Automatic classification of pulmonary nodules in computed tomography images using pre-trained networks and bag of features.

Lung cancer has the highest incidence in the world. The standard tests for its diagnostics are medical imaging exams, sputum cytology, and lung biopsy. Computed Tomography (CT) of the chest plays an essential role in the early detection of nodules since it can allow for more treatment options and increases patient survival. However, the analysis of these exams is a tiring and error-prone process. Thus, computational methods can help the specialist in this analysis. This work addresses the classification of pulmonary nodules as benign or malignant on CT images. Our approach uses the pre-trained VGG16, VGG19, Inception, Resnet50, and Xception, to extract features from each 2D slice of the 3D nodules. Then, we use Principal Component Analysis to reduce the dimensionality of the feature vectors and make them all the same length. Then, we use Bag of Features (BoF) to combine the feature vectors of the different 2D slices and generate only one signature representing the 3D nodule. The classification step uses Random Forest. We evaluated the proposed method with 1,405 segmented nodules from the LIDC-IDRI database and obtained an accuracy of 95.34%, F1-Score of 91.73, kappa of 0.88, sensitivity of 90.53%, specificity of 97.26% and AUC of 0.99. The main conclusion was that the combination by BoF of features extracted from 2D slices using pre-trained architectures produced better results than training 2D and 3D CNNs in the nodules. In addition, the use of BoF also makes the creation of the nodule signature independent of the number of slices.

A ensemble methodology for automatic classification of chest X-rays using deep learning.

Chest radiographies, or chest X-rays, are the most standard imaging exams used in daily hospitals. Responsible for assisting in detecting numerous pathologies and findings that directly interfere in the patient's life, this exam is therefore crucial in screening patients. This work proposes a methodology based on a Convolutional Neural Networks (CNNs) ensemble to aid the diagnosis of chest X-ray exams by screening them with a high probability of being normal or abnormal. In the development of this study, a private dataset with frontal and lateral projections X-ray images was used. To build the ensemble model, VGG-16, ResNet50 and DenseNet121 architectures, which are commonly used in the classification of Chest X-rays, were evaluated. A Confidence Threshold (CTR) was used to define the predictions into High Confidence Normal (HCn), Borderline classification (BC), or High Confidence Abnormal (HCa). In the tests performed, very promising results were achieved: 54.63% of the exams were classified with high confidence; of the normal exams, 32% were classified as HCn with an false discovery rate (FDR) of 1.68%; and as to the abnormal exams, 23% were classified as HCa with 4.91% false omission rate (FOR).

Semi-automatic segmentation of skin lesions based on superpixels and hybrid texture information.

Dermoscopic images are commonly used in the early diagnosis of skin lesions, and several computational systems have been proposed to analyze them. The segmentation of the lesions is a fundamental step in many of these systems. Therefore, a semi-automatic segmentation method is proposed here, which begins by building the superpixels of the image under analysis based on the zero parameter version of the simple linear iterative clustering (SLIC0) algorithm. Then, each superpixel is represented using a descriptor built by combining the grey-level co-occurrence matrix and Tamura texture features. Afterward, the gain ratios of the features are used to select the input for the semi-supervised seeded fuzzy C-means clustering algorithm. Hence, from a few specialist-selected superpixels, this clustering algorithm groups the built superpixels into lesion or background regions. Finally, the segmented image undergoes a post-processing step to eliminate sharp edges. The experiments were performed on 1380 images: 401 images from the PH2 and DermIS datasets, which were used to establish the parameters of the method, and 3,573 images from the ISIC 2016, ISIC 2017 and ISIC 2018 datasets were used for the analysis of the method's performance. The findings suggest that, by manually identifying just a few of the generated superpixels, the method can achieve an average segmentation accuracy of 96.78%, which confirms its superiority to the ones in the literature.

Classification of COVID-19 in X-ray images with Genetic Fine-tuning.

New and more transmissible SARS-COV-2 variants aggravated the SARS-COV-2 emergence. Lung X-ray images stand out as an alternative to support case screening. The latest computer-aided diagnosis systems have been using Deep Learning (DL) to detect pulmonary diseases. In this context, our work investigates different types of pneumonia detection, including COVID-19, based on X-ray image processing and DL techniques. Our methodology comprehends a pre-processing step including data-augmentation, contrast enhancement, and resizing method to overcome the challenge of heterogeneous and few samples of public datasets. Additionally, we propose a new Genetic Fine-Tuning method to automatically define an optimal set of hyper-parameters of ResNet50 and VGG16 architectures. Our results are encouraging; we achieve an accuracy of 97% considering three classes: COVID-19, other pneumonia, and healthy. Thus, our methodology could assist in classifying COVID-19 pneumonia, which could reduce costs by making the process faster and more efficient.

Diagnosis of Leukaemia in Blood Slides Based on a Fine-Tuned and Highly Generalisable Deep Learning Model.

Leukaemia is a dysfunction that affects the production of white blood cells in the bone marrow. Young cells are abnormally produced, replacing normal blood cells. Consequently, the person suffers problems in transporting oxygen and in fighting infections. This article proposes a convolutional neural network (CNN) named LeukNet that was inspired on convolutional blocks of VGG-16, but with smaller dense layers. To define the LeukNet parameters, we evaluated different CNNs models and fine-tuning methods using 18 image datasets, with different resolution, contrast, colour and texture characteristics. We applied data augmentation operations to expand the training dataset, and the 5-fold cross-validation led to an accuracy of 98.61%. To evaluate the CNNs generalisation ability, we applied a cross-dataset validation technique. The obtained accuracies using cross-dataset experiments on three datasets were 97.04, 82.46 and 70.24%, which overcome the accuracies obtained by current state-of-the-art methods. We conclude that using the most common and deepest CNNs may not be the best choice for applications where the images to be classified differ from those used in pre-training. Additionally, the adopted cross-dataset validation approach proved to be an excellent choice to evaluate the generalisation capability of a model, as it considers the model performance on unseen data, which is paramount for CAD systems.

