methods providing a more suitable atlas selection and improving the segmentation of ganglia basal structures.