Artificial intelligence in radiology: relevance of collaborative work between radiologists and engineers for building a multidisciplinary team.

The use of artificial intelligence (AI) algorithms in the field of radiology is becoming more common. Several studies have demonstrated the potential utility of machine learning (ML) and deep learning (DL) techniques as aids for radiologists to solve specific radiological challenges. The decision-making process, the establishment of specific clinical or radiological targets, the profile of the different professionals involved in the development of AI solutions, and the relation with partnerships and stakeholders are only some of the main issues that have to be faced and solved prior to starting the development of radiological AI solutions. Among all the players in this multidisciplinary team, the communication between radiologists and data scientists is essential for a successful collaborative work. There are specific skills that are inherent to radiological and medical training that are critical for identifying anatomical or clinical targets as well as for segmenting or labelling lesions. These skills would then have to be transferred, explained, and taught to the data science experts to facilitate their comprehension and integration into ML or DL algorithms. On the other hand, there is a wide range of complex software packages, deep neural-network architectures, and data transfer processes for which radiologists need the expertise of software engineers and data scientists in order to select the optimal manner to analyse and post-process this amount of data. This paper offers a summary of the top five challenges faced by radiologists and data scientists including tips and tricks to build a successful AI team.

Nonlinear Weighting Ensemble Learning Model to Diagnose Parkinson's Disease Using Multimodal Data.

Parkinson's Disease (PD) is the second most prevalent neurodegenerative disorder among adults. Although its triggers are still not clear, they may be due to a combination of different types of biomarkers measured through medical imaging, metabolomics, proteomics or genetics, among others. In this context, we have proposed a Computer-Aided Diagnosis (CAD) system that combines structural and functional imaging data from subjects in Parkinson's Progression Markers Initiative dataset by means of an Ensemble Learning methodology trained to identify and penalize input sources with low classification rates and/ or high-variability. This proposal improves results published in recent years and provides an accurate solution not only from the point of view of image preprocessing (including a comparison between different intensity preservation techniques), but also in terms of dimensionality reduction methods (Isomap). In addition, we have also introduced a bagging classification schema for scenarios with unbalanced data. As shown by our results, the CAD proposal is able to detect PD with [Formula: see text] of balanced accuracy, and opens up the possibility of combining any number of input data sources relevant for PD.

Improved parkinsonism diagnosis using a partial least squares based approach.

PURPOSE: An accurate and early diagnosis of Parkinsonian syndrome (PS) is nowadays a challenge. This syndrome includes several pathologies with similar symptoms (Parkinson's disease, multisystem atrophy, progressive supranuclear palsy, corticobasal degeneration and others) which make the diagnosis more difficult. (123)I-ioflupane allows to obtain in vivo images of the brain that can be used to assist the PS diagnosis and provides a way to improve its accuracy. METHODS: In this paper, we show a novel method to automatically classify (123)I-ioflupane images into two groups: controls or PS. The proposed methodology analyzes separately each hemisphere of the brain by means of a novel approach based on partial least squares (PLS) and support vector machine. RESULTS: A database with 189 (123)I-ioflupane images (94 controls and 95 pathological images) was used for evaluation purposes. The application of the proposed method based on PLS yields high accuracy rates up to 94.7% with sensitivity = 93.7% and specificity = 95.7%, outperforming previous approaches based on singular value decomposition, which are used as a reference. CONCLUSIONS: The use of advanced techniques based on classical signal analysis and their application to each hemisphere of the brain separately improves the (assisted) diagnosis of PS.

A Connection Between Pattern Classification by Machine Learning and Statistical Inference With the General Linear Model.

A connection between the general linear model (GLM) with frequentist statistical testing and machine learning (MLE) inference is derived and illustrated. Initially, the estimation of GLM parameters is expressed as a Linear Regression Model (LRM) of an indicator matrix; that is, in terms of the inverse problem of regressing the observations. Both approaches, i.e. GLM and LRM, apply to different domains, the observation and the label domains, and are linked by a normalization value in the least-squares solution. Subsequently, we derive a more refined predictive statistical test: the linear Support Vector Machine (SVM), that maximizes the class margin of separation within a permutation analysis. This MLE-based inference employs a residual score and associated upper bound to compute a better estimation of the actual (real) error. Experimental results demonstrate how parameter estimations derived from each model result in different classification performance in the equivalent inverse problem. Moreover, using real data, the MLE-based inference including model-free estimators demonstrates an efficient trade-off between type I errors and statistical power.