Recent computational methods for white blood cell nuclei segmentation: A comparative study.

BACKGROUND AND OBJECTIVE: Leukaemia is a disease found worldwide; it is a type of cancer that originates in the bone marrow and is characterised by an abnormal proliferation of white blood cells (leukocytes). In order to correctly identify this abnormality, haematologists examine blood smears from patients. A diagnosis obtained by this method may be influenced by factors such as the experience and level of fatigue of the haematologist, resulting in non-standard reports and even errors. In the literature, several methods have been proposed that involve algorithms to diagnose this disease. However, no reviews or surveys have been conducted. This paper therefore presents an empirical investigation of computational methods focusing on the segmentation of leukocytes. METHODS: In our study, 15 segmentation methods were evaluated using five public image databases: ALL-IDB2, BloodSeg, Leukocytes, JTSC Database and CellaVision. Following the standard methodology for literature evaluation, we conducted a pixel-level segmentation evaluation by comparing the segmented image with its corresponding ground truth. In order to identify the strengths and weaknesses of these methods, we performed an evaluation using six evaluation metrics: accuracy, specificity, precision, recall, kappa, Dice, and true positive rate. RESULTS: The segmentation algorithms performed significantly differently for different image databases, and for each database, a different algorithm achieved the best results. Moreover, the two best methods achieved average accuracy values higher than 97%, with an excellent kappa index. Also, the average Dice index indicated that the similarity between the segmented leukocyte and its ground truth was higher than 0.85 for these two methods This result confirms the high level of similarity between these images but does not guarantee that a method has segmented all leukocyte nuclei. We also found that the method that performed best segmented only 58.44% of all leukocytes. CONCLUSIONS: Of the techniques used to segment leukocytes, we note that clustering algorithms, the Otsu threshold, simple arithmetic operations and region growing are the approaches most widely used for this purpose. However, these computational methods have not yet overcome all the challenges posed by this problem.

Síndrome de Lemierre: relato de caso / Lemierre syndrome: case report

síndrome de Lemierre caracteriza-se pela tromboflebite séptica da veia jugular interna, após uma orofaringite, com embolização séptica para o pulmão ou outros órgãos. Neste relato de caso, apresentamos uma paciente feminina, 37 anos de idade, com história de edema e dor em hemiface direita há três dias, associada a fadiga e dispneia progressiva há um dia. História de extração dentária do elemento 48 há três dias. No exame físico admissional, apresentava-se taquipneica, saturando 60% (em ar ambiente), com edema em ângulo da mandíbula direita, redução difusa do murmúrio vesicular e panturrilhas sem empastamento. Angiotomografia de tórax e exames laboratoriais foram compatíveis com quadro de embolia séptica, e tomografia computadorizada da cervical corroborou o diagnóstico de tromboflebite séptica da veia jugular interna. Foi tratada com antibióticos e sintomáticos. A síndrome de Lemierre afeta mais homens jovens e tem embolização para o pulmão em até 97% dos casos. Extrações dentárias raramente podem ser a etiologia dessa síndrome. A tomografia computadorizada é o método de imagem mais utilizado no diagnóstico, e o tratamento é, essencialmente, com antibióticos; portanto, a abordagem cirúrgica é raramente necessária

Lemierre syndrome is characterized by septic thrombophlebitis of the internal jugular vein, after an oropharyngeal infection, with septic embolization to the lungs or other organs. This case report describes a 37-year-old female patient who presented with edema and pain in the right hemiface with onset 3 days previously and progressive fatigue and dyspnea since the previous day. She had had tooth 48 extracted 3 days previously. Physical examination at admission found tachypnea, with 60% saturation (in room air), edema at the angle of the right mandible, diffuse reduction of vesicular murmur, and calves free from clubbing. Angiotomography of the chest and laboratory tests were compatible with septic emboli, and cervical computed tomography confirmed a diagnosis of septic thrombophlebitis of the internal jugular vein. She was managed with antibiotics and given treatment for her symptoms. Lemierre syndrome most often occurs in young men and there is embolization to the lungs in up to 97% of cases. Rarely, the etiology of this syndrome may be tooth extraction. Computed tomography is the imaging method most often used for diagnosis and treatment is basically antibiotic. Surgery is thus rarely necessary

Lemierre syndrome: case report.

Lemierre syndrome is characterized by septic thrombophlebitis of the internal jugular vein, after an oropharyngeal infection, with septic embolization to the lungs or other organs. This case report describes a 37-year-old female patient who presented with edema and pain in the right hemiface with onset 3 days previously and progressive fatigue and dyspnea since the previous day. She had had tooth 48 extracted 3 days previously. Physical examination at admission found tachypnea, with 60% saturation (in room air), edema at the angle of the right mandible, diffuse reduction of vesicular murmur, and calves free from clubbing. Angiotomography of the chest and laboratory tests were compatible with septic emboli, and cervical computed tomography confirmed a diagnosis of septic thrombophlebitis of the internal jugular vein. She was managed with antibiotics and given treatment for her symptoms. Lemierre syndrome most often occurs in young men and there is embolization to the lungs in up to 97% of cases. Rarely, the etiology of this syndrome may be tooