Francisco J. Martínez-Murcia

Francisco J. Martinez-Murcia, Juan M. Górriz, Javier Ramírez et al.

Spatial and intensity normalization are nowadays a prerequisite for neuroimaging analysis. Influenced by voxel-wise and other univariate comparisons, where these corrections are key, they are commonly applied to any type of analysis and imaging modalities. Nuclear imaging modalities such as PET-FDG or FP-CIT SPECT, a common modality used in Parkinson's Disease diagnosis, are especially dependent on intensity normalization. However, these steps are computationally expensive and furthermore, they may introduce deformations in the images, altering the information contained in them. Convolutional Neural Networks (CNNs), for their part, introduce position invariance to pattern recognition, and have been proven to classify objects regardless of their orientation, size, angle, etc. Therefore, a question arises: how well can CNNs account for spatial and intensity differences when analysing nuclear brain imaging? Are spatial and intensity normalization still needed? To answer this question, we have trained four different CNN models based on well-established architectures, using or not different spatial and intensity normalization preprocessing. The results show that a sufficiently complex model such as our three-dimensional version of the ALEXNET can effectively account for spatial differences, achieving a diagnosis accuracy of 94.1% with an area under the ROC curve of 0.984. The visualization of the differences via saliency maps shows that these models are correctly finding patterns that match those found in the literature, without the need of applying any complex spatial normalization procedure. However, the intensity normalization -- and its type -- is revealed as very influential in the results and accuracy of the trained model, and therefore must be well accounted.

Juan M Gorriz, J. Ramirez, F. Segovia et al.

Regression analysis is a central topic in statistical modeling, aimed at estimating the relationships between a dependent variable, commonly referred to as the response variable, and one or more independent variables, i.e., explanatory variables. Linear regression is by far the most popular method for performing this task in various fields of research, such as data integration and predictive modeling when combining information from multiple sources. Classical methods for solving linear regression problems, such as Ordinary Least Squares (OLS), Ridge, or Lasso regressions, often form the foundation for more advanced machine learning (ML) techniques, which have been successfully applied, though without a formal definition of statistical significance. At most, permutation or analyses based on empirical measures (e.g., residuals or accuracy) have been conducted, leveraging the greater sensitivity of ML estimations for detection. In this paper, we introduce Statistical Agnostic Regression (SAR) for evaluating the statistical significance of ML-based linear regression models. This is achieved by analyzing concentration inequalities of the actual risk (expected loss) and considering the worst-case scenario. To this end, we define a threshold that ensures there is sufficient evidence, with a probability of at least $1-η$, to conclude the existence of a linear relationship in the population between the explanatory (feature) and the response (label) variables. Simulations demonstrate the ability of the proposed agnostic (non-parametric) test to provide an analysis of variance similar to the classical multivariate $F$-test for the slope parameter, without relying on the underlying assumptions of classical methods. Moreover, the residuals computed from this method represent a trade-off between those obtained from ML approaches and the classical OLS.

C. Vázquez-García, F. J. Martínez-Murcia, F. Segovia Román et al.

Neuroimaging data, particularly from techniques like MRI or PET, offer rich but complex information about brain structure and activity. To manage this complexity, latent representation models - such as Autoencoders, Generative Adversarial Networks (GANs), and Latent Diffusion Models (LDMs) - are increasingly applied. These models are designed to reduce high-dimensional neuroimaging data to lower-dimensional latent spaces, where key patterns and variations related to brain function can be identified. By modeling these latent spaces, researchers hope to gain insights into the biology and function of the brain, including how its structure changes with age or disease, or how it encodes sensory information, predicts and adapts to new inputs. This review discusses how these models are used for clinical applications, like disease diagnosis and progression monitoring, but also for exploring fundamental brain mechanisms such as active inference and predictive coding. These approaches provide a powerful tool for both understanding and simulating the brain's complex computational tasks, potentially advancing our knowledge of cognition, perception, and neural disorders.

Carmen Jimenez-Mesa, Yizhou Wan, Guilio Sansone et al.

Brain tumor resection is a highly complex procedure with profound implications for survival and quality of life. Predicting patient outcomes is crucial to guide clinicians in balancing oncological control with preservation of neurological function. However, building reliable prediction models is severely limited by the rarity of curated datasets that include both pre- and post-surgery imaging, given the clinical, logistical and ethical challenges of collecting such data. In this study, we develop a novel framework that integrates explainable artificial intelligence (XAI) with neuroimaging-based feature engineering for survival assessment in brain tumor patients. We curated structural MRI data from 49 patients scanned pre- and post-surgery, providing a rare resource for identifying survival-related biomarkers. A key methodological contribution is the development of a global explanation optimizer, which refines survival-related feature attribution in deep learning models, thereby improving both the interpretability and reliability of predictions. From a clinical perspective, our findings provide important evidence that survival after oncological surgery is influenced by alterations in regions related to cognitive and sensory functions. These results highlight the importance of preserving areas involved in decision-making and emotional regulation to improve long-term outcomes. From a technical perspective, the proposed optimizer advances beyond state-of-the-art XAI methods by enhancing both the fidelity and comprehensibility of model explanations, thus reinforcing trust in the recognition patterns driving survival prediction. This work demonstrates the utility of XAI-driven neuroimaging analysis in identifying survival-related variability and underscores its potential to inform precision medicine strategies in brain tumor treatment.

C. Vázquez-García, F. J. Martínez-Murcia, F. Segovia Román et al.

In this tutorial, we explore Variational Autoencoders (VAEs), an essential framework for unsupervised learning, particularly suited for high-dimensional datasets such as neuroimaging. By integrating deep learning with Bayesian inference, VAEs enable the generation of interpretable latent representations. This tutorial outlines the theoretical foundations of VAEs, addresses practical challenges such as convergence issues and over-fitting, and discusses strategies like the reparameterization trick and hyperparameter optimization. We also highlight key applications of VAEs in neuroimaging, demonstrating their potential to uncover meaningful patterns, including those associated with neurodegenerative processes, and their broader implications for analyzing complex brain data.

Nicolás Gallego-Molina, Marco Formoso, Andrés Ortiz et al.

Electroencephalography signals allow to explore the functional activity of the brain cortex in a non-invasive way. However, the analysis of these signals is not straightforward due to the presence of different artifacts and the very low signal-to-noise ratio. Cross-Frequency Coupling (CFC) methods provide a way to extract information from EEG, related to the synchronization among frequency bands. However, CFC methods are usually applied in a local way, computing the interaction between phase and amplitude at the same electrode. In this work we show a method to compute PAC features among electrodes to study the functional connectivity. Moreover, this has been applied jointly with Principal Component Analysis to explore patterns related to Dyslexia in 7-years-old children. The developed methodology reveals the temporal evolution of PAC-based connectivity. Directions of greatest variance computed by PCA are called eigenPACs here, since they resemble the classical \textit{eigenfaces} representation. The projection of PAC data onto the eigenPACs provide a set of features that has demonstrates their discriminative capability, specifically in the Beta-Gamma bands.

Marco A. Formoso, Andrés Ortiz, Francisco J. Martínez-Murcia et al.

Several methods have been developed to extract information from electroencephalograms (EEG). One of them is Phase-Amplitude Coupling (PAC) which is a type of Cross-Frequency Coupling (CFC) method, consisting in measure the synchronization of phase and amplitude for the different EEG bands and electrodes. This provides information regarding brain areas that are synchronously activated, and eventually, a marker of functional connectivity between these areas. In this work, intra and inter electrode PAC is computed obtaining the relationship among different electrodes used in EEG. The connectivity information is then treated as a graph in which the different nodes are the electrodes and the edges PAC values between them. These structures are embedded to create a feature vector that can be further used to classify multichannel EEG samples. The proposed method has been applied to classified EEG samples acquired using specific auditory stimuli in a task designed for dyslexia disorder diagnosis in seven years old children EEG's. The proposed method provides AUC values up to 0.73 and allows selecting the most discriminant electrodes and EEG bands.