Feature selection using factor analysis for Alzheimer's diagnosis using 18F-FDG PET images.

PURPOSE: This article presents a computer-aided diagnosis technique for improving the accuracy of the early diagnosis of Alzheimer's disease (AD). Two hundred and ten 18F-FDG PET images from the ADNI initiative [52 normal controls (NC), 114 mild cognitive impairment (MCI), and 53 AD subjects] are studied. METHODS: The proposed methodology is based on the selection of voxels of interest using the t-test and a posterior reduction of the feature dimension using factor analysis. Factor loadings are used as features for three different classifiers: Two multivariate Gaussian mixture model, with linear and quadratic discriminant function, and a support vector machine with linear kernel. RESULTS: An accuracy rate up to 95% when NC and AD are considered and an accuracy rate up to 88% and 86% for NC-MCI and NC-MCI,AD, respectively, are obtained using SVM with linear kernel. CONCLUSIONS: Results are compared to the voxel-as-features and a PCA- based approach and the proposed methodology achieves better classification performance.

Prediction of CO maximum ground level concentrations in the Bay of Algeciras, Spain using artificial neural networks.

The region of the Bay of Algeciras is a very industrialized area where very few air pollution studies have been carried out. The main objective of this work has been the use of artificial neural networks (ANNs) as a predictive tool of high levels of ambient carbon monoxide (CO). Two approaches have been used: multilayer perceptron models (MLPs) with backpropagation learning rule and k-Nearest Neighbours (k-nn) classifiers, in order to predict future peaks of carbon monoxide. A resampling strategy with twofold cross-validation allowed the statistical comparison of the different topologies and models considered in the study. The procedure of random resampling permits an adequate and robust multiple comparisons of the tested models and allow us to select a group of best models.

Speech enhancement in discontinuous transmission systems using the constrained-stability least-mean-squares algorithm.

In this paper a novel constrained-stability least-mean-squares (LMS) algorithm for filtering speech sounds is proposed in the adaptive noise cancellation (ANC) problem. It is based on the minimization of the squared Euclidean norm of the weight vector change under a stability constraint over the a posteriori estimation errors. To this purpose, the Lagrangian methodology has been used in order to propose a nonlinear adaptation in terms of the product of differential input and error. Convergence analysis is also studied in terms of the evolution of the natural modes to the optimal Wiener-Hopf solution so that the stability performance depends exclusively on the adaptation parameter mu and the eigenvalues of the difference matrix DeltaR(1). The algorithm shows superior performance over the referenced algorithms in the ANC problem of speech discontinuous transmission systems, which are characterized by rapid transitions of the desired signal. The experimental analysis carried out on the AURORA 3 speech databases provides an extensive performance evaluation together with an exhaustive comparison to the standard LMS algorithms, i.e., the normalized LMS (NLMS), and other recently reported LMS algorithms such as the modified NLMS, the error nonlinearity LMS, or the normalized data nonlinearity LMS adaptation.

Using deep neural networks along with dimensionality reduction techniques to assist the diagnosis of neurodegenerative disorders.

The analysis of neuroimaging data is frequently used to assist the diagnosis of neurodegenerative disorders such as Alzheimer's disease (AD) or Parkinson's disease (PD) and has become a routine procedure in the clinical practice. During the past decade, the pattern recognition community has proposed a number of machine learning-based systems that automatically analyse neuroimaging data in order to improve the diagnosis. However, the high dimensionality of the data is still a challenge and there is room for improvement. The development of novel classification frameworks as TensorFlow, recently released as open source by Google Inc., represents an opportunity to continue evolving these systems. In this work, we demonstrate several computer-aided diagnosis (CAD) systems based on Deep Neural Networks that improve the diagnosis for AD and PD and outperform those based on classical classifiers. In order to address the small sample size problem we evaluate two dimensionality reduction algorithms based on Principal Component Analysis and Non-Negative Matrix Factorization (NNMF), respectively. The performance of developed CAD systems is assessed using 4 datasets with neuroimaging data of different modalities.

Automated Detection and Segmentation of Nonmass-Enhancing Breast Tumors with Dynamic Contrast-Enhanced Magnetic Resonance Imaging.

