Search

Typically, deep learning models for image segmentation tasks are trained using large datasets of images annotated at the pixel level, which can be expensive and highly time-consuming. A way to reduce the amount of annotated images required for training is to adopt a semi-supervised approach. In this regard, generative deep learning models, concretely Generative Adversarial Networks (GANs), have been adapted to semi-supervised training of segmentation tasks. This work proposes MaskGDM, a deep learning architecture combining some ideas from EditGAN, a GAN that jointly models images and their segmentations, together with a generative diffusion model. With careful integration, we find that using a generative diffusion model can improve EditGAN performance results in multiple segmentation datasets, both multi-class and with binary labels. According to the quantitative results obtained, the proposed model improves multi-class image segmentation when compared to the EditGAN and DatasetGAN models, respectively, by [Formula: see text] and [Formula: see text]. Moreover, using the ISIC dataset, our proposal improves the results from other models by up to [Formula: see text] for the binary image segmentation approach.

The application of deep learning to image and video processing has become increasingly popular nowadays. Employing well-known pre-trained neural networks for detecting and classifying objects in images is beneficial in a wide range of application fields. However, diverse impediments may degrade the performance achieved by those neural networks. Particularly, Gaussian noise and brightness, among others, may be presented on images as sensor noise due to the limitations of image acquisition devices. In this work, we study the effect of the most representative noise types and brightness alterations on images in the performance of several state-of-the-art object detectors, such as YOLO or Faster-RCNN. Different experiments have been carried out and the results demonstrate how these adversities deteriorate their performance. Moreover, it is found that the size of objects to be detected is a factor that, together with noise and brightness factors, has a considerable impact on their performance.

Anomaly detection in sequences is a complex problem in security and surveillance. With the exponential growth of surveillance cameras in urban roads, automating them to analyze the data and automatically identify anomalous events efficiently is essential. This paper presents a methodology to detect anomalous events in urban sequences using pre-trained convolutional neural networks (CNN) and super-resolution (SR) models. The proposal is composed of two parts. In the offline stage, the pre-trained CNN model evaluated a large dataset of urban sequences to detect and establish the common locations of the elements of interest. Analyzing the offline sequences, a density matrix is calculated to learn the spatial patterns and identify the most frequent locations of these elements. Based on probabilities previously calculated from the offline analysis, the pre-trained CNN, now in an online stage, assesses the probability of anomalies appearing in the real-time sequence using the density matrix. Experimental results demonstrate the effectiveness of the presented approach in detecting several anomalies, such as unusual pedestrian routes. This research contributes to urban surveillance by providing a practical and reliable method to improve public safety in urban environments. The proposed methodology can assist city management authorities in proactively detecting anomalies, thus enabling timely reaction and improving urban safety.

Introduction: Anti-glomerular basement membrane (anti-GBM) disease is a severe entity with few therapeutic options including plasma exchange and immunosuppressive agents. The aim of this study was to analyze the clinical and pathological features that predict the evolution of end-stage kidney disease (ESKD) and the kidney survival in a cohort of patients with anti-GBM disease with renal involvement in real life., Methods: A retrospective multicentre observational study including 72 patients from 18 nephrology departments with biopsy-proven anti-GBM disease from 1999 to 2019 was performed. Progression to ESKD in relation to clinical and histological variables was evaluated., Results: Creatinine at admission was 8.6 (± 4) mg/dL and 61 patients (84.7%) required dialysis. Sixty-five patients (90.3%) underwent plasma exchange. Twenty-two patients (30.6%) presented pulmonary hemorrhage. Kidney survival was worse in patients with creatinine levels > 4.7 mg/dL (3 vs. 44% p < 0.01) and in patients with > 50% crescents (6 vs. 49%; p = 0.03). Dialysis dependence at admission and creatinine levels > 4.7 mg/dL remained independent significant predictors of ESKD in the multivariable analysis [HR (hazard ratio) 3.13 (1.25-7.84); HR 3 (1.01-9.14); p < 0.01]. The discrimination value for a creatinine level > 4.7 mg/dL and 50.5% crescents had an area under the curve (AUC) of 0.9 (95% CI 0.82-0.97; p < 0.001) and 0.77 (95% CI 0.56-0.98; p = 0.008), respectively. Kidney survival at 1 and 2 years was 13.5 and 11%, respectively. Patient survival at 5 years was 81%., Conclusion: In real life, patients with severe anti-GBM disease (creatinine > 4.7 mg/dL and > 50% crescents) remained with devastating renal prognosis despite plasma exchange and immunosuppressive treatment. New therapies for the treatment of this rare renal disease are urgently needed., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Sánchez-Agesta, Rabasco, Soler, Shabaka, Canllavi, Fernández, Cazorla, López-Rubio, Romera, Barroso, Huerta, Calle, Sierra, Domínguez-Torres, Moreno-Ramírez, Afonso, Mascarós, Coca, Espinosa and Spanish Group for the Study of Glomerular Diseases (GLOSEN).)

