Automatic diagnosis of COVID-19 from CT images using CycleGAN and transfer learning.

The outbreak of the corona virus disease (COVID-19) has changed the lives of most people on Earth. Given the high prevalence of this disease, its correct diagnosis in order to quarantine patients is of the utmost importance in the steps of fighting this pandemic. Among the various modalities used for diagnosis, medical imaging, especially computed tomography (CT) imaging, has been the focus of many previous studies due to its accuracy and availability. In addition, automation of diagnostic methods can be of great help to physicians. In this paper, a method based on pre-trained deep neural networks is presented, which, by taking advantage of a cyclic generative adversarial net (CycleGAN) model for data augmentation, has reached state-of-the-art performance for the task at hand, i.e., 99.60% accuracy. Also, in order to evaluate the method, a dataset containing 3163 images from 189 patients has been collected and labeled by physicians. Unlike prior datasets, normal data have been collected from people suspected of having COVID-19 disease and not from data from other diseases, and this database is made available publicly. Moreover, the method's reliability is further evaluated by calibration metrics, and its decision is interpreted by Grad-CAM also to find suspicious regions as another output of the method and make its decisions trustworthy and explainable.

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.

[Renal pathophysiology and pharmacological mechanisms of nephroprotection]. / Fisiopatología renal y mecanismos farmacológicos de nefroprotección.

Several risk factors may affect the progression of chronic kidney disease (CKD). Arterial hypertension, proteinuria, obesity, intraglomerular hypertension, smoking and metabolic control in diabetes mellitus are the main modifiable risk factors for progression. The progression of CKD involves many cellular processes that originate in specific compartments of the kidney, the vascular compartment with nephroangiosclerosis and the tubulointerstitial compartment with fibrosis and tubulointerstitial atrophy, and there may be overlap between both mechanisms. Given the involvement of so many risk factors and so many pathogenic pathways in the progression of CKD, the best hope for delaying or preventing the progression of CKD lies in a combined and multidisciplinary therapeutic approach, based on the existing evidence and acting on all these processes and pathways from the mechanistic point of view, and on a global process that is cardiovascular and renal risk to improve the prognosis of patients.

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.

[COVID-19 and cardiovascular and kidney disease: Where are we? Where are we going?] / COVID-19 y enfermedad cardiovascular y renal: ¿Dónde estamos? ¿Hacia dónde vamos?

The SARS-CoV-2 pandemic is a global health emergency and we need to know more about it. Patients with cardiovascular risk and previous kidney risk have been identified as especially vulnerable for greater morbidity and mortality when they suffer from COVID-19. A considerable proportion of patients can develop a vascular lesion in the context of the disease that entails a greater lethality. Cardiovascular and renal complications represent a problem and, probably in the near future, may pose a threat to patients who have survived COVID-19. As physicians, we cannot forget that during an epidemic like this, other chronic diseases are present, and patients continue to require care. We are obliged to monitor even more intensely their treatments and control degree. Furthermore, we must not forget that urgent situations continue to arise in this pandemic situation and require prompt attention. In this current situation, it is very likely that many patients, out of fear, have not sought medical attention. The situation during the epidemic and the uncertainty of the post-COVID-19 period, requires intensification in the control and monitoring of cardiovascular and kidney disease in our patients. Primary care constitutes a key level of care for the care of the population with cardiovascular disease. Likewise, and in the face of this new health scenario, we need to promote the prevention and control measures that emanate from the studies currently underway. Now, more than ever, we need research, crucial to improve the cardiovascular and renal prognosis of our patients.

[Tools to improve efficiency in the clinical management of hypertensive patients]. / Herramienta para mejorar la eficiencia en el manejo clínico de pacientes hipertensos.

OBJECTIVE: To create a tool to evaluate the efficiency of the clinical management of hypertensive patients in Primary Care. MATERIAL AND METHODS: A web-based questionnaire was designed for Primary Care centres to self-evaluate the management of hypertension in five specific areas: information systems, diagnostic and analytical tests, organisational aspects, use of resources, and continuous training programmes for patients and healthcare professionals. A committee of experts previously defined these questions and their ideal responses or "control", based on the scientific literature or, if there were no published references, by consensus of the committee. A descriptive analysis was performed on the data, and an adherence score was created that ranged from 0 (no adherence) to 1 (total adherence). RESULTS: A total of 35 Primary Care centres entered their data into the website for the clinical management of hypertensive patients. The highest adherence to the ideal algorithm was observed in the area "Diagnostic and analytical tests" (0.69±0.10), and the lowest in "Continuous training programmes for patients and professionals" (0.42±0.21). CONCLUSIONS: The efficiency of clinical management in hypertensive patients can be analysed using the website tool created for this purpose. Its use allows an internal audit to detect the areas that need improvement, and also serves to make comparative evaluations in the different areas of management over time.

[Positioning for the management of arterial hypertension in Primary Care from the critical analysis of the American (2017) and European (2018) guidelines. Spanish Society of Primary Care Physicians (SEMERGEN)]. / Posicionamiento para el manejo de la hipertensión arterial en atención primaria a partir del análisis crítico de las guías americana (2017) y europea (2018). Sociedad Española de Médicos de Atención Primaria (SEMERGEN).