Nonmass-enhancing (NME) lesions constitute a diagnostic challenge in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the breast. Computer-aided diagnosis (CAD) systems provide physicians with advanced tools for analysis, assessment, and evaluation that have a significant impact on the diagnostic performance. Here, we propose a new approach to address the challenge of NME lesion detection and segmentation, taking advantage of independent component analysis (ICA) to extract data-driven dynamic lesion characterizations. A set of independent sources was obtained from the DCE-MRI dataset of breast cancer patients, and the dynamic behavior of the different tissues was described by multiple dynamic curves, together with a set of eigenimages describing the scores for each voxel. A new test image is projected onto the independent source space using the unmixing matrix, and each voxel is classified by a support vector machine (SVM) that has already been trained with manually delineated data. A solution to the high false-positive rate problem is proposed by controlling the SVM hyperplane location, outperforming previously published approaches.

Ensemble of random forests One vs. Rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares.

BACKGROUND: Alzheimer's disease (AD) is the most common cause of dementia in the elderly and affects approximately 30 million individuals worldwide. Mild cognitive impairment (MCI) is very frequently a prodromal phase of AD, and existing studies have suggested that people with MCI tend to progress to AD at a rate of about 10-15% per year. However, the ability of clinicians and machine learning systems to predict AD based on MRI biomarkers at an early stage is still a challenging problem that can have a great impact in improving treatments. METHOD: The proposed system, developed by the SiPBA-UGR team for this challenge, is based on feature standardization, ANOVA feature selection, partial least squares feature dimension reduction and an ensemble of One vs. Rest random forest classifiers. With the aim of improving its performance when discriminating healthy controls (HC) from MCI, a second binary classification level was introduced that reconsiders the HC and MCI predictions of the first level. RESULTS: The system was trained and evaluated on an ADNI datasets that consist of T1-weighted MRI morphological measurements from HC, stable MCI, converter MCI and AD subjects. The proposed system yields a 56.25% classification score on the test subset which consists of 160 real subjects. COMPARISON WITH EXISTING METHOD(S): The classifier yielded the best performance when compared to: (i) One vs. One (OvO), One vs. Rest (OvR) and error correcting output codes (ECOC) as strategies for reducing the multiclass classification task to multiple binary classification problems, (ii) support vector machines, gradient boosting classifier and random forest as base binary classifiers, and (iii) bagging ensemble learning. CONCLUSIONS: A robust method has been proposed for the international challenge on MCI prediction based on MRI data. The system yielded the second best performance during the competition with an accuracy rate of 56.25% when evaluated on the real subjects of the test set.

Combining Feature Extraction Methods to Assist the Diagnosis of Alzheimer's Disease.

Neuroimaging data as (18)F-FDG PET is widely used to assist the diagnosis of Alzheimer's disease (AD). Looking for regions with hypoperfusion/ hypometabolism, clinicians may predict or corroborate the diagnosis of the patients. Modern computer aided diagnosis (CAD) systems based on the statistical analysis of whole neuroimages are more accurate than classical systems based on quantifying the uptake of some predefined regions of interests (ROIs). In addition, these new systems allow determining new ROIs and take advantage of the huge amount of information comprised in neuroimaging data. A major branch of modern CAD systems for AD is based on multivariate techniques, which analyse a neuroimage as a whole, considering not only the voxel intensities but also the relations among them. In order to deal with the vast dimensionality of the data, a number of feature extraction methods have been successfully applied. In this work, we propose a CAD system based on the combination of several feature extraction techniques. First, some commonly used feature extraction methods based on the analysis of the variance (as principal component analysis), on the factorization of the data (as non-negative matrix factorization) and on classical magnitudes (as Haralick features) were simultaneously applied to the original data. These feature sets were then combined by means of two different combination approaches: i) using a single classifier and a multiple kernel learning approach and ii) using an ensemble of classifier and selecting the final decision by majority voting. The proposed approach was evaluated using a labelled neuroimaging database along with a cross validation scheme. As conclusion, the proposed CAD system performed better than approaches using only one feature extraction technique. We also provide a fair comparison (using the same database) of the selected feature extraction methods.

Using frequency analysis to improve the precision of human body posture algorithms based on Kalman filters.

With the advent of miniaturized inertial sensors many systems have been developed within the last decade to study and analyze human motion and posture, specially in the medical field. Data measured by the sensors are usually processed by algorithms based on Kalman Filters in order to estimate the orientation of the body parts under study. These filters traditionally include fixed parameters, such as the process and observation noise variances, whose value has large influence in the overall performance. It has been demonstrated that the optimal value of these parameters differs considerably for different motion intensities. Therefore, in this work, we show that, by applying frequency analysis to determine motion intensity, and varying the formerly fixed parameters accordingly, the overall precision of orientation estimation algorithms can be improved, therefore providing physicians with reliable objective data they can use in their daily practice.