The COVID-19 pandemic forced the population worldwide into lockdown. The purpose of this study was to assess the impact of this measure on the health and comfort of university students and the role that the characteristics of the home may have played. It is essential to differentiate between the terms comfort and health both from the medical and architectural perspectives, as there are differences between the two concepts that are, nonetheless, shared by both disciplines. An online survey was fulfilled by 188 medicine and architecture undergraduate students at the University of Seville, Spain. In terms of health, 89% suffered neuropsychiatric disorders (56% anxiety and 49% depression), 38% gained weight and 59% reported alcohol consumption. In relation to comfort, the majority rated their home positively, comfortable in terms of room temperature and noise at night, and they had a good relationship with cohabitants. However, those who did not have a balcony or terrace would have liked to have open spaces They would have also liked to increase the size of their bedroom, where they spent most of their time and where they studied. A built-up environment gave them a sense of being imprisoned, while those who enjoyed open spaces found a sense of peace. The absence of open spaces in the house, the environment and the impossibility of making the most frequently used spaces more flexible may have had negative impacts on the health and comfort of university students during confinement.

One of the most important challenges in computer vision applications is the background modeling, especially when the background is dynamic and the input distribution might not be stationary, i.e. the distribution of the input data could change with time (e.g. changing illuminations, waving trees, water, etc.). In this work, an unsupervised learning neural network is proposed which is able to cope with progressive changes in the input distribution. It is based on a dual learning mechanism which manages the changes of the input distribution separately from the cluster detection. The proposal is adequate for scenes where the background varies slowly. The performance of the method is tested against several state-of-the-art foreground detectors both quantitatively and qualitatively, with favorable results.

In this work, a novel self-organizing model called growing neural forest (GNF) is presented. It is based on the growing neural gas (GNG), which learns a general graph with no special provisions for datasets with separated clusters. On the contrary, the proposed GNF learns a set of trees so that each tree represents a connected cluster of data. High dimensional datasets often contain large empty regions among clusters, so this proposal is better suited to them than other self-organizing models because it represents these separated clusters as connected components made of neurons. Experimental results are reported which show the self-organization capabilities of the model. Moreover, its suitability for unsupervised clustering and foreground detection applications is demonstrated. In particular, the GNF is shown to correctly discover the connected component structure of some datasets. Moreover, it outperforms some well-known foreground detectors both in quantitative and qualitative terms.

Background: Renal biopsy registries allow histopathological data to be collected to improve knowledge of different pathologies and their natural history., Aim: To analyse the data of the Castilla La Mancha Glomerulonephritis Registry (GLOMANCHA) and the evolution of the different biopsy-proven pathologies between 1994 and 2008., Methods: The 6 most common biopsy-proven pathologies were collected during the 14 years of the study (941 biopsies) in the 5 participant centres of the autonomous community. In 2008, we assessed patient renal survival and mortality and we evaluated associated factors to each situation for each pathology., Results: Of the 941 biopsies, 59% belonged to men, with a mean age of 48±18 years. At the time of the biopsy, the median glomerular filtration rate was 50.3 (25.5-76.3) ml/min/1,73 m(2) and median proteinuria was 3.4 (1.5-6.4) grams per day. The most common pathology were lupus nephropathy, followed by focal segmental glomerulosclerosis and membranous nephropathy. Lupus nephropathy and minimal change disease achieved the best renal prognosis during follow-up (mean 7.3±4.8 years). Rapidly progressive glomerulonephritis type 3 and focal segmental glomerulosclerosis had the worst renal prognosis. In addition, rapidly progressive glomerulonephritis type 3 presented the worst vital prognosis., Conclusions: In GLOMANCHA, we demonstrate the poor prognosis of rapidly progressive glomerulonephritis type 3, in contrast to minimal change disease or lupus nephropathy. Renal function is an independent predictor of renal survival and mortality in this study., (Copyright © 2016 Sociedad Española de Nefrología. Published by Elsevier España, S.L.U. All rights reserved.)