Juan E. Arco, Andrés Ortiz, Javier Ramírez et al.

The outbreak of the COVID-19 (Coronavirus disease 2019) pandemic has changed the world. According to the World Health Organization (WHO), there have been more than 100 million confirmed cases of COVID-19, including more than 2.4 million deaths. It is extremely important the early detection of the disease, and the use of medical imaging such as chest X-ray (CXR) and chest Computed Tomography (CCT) have proved to be an excellent solution. However, this process requires clinicians to do it within a manual and time-consuming task, which is not ideal when trying to speed up the diagnosis. In this work, we propose an ensemble classifier based on probabilistic Support Vector Machine (SVM) in order to identify pneumonia patterns while providing information about the reliability of the classification. Specifically, each CCT scan is divided into cubic patches and features contained in each one of them are extracted by applying kernel PCA. The use of base classifiers within an ensemble allows our system to identify the pneumonia patterns regardless of their size or location. Decisions of each individual patch are then combined into a global one according to the reliability of each individual classification: the lower the uncertainty, the higher the contribution. Performance is evaluated in a real scenario, yielding an accuracy of 97.86%. The large performance obtained and the simplicity of the system (use of deep learning in CCT images would result in a huge computational cost) evidence the applicability of our proposal in a real-world environment.

Juan E. Arco, A. Ortiz, J. Ramirez et al.

Respiratory diseases kill million of people each year. Diagnosis of these pathologies is a manual, time-consuming process that has inter and intra-observer variability, delaying diagnosis and treatment. The recent COVID-19 pandemic has demonstrated the need of developing systems to automatize the diagnosis of pneumonia, whilst Convolutional Neural Network (CNNs) have proved to be an excellent option for the automatic classification of medical images. However, given the need of providing a confidence classification in this context it is crucial to quantify the reliability of the model's predictions. In this work, we propose a multi-level ensemble classification system based on a Bayesian Deep Learning approach in order to maximize performance while quantifying the uncertainty of each classification decision. This tool combines the information extracted from different architectures by weighting their results according to the uncertainty of their predictions. Performance of the Bayesian network is evaluated in a real scenario where simultaneously differentiating between four different pathologies: control vs bacterial pneumonia vs viral pneumonia vs COVID-19 pneumonia. A three-level decision tree is employed to divide the 4-class classification into three binary classifications, yielding an accuracy of 98.06% and overcoming the results obtained by recent literature. The reduced preprocessing needed for obtaining this high performance, in addition to the information provided about the reliability of the predictions evidence the applicability of the system to be used as an aid for clinicians.

Andrés Ortiz, Francisco J. Martinez-Murcia, Marco A. Formoso et al.

Objective dyslexia diagnosis is not a straighforward task since it is traditionally performed by means of the intepretation of different behavioural tests. Moreover, these tests are only applicable to readers. This way, early diagnosis requires the use of specific tasks not only related to reading. Thus, the use of Electroencephalography (EEG) constitutes an alternative for an objective and early diagnosis that can be used with pre-readers. In this way, the extraction of relevant features in EEG signals results crucial for classification. However, the identification of the most relevant features is not straighforward, and predefined statistics in the time or frequency domain are not always discriminant enough. On the other hand, classical processing of EEG signals based on extracting EEG bands frequency descriptors, usually make some assumptions on the raw signals that could cause indormation loosing. In this work we propose an alternative for analysis in the frequency domain based on Singluar Spectrum Analysis (SSA) to split the raw signal into components representing different oscillatory modes. Moreover, correlation matrices obtained for each component among EEG channels are classfied using a Convolutional Neural network.