A Spherical Brain Mapping of MR Images for the Detection of Alzheimer's Disease.

Magnetic Resonance Imaging (MRI) is of fundamental importance in neuroscience, providing good contrast and resolution, as well as not being considered invasive. Despite the development of newer techniques involving radiopharmaceuticals, it is still a recommended tool in Alzheimer's Disease (AD) neurological practice to assess neurodegeneration, and recent research suggests that it could reveal changes in the brain even before the symptomatology appears. In this paper we propose a method that performs a Spherical Brain Mapping, using different measures to project the three-dimensional MR brain images onto two-dimensional maps revealing statistical characteristics of the tissue. The resulting maps could be assessed visually, but also perform a significant feature reduction that will allow further supervised or unsupervised processing, reducing the computational load while maintaining a large amount of the original information. We have tested our methodology against a MRI database comprising 180 AD affected patients and 180 normal controls, where some of the mappings have revealed as an optimum strategy for the automatic processing and characterization of AD patterns, achieving up to a 90.9% of accuracy, as well as significantly reducing the computational load. Additionally, our maps allow the visual analysis and interpretation of the images, which can be of great help in the diagnosis of this and other types of dementia.

An Optimal Approach for Selecting Discriminant Regions for the Diagnosis of Alzheimer's Disease.

In this work, we present a fully automatic computer-aided diagnosis method for the early diagnosis of the Alzheimer's disease. We study the distance between classes (labelled as normal controls and possible Alzheimer's disease) calculated in 116 regions of the brain using the Welchs's t-test. We select the regions with highest Welchs's t-test value as features to perform classification. Furthermore, we also study the less discriminative region according to the t-test (regions with lowest t-test absolute values) in order to use them as reference. We show that the mean and standard deviation of the intensity values in these two regions, the less and most discriminative according to the Welch's ttest, can be combined as a vector. The modulus and phase of this vector reveal statistical differences between groups which can be used to improve the classification task. We show how they can be used as input for a support vector machine classifier. The proposed methodology is tested in a SPECT brain database of 70 SPECT brain images yielding an accuracy up to 91.5% for a wide range of selected voxels.

Functional Biomedical Images of Alzheimer's Disease. A Green's Function-based Empirical Mode Decomposition Study.

Positron emission tomography (PET) provides a functional imaging modality to detect signs of dementias in human brains. Two-dimensional empirical mode decomposition (2D-EMD) provides means to analyze such images. It decomposes the latter into characteristic modes which represent textures on different spatial scales. These textures provide informative features for subsequent classification purposes. The study proposes a new EMD variant which relies on a Green's function based estimation method including a tension parameter to fast and reliably estimate the envelope hypersurfaces interpolating extremal points of the two-dimensional intensity distrubution of the images. The new method represents a fast and stable bi-dimensional EMD which speeds up computations roughly 100-fold. In combination with proper classifiers these exploratory feature extraction techniques can form a computer aided diagnosis (CAD) system to assist clinicians in identifying various diseases from functional images alone. PET images of subjects suffering from Alzheimer's disease are taken to illustrate this ability.

Comparison between Different Intensity Normalization Methods in 123I-Ioflupane Imaging for the Automatic Detection of Parkinsonism.

Intensity normalization is an important pre-processing step in the study and analysis of DaTSCAN SPECT imaging. As most automatic supervised image segmentation and classification methods base their assumptions regarding the intensity distributions on a standardized intensity range, intensity normalization takes on a very significant role. In this work, a comparison between different novel intensity normalization methods is presented. These proposed methodologies are based on Gaussian Mixture Model (GMM) image filtering and mean-squared error (MSE) optimization. The GMM-based image filtering method is achieved according to a probability threshold that removes the clusters whose likelihood are negligible in the non-specific regions. The MSE optimization method consists of a linear transformation that is obtained by minimizing the MSE in the non-specific region between the intensity normalized image and the template. The proposed intensity normalization methods are compared to: i) a standard approach based on the specific-to-non-specific binding ratio that is widely used, and ii) a linear approach based on the α-stable distribution. This comparison is performed on a DaTSCAN image database comprising analysis and classification stages for the development of a computer aided diagnosis (CAD) system for Parkinsonian syndrome (PS) detection. In addition, these proposed methods correct spatially varying artifacts that modulate the intensity of the images. Finally, using the leave-one-out cross-validation technique over these two approaches, the system achieves results up to a 92.91% of accuracy, 94.64% of sensitivity and 92.65 % of specificity, outperforming previous approaches based on a standard and a linear approach, which are used as a reference. The use of advanced intensity normalization techniques, such as the GMM-based image filtering and the MSE optimization improves the diagnosis of PS.

Gated Sensor Fusion: A way to Improve the Precision of Ambulatory Human Body Motion Estimation.

Human body motion is usually variable in terms of intensity and, therefore, any Inertial Measurement Unit attached to a subject will measure both low and high angular rate and accelerations. This can be a problem for the accuracy of orientation estimation algorithms based on adaptive filters such as the Kalman filter, since both the variances of the process noise and the measurement noise are set at the beginning of the algorithm and remain constant during its execution. Setting fixed noise parameters burdens the adaptation capability of the filter if the intensity of the motion changes rapidly. In this work we present a conjoint novel algorithm which uses a motion intensity detector to dynamically vary the noise statistical parameters of different approaches of the Kalman filter. Results show that the precision of the estimated orientation in terms of the RMSE can be improved up to 29% with respect to the standard fixed-parameters approaches.

Parametrization of textural patterns in 123I-ioflupane imaging for the automatic detection of Parkinsonism.

PURPOSE: A novel approach to a computer aided diagnosis system for the Parkinson's disease is proposed. This tool is intended as a supporting tool for physicians, based on fully automated methods that lead to the classification of (123)I-ioflupane SPECT images. METHODS: (123)I-ioflupane images from three different databases are used to train the system. The images are intensity and spatially normalized, then subimages are extracted and a 3D gray-level co-occurrence matrix is computed over these subimages, allowing the characterization of the texture using Haralick texture features. Finally, different discrimination estimation methods are used to select a feature vector that can be used to train and test the classifier. RESULTS: Using the leave-one-out cross-validation technique over these three databases, the system achieves results up to a 97.4% of accuracy, and 99.1% of sensitivity, with positive likelihood ratios over 27. CONCLUSIONS: The system presents a robust feature extraction method that helps physicians in the diagnosis task by providing objective, operator-independent textural information about (123)I-ioflupane images, commonly used in the diagnosis of the Parkinson's disease. Textural features computation has been optimized by using a subimage selection algorithm, and the discrimination estimation methods used here makes the system feature-independent, allowing us to extend it to other databases and diseases.

Functional activity maps based on significance measures and Independent Component Analysis.

The use of functional imaging has been proven very helpful for the process of diagnosis of neurodegenerative diseases, such as Alzheimer's Disease (AD). In many cases, the analysis of these images is performed by manual reorientation and visual interpretation. Therefore, new statistical techniques to perform a more quantitative analysis are needed. In this work, a new statistical approximation to the analysis of functional images, based on significance measures and Independent Component Analysis (ICA) is presented. After the images preprocessing, voxels that allow better separation of the two classes are extracted, using significance measures such as the Mann-Whitney-Wilcoxon U-Test (MWW) and Relative Entropy (RE). After this feature selection step, the voxels vector is modelled by means of ICA, extracting a few independent components which will be used as an input to the classifier. Naive Bayes and Support Vector Machine (SVM) classifiers are used in this work. The proposed system has been applied to two different databases. A 96-subjects Single Photon Emission Computed Tomography (SPECT) database from the "Virgen de las Nieves" Hospital in Granada, Spain, and a 196-subjects Positron Emission Tomography (PET) database from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Values of accuracy up to 96.9% and 91.3% for SPECT and PET databases are achieved by the proposed system, which has yielded many benefits over methods proposed on recent works.

Parameterization of the distribution of white and grey matter in MRI using the α-stable distribution.

This work presents a study of the distribution of the grey matter (GM) and white matter (WM) in brain magnetic resonance imaging (MRI). The distribution of GM and WM is characterized using a mixture of α-stable distributions. A Bayesian α-stable mixture model for histogram data is presented and unknown parameters are sampled using the Metropolis-Hastings algorithm. The proposed methodology is tested in 18 real images from the MRI brain segmentation repository. The GM and WM distributions are accurately estimated. The α-stable distribution mixture model presented in this paper can be used as previous step in more complex MRI segmentation procedures using spatial information. Furthermore, due to the fact that the α-stable distribution is a generalization of the Gaussian distribution, the proposed methodology can be applied instead of the Gaussian mixture model, which is widely used in segmentation of brain MRI in the literature.