The original Self-Organizing Feature Map (SOFM) has been extended in many ways to suit different goals and application domains. However, the topologies of the map lattice that we can found in literature are nearly always square or, more rarely, hexagonal. In this paper we study alternative grid topologies, which are derived from the geometrical theory of tessellations. Experimental results are presented for unsupervised clustering, color image segmentation and classification tasks, which show that the differences among the topologies are statistically significant in most cases, and that the optimal topology depends on the problem at hand. A theoretical interpretation of these results is also developed., (Copyright © 2014 Elsevier Ltd. All rights reserved.)

Growing hierarchical self-organizing models are characterized by the flexibility of their structure, which can easily accommodate for complex input datasets. However, most proposals use the Euclidean distance as the only error measure. Here we propose a way to introduce Bregman divergences in these models, which is based on stochastic approximation principles, so that more general distortion measures can be employed. A procedure is derived to compare the performance of networks using different divergences. Moreover, a probabilistic interpretation of the model is provided, which enables its use as a Bayesian classifier. Experimental results are presented for classification and data visualization applications, which show the advantages of these divergences with respect to the classical Euclidean distance.

The estimation of multivariate probability density functions has traditionally been carried out by mixtures of parametric densities or by kernel density estimators. Here we present a new nonparametric approach to this problem which is based on the integration of several multivariate histograms, computed over affine transformations of the training data. Our proposal belongs to the class of averaged histogram density estimators. The inherent discontinuities of the histograms are smoothed, while their low computational complexity is retained. We provide a formal proof of the convergence to the real probability density function as the number of training samples grows, and we demonstrate the performance of our approach when compared with a set of standard probability density estimators.

Background: Mycophenolate (MF) is effective as induction and maintenance treatment in patients with lupus nephritis (LN). This study evaluates the efficacy and safety of MF in patients with refractory and relapsing LN., Methods: Data were retrospectively obtained for 85 patients (35 refractory and 50 relapsing) from 11 nephrology departments in Spain. The primary endpoints were the incidence and cumulative number of renal responses and relapses and their relationship with baseline clinical and analytical data. The secondary endpoint was the appearance of side effects., Results: The main clinical and analytical variables were similar both in refractory and relapsing LN. Most of the patients had received cyclophosphamide, and all of them switched to MF. 74 patients (87%) achieved a response (69% partial, 31% complete). Age at starting MF, gender, pathological classification, body mass index, blood pressure, baseline renal function, and proteinuria were not associated with achieving response. After stopping MF, 3 of 19 patients (15.7%) relapsed, all at 6 months of follow-up. No differences were found between clinical and analytical variables and number of relapses. Side effects were unremarkable, except for 1 patient, who died of thrombocytopenia and ovarian hemorrhage., Conclusions: Switching to MF from other immunosuppressive treatments is effective and safe in refractory and relapsing LN., (© 2014 S. Karger AG, Basel)

Background: Mycophenolate (MF) is effective as a maintenance therapy after induction therapy in patients with lupus nephritis (LN). However, little is known about its role in patients with impaired renal function. The purpose of this study was to evaluate the efficacy and safety of MF as a maintenance therapy for LN and its association with renal function., Methods: Data were obtained for 56 Spanish patients who were receiving MF as a maintenance therapy for LN. Patients were classified into two groups according to renal function at the initiation of MF treatment: group 1 [estimated glomerular filtration rate (eGFR) ≥60 ml/min/1.73 m(2)] and group 2 (eGFR <60 ml/min/1.73 m(2)). The primary endpoints of the study were the rates of renal relapse and responses, and their relationship with baseline renal function. Secondary outcomes were the appearance of side effects during treatment., Results: At initiation of MF treatment, the only differences between the groups were for age, hemoglobin levels, anti-DNA antibody titer, proteinuria, and renal function. In group 1 (n = 38), the eGFR was 98 ± 34 ml/min/1.73 m(2) and in group 2 (n = 18) the eGFR was 43 ± 14 ml/min/1.73 m(2). Only 3 cases had an eGFR <30 ml/min/1.73 m(2). No significant differences were observed in the rate of relapse at 6 months (group 1: 20%; group 2: 23%) or at 12 months (group 1: 25%; group 2: 17%). Response rates were also similar in both groups. Side effects were unremarkable., Conclusions: MF is effective and safe as a maintenance therapy for LN both in patients with normal renal function and in those with renal impairment., (Copyright © 2013 S. Karger AG, Basel.)