The Scientific Societies of Primary Care, being the area in which there is a considerable prevalence of Arterial Hypertension (AHT), need to periodically evaluate the international guidelines for its management. This is particularly relevant when disparate guidelines make it difficult to make decisions in daily clinical practice. The present document has as its aim to analyse the changes and new developments proposed in the guidelines of the American College of Cardiology and the American Heart Association (ACC/AHA 2017), as well as in the guidelines of the European Society of Cardiology and European Society of Hypertension (ESC/ESH 2018). An analysis will be made of any differences, limitations, and their applicability to Primary Care in Spain. Finally, the most relevant available and appropriate information is extracted and integrated in order to homogenise the care of the hypertensive patient, from a critical, but also a reasoned, perspective. The discrepancies between the recommendations in such essential aspects as the management of the disease, require the compiling and critical analysis of the information that enables us as scientific society, interested in providing all PC physicians with the most relevant, and at the same time, sensible, recommendations of all the guidelines.

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.

[Unawareness of the K/DOQI guidelines for bone and mineral metabolism in predialysis chronic kidney disease: results of the OSERCE Spanish multicenter-study survey]. / Desconocimiento de las guías K/DOQI sobre la alteración del metabolismo óseo-mineral asociada a la enfermedad renal crónica no en diálisis: resultados de la encuesta en el estudio multicéntrico español OSERCE.

Since its publication in 2003, the K/DOQI clinical practice guidelines for bone metabolism and disease in chronic kidney disease (CKD) have become a worldwide reference. The aim of this study was to analyze the observance to these guidelines in patients with a glomerular filtration rate < 60 ml/min/1,73m2 not yet included in dialysis in a Spanish multicenter cohort. A questionnaire by investigator/centre was completed by 32 different nephrologists participating in the OSERCE study and representing the overall Spanish public health net. We observed that biochemical parameters were measured less frequently than recommended, except in CKD stage 3. The therapeutic goals for intact PTH were not properly reported by 59 % of the consulted nephrologists for stages 3 and 4, whereas only 22% did not report them properly for stage 5. The goals for phosphorus were not adequately reported in 50 % of cases (stages 3 y 4) and 60 % (stage 5). For calcium, these values were 70 %, 73.3 % and 65.5 % for stages 3, 4 and 5, respectively. A corrected plasma calcium between 9.5 and 10.2 mg/dl is still considered adequate for 31%. As much as 87% nephrologists stated that they did not sistematically measure calcidiol plasma levels. In general, these results demonstrate that there is a great degree of unawareness of K/DOQITM predialysis guidelines. Thus, their poor implementation is probably not only due to the lower availability of approved therapeutic agents, the difficult achievement of goals or the disbelief on current recommendations. It would be desirable that forthcoming guidelines such as the KDIGO could also consider the need of educational efforts for CKD-Mineral and Bone Disorder.

Sodium zirconium cyclosilicate: a new potassium binder for the treatment of hyperkalemia.

Hyperkalemia is one of the most common electrolyte disturbances, especially among some groups of patients, such as in those with chronic kidney disease, diabetes or heart failure. Hyperkalemia has been associated with increased risks of mortality, arrhythmias, hospitalization and costs, as well as the need to down titrate/discontinue renin-angiotensin-aldosterone system inhibitors (RAASIs), despite their well-known cardiovascular and nephroprotective benefits. Current potassium binders have limitations (slow onset of action, limited selectivity for potassium binding, risk of drug interactions or gastrointestinal intolerance). Sodium zirconium cyclosilicate (SZC) is a new potassium binder recently approved for the treatment of chronic hyperkalemia. It is a nonabsorbable, inorganic crystal which selectively binds potassium and ammonium in exchange of Na+ and H+ in the whole gastrointestinal tract, achieving a rapid correction of serum potassium levels (within 2 days) and maintaining normokalemia in the long term (up to 1 year), with a good safety profile (common adverse reactions include gastrointestinal events and a dose-dependent risk of edema), excellent tolerability and a low potential for drug interactions. Its potassium-lowering efficacy is maintained irrespective of the use of RAASIs. In summary, SZC is a new potassium binder recently approved for the treatment of hyperkalemia. Its differences with respect to currently available potassium binders make SZC an attractive therapeutic option.

[Anemia of chronic kidney disease: Protocol of study, management and referral to Nephrology]. / Anemia en la enfermedad renal crónica: protocolo de estudio, manejo y derivación a Nefrología.

The objective of this protocol is to know which test are needed to study an anaemia in a patient with chronic kidney disease, the differential diagnosis of renal anaemia, to know and correct other deficiency anaemias, and the criteria for referral to Nephrology or other specialties of the anaemic patient with chronic kidney disease.

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.

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.

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.

[Seasonal perodicity in vascular access thrombosis for haemodialysis]. / Ritmo estacional en la trombosis del acceso vascular para hemodiálisis.

Different studies have shown that some clinical events, particularly cardiovascular and thrombotic events, show a regularity in its appearance. The aim of our study was to analyse the possible existence of seasonal periodicity in the incidence of the vascular access thrombosis in patients on chronic haemodialysis. Prospectively, we collected information of 164 patients with 250 episodes of vascular access thrombosis referred to our hospital from january 1995 to december 1999. An ANOVA test for comparison of the means, and a time series analysis were performed. During the five year study the consecutive number of thrombosis were 43, 57, 55, 59 and 36. When the different seasons were analysed, the cumulative number of events in summer during the study period were 91, a significant increase compared to spring, autumn, and winter (54, 54, and 51, respectively; p<0.001). Time series analysis confirmed that thrombolic events during summer showed an increased incidence over the mean (p<0.001), and it occurred every year. The same results were obtained when the PTFE grafts were analyzed separetely (july RR 2.62, p=0.002; august, RR 2.37, p=0.04), but not with the arteriovenous fistulae. In conclusion, this study showed a seasonal periodicity of vascular access thrombosis, with a PTFE graft. Although the causes were unknown, these data alert us on the convenience of an increased attention to the vascular access during the summer months in order to prevent its thrombosis.