Background: Mycophenolate (MF) is effective as induction therapy for lupus nephritis (LN) in patients with normal renal function; however, little is known about its role in patients with impaired renal failure. The purpose of this study was to evaluate the response to MF in LN and its association with baseline renal function., Methods: Data were obtained for 90 patients from 12 Spanish renal units who were receiving MF as induction therapy for LN. Patients were classified into 2 groups: group 1 (estimated glomerular filtration rate [eGFR] ≥60 ml/min/1.73 m(2)) and group 2 (eGFR <60 ml/min/ 1.73 m(2)). The primary outcome measure was the percentage of patients who achieved any response and its relationship with initial eGFR. The secondary outcome measures were the percentage of patients who achieved a complete response (CR) or partial response (PR) and the appearance of relapses during treatment and side effects., Results: At initiation of MF treatment, there were no differences in the main parameters between group 1 (n = 63; eGFR 87 ± 23 ml/min/ 1.73 m(2)) and group 2 (n = 27; eGFR 44 ± 12 ml/min/1.73 m(2)). Exposure to prednisone and MF was similar. The percentages of patients who achieved a response in groups 1 and 2 were, respectively, 69.2 and 43.8% at 6 months and 81.3 and 73.7% at 12 months. CR was more frequent in group 1, whereas PR was similar in both groups. Four patients relapsed and side effects were unremarkable., Conclusions: MF is effective and safe as induction therapy for LN, and response is even achieved in patients with baseline renal impairment., (Copyright © 2012 S. Karger AG, Basel.)

Kernel regression is a non-parametric estimation technique which has been successfully applied to image denoising and enhancement in recent times. Magnetic resonance 3D image denoising has two features that distinguish it from other typical image denoising applications, namely the tridimensional structure of the images and the nature of the noise, which is Rician rather than Gaussian or impulsive. Here we propose a principled way to adapt the general kernel regression framework to this particular problem. Our noise removal system is rooted on a zeroth order 3D kernel regression, which computes a weighted average of the pixels over a regression window. We propose to obtain the weights from the similarities among small sized feature vectors associated to each pixel. In turn, these features come from a second order 3D kernel regression estimation of the original image values and gradient vectors. By considering directional information in the weight computation, this approach substantially enhances the performance of the filter. Moreover, Rician noise level is automatically estimated without any need of human intervention, i.e. our method is fully automated. Experimental results over synthetic and real images demonstrate that our proposal achieves good performance with respect to the other MRI denoising filters being compared., (Copyright © 2011 Elsevier B.V. All rights reserved.)

Since the introduction of the growing hierarchical self-organizing map, much work has been done on self-organizing neural models with a dynamic structure. These models allow adjusting the layers of the model to the features of the input dataset. Here we propose a new self-organizing model which is based on a probabilistic mixture of multivariate Gaussian components. The learning rule is derived from the stochastic approximation framework, and a probabilistic criterion is used to control the growth of the model. Moreover, the model is able to adapt to the topology of each layer, so that a hierarchy of dynamic graphs is built. This overcomes the limitations of the self-organizing maps with a fixed topology, and gives rise to a faithful visualization method for high-dimensional data.

Background modeling and foreground detection are key parts of any computer vision system. These problems have been addressed in literature with several probabilistic approaches based on mixture models. Here we propose a new kind of probabilistic background models which is based on probabilistic self-organising maps. This way, the background pixels are modeled with more flexibility. On the other hand, a statistical correlation measure is used to test the similarity among nearby pixels, so as to enhance the detection performance by providing a feedback to the process. Several well known benchmark videos have been used to assess the relative performance of our proposal with respect to traditional neural and non neural based methods, with favourable results, both qualitatively and quantitatively. A statistical analysis of the differences among methods demonstrates that our method is significantly better than its competitors. This way, a strong alternative to classical methods is presented.

We present a self-organizing map model to study qualitative data (also called categorical data). It is based on a probabilistic framework which does not assume any prespecified distribution of the input data. Stochastic approximation theory is used to develop a learning rule that builds an approximation of a discrete distribution on each unit. This way, the internal structure of the input dataset and the correlations between components are revealed without the need of a distance measure among the input values. Experimental results show the capabilities of the model in visualization and unsupervised learning tasks., (Copyright © 2010 Elsevier Ltd. All rights reserved.)

The original Kohonen's Self-Organizing Map model has been extended by several authors to incorporate an underlying probability distribution. These proposals assume mixtures of Gaussian probability densities. Here we present a new self-organizing model which is based on a mixture of multivariate Student-t components. This improves the robustness of the map against outliers, while it includes the Gaussians as a limit case. It is based on the stochastic approximation framework. The 'degrees of freedom' parameter for each mixture component is estimated within the learning procedure. Hence it does not need to be tuned manually. Experimental results are presented to show the behavior of our proposal in presence of outliers, and its performance in adaptive filtering and classification problems.

Robustness against outliers is a desirable property of any unsupervised learning scheme. In particular, probability density estimators benefit from incorporating this feature. A possible strategy to achieve this goal is to substitute the sample mean and the sample covariance matrix by more robust location and spread estimators. Here we use the L1-median to develop a nonparametric probability density function (PDF) estimator. We prove its most relevant properties, and we show its performance in density estimation and classification applications.

In this paper, we present a probabilistic neural model, which extends Kohonen's self-organizing map (SOM) by performing a probabilistic principal component analysis (PPCA) at each neuron. Several SOMs have been proposed in the literature to capture the local principal subspaces, but our approach offers a probabilistic model while it has a low complexity on the dimensionality of the input space. This allows to process very high-dimensional data to obtain reliable estimations of the probability densities which are based on the PPCA framework. Experimental results are presented, which show the map formation capabilities of the proposal with high-dimensional data, and its potential in image and video compression applications.

We present a new neural model which extends the classical competitive learning (CL) by performing a Probabilistic Principal Components Analysis (PPCA) at each neuron. The model also has the ability to learn the number of basis vectors required to represent the principal directions of each cluster, so it overcomes a drawback of most local PCA models, where the dimensionality of a cluster must be fixed a priori. Experimental results are presented to show the performance of the network with multispectral image data.

Introduction: Outcome of renal transplant from expanded criteria donors (ECD) is usually inferior than those from standard criteria donors (SCD) and may be improved decreasing cold ischemia time (CIT) and minimizing preservation injury. We compare the results obtained with CIT <15 hours in kidney transplants from ECD vs SCD., Subjects and Methods: Prospective, single center study of kidney transplants performed since June 2003 to December 2007. Minimum follow-up period was 12 months. Data of donors, receptors and transplant outcome from ECD and SCD are compared., Results: CIT (mean +/- SD) was 9.3+/-2.5 hours in transplants from ECD (n=24) and 8.3+/-3.3 hours in those from SCD (N=50), p=0.18. We did not find significant differences among recipients of grafts from ECD and those from SCD regarding: primary non-function (4.2% vs 2%, respectively), delayed graft function (16.7% vs 10%), surgical complications (25% vs 16%) or acute rejection episodes (8.3% vs 2%). Glomerular filtration rate at one year follow-up was 65.8+/-14.9 ml/min in ECD recipients and 49.4+/-12.5 ml/min (p<0.0001). One year graft survival was 95.8% in ECD recipients and 94% in SCD recipients (p=0.75)., Conclusions: Short CIT in kidney transplant from ECD leads to similar outcome than that obtained from SCD, although renal function is inferior in ECD grafts.

Adrenal myelolipoma is a rare, benign, slow-growing tumor composed of adipose tissue and hematopoietic elements. It is usually diagnosed incidentally, although there are reports of patients with symptoms and descriptions of retroperitoneal hemorrhage due to rupture of large tumors. The condition has been associated with obesity, high blood pressure and adrenal dysfunction. We present a patient with retroperitoneal hemorrhage due to spontaneous rupture of a myelolipoma, hypertension, and renal failure secondary to nephroangiosclerosis.

We present a patient with lupus nephropathy of 20 years of evolution in treatment with oral steroids who developed a meningoencephalitis associated to bacteraemia by Listeria monocytogenes. The patient was treated successfully with gentamicin and ampicillin for 6 weeks. Infection by Listeria monocytogenes occurs more frequently in individuals with some form of immunodeficiency like lupus disease, with a mortality around 30%.

We present a patient from Germany with Hantavirus infection, admitted in the Emergency room of our hospital, with fever, thrombocytopenia, acute renal failure, oliguria, mild proteinuria and hematuria. Percutaneous renal biopsy revealed an acute interstitial nephritis without medulla haemorrhages. The virus infection confirmation was made by detection of IgM against Hantavirus Puumala. This infection should be considered in patients with thrombocytopenia, fever and acute renal failure, over all if they are from North and Central Europe.

We present a new neural model that extends the classical competitive learning by performing a principal components analysis (PCA) at each neuron. This model represents an improvement with respect to known local PCA methods, because it is not needed to present the entire data set to the network on each computing step. This allows a fast execution while retaining the dimensionality-reduction properties of the PCA. Furthermore, every neuron is able to modify its behavior to adapt to the local dimensionality of the input distribution. Hence, our model has a dimensionality estimation capability. The experimental results we present show the dimensionality-reduction capabilities of the model with multisensor images.

We propose a new self-organizing neural model that performs principal components analysis. It is also related to the adaptive subspace self-organizing map (ASSOM) network, but its training equations are simpler. Experimental results are reported, which show that the new model has better performance than the ASSOM network.

Amyloidosis is a systemic disease characterized by generalized deposition of beta-organized proteic fibrillar material with green birefringence under polarized light, in different tissues and organs, the most frequent kidney, liver and heart, with important clinical repercussion. Primary or AL amyloidosis is the most common subtype of amyloidosis (1), confirmed by biopsy-proved amyloid deposition in abdominal fat pad, rectum, kidney or liver, if necessary, in which fragments of monoclonal light chains are deposited. Cases with factor X (Stuart factor) of coagulation deficiency associated are described, due to adsorption of this factor to amyloid fibrills. Normally, evolution is fatal, with only few months of survival. We report a case of primary amyloidosis with nephrotic syndrome, severe factor X deficiency (without bleeding complications), possible heart affection and short-term good response to chemotherapic treatment.

Objectives: Presentation of a series of 18 patients who underwent surgery of aldosterone-producing adrenal adenoma (Conn's syndrome) over the last 10 years. Assessment of the most significant clinical and pathological aspects from a surgical point of view., Methods: Retrospective study evaluating a broad range of features: clinical, analytical, hormonal, imaging, types of anaesthesia, approaches, technique used, intra and post-operative morbidity and mortality, evolution and pathoanatomical diagnosis., Results: The most frequent clinical data of primary hyperaldosteronism were: 94.4% volume-dependent HBP, 50% headaches and dizziness, 27.8% epistasis and/or episodes of angor or acute myocardial infarction, and 22.2% heart failure. The biochemical study and hormonal testing evidenced: hypokalemia in 88.9%, metabolic alkalosis 66.7% and hypernatremia in 61.1%. Mean aldosterone levels were 517.5 pg/mL, and urinary levels 85.9 mcg/day. Resting plasma renin activity (PRA) < 0.2 ng/mL/h in 77.8% cases and positive aldosterone stimulation test in 61.1%: captopril test positive. Imaging diagnosis was based in CAT which was conclusive in 88.9% and ultrasound which was diagnostic in 27.8% cases. The surgical approach was: lumbotomy (over the 11th or 12th rib) in 14 patients and transpleurodiaphragmatic in all remaining patients. The intraoperative complications reported were placement of endothoracic tube due to iatrogenic pneumothorax in two occasions. Duration of the procedure (mean 136.1 min) and post-operative hospitalization (mean 7.76 days), as well as post-surgery follow-up for up to 96 months were also studied. At final time point there was 66.7 asymptomatic patients, 33.3% cases of HBP, and no deaths., Conclusions: Primary hyperaldosteronism due to adrenal adenoma is an uncommon reason for HBP, but in most cases can be cured with surgery. Biochemical and hormonal testing is determinant to research a diagnosis. Ultrasound and CAT are essential for imaging diagnosis, and occasionally NMR can be of help. Lumbotomy is considered the choice approach for these small tumours as it is a familial technique for urologists with a low complications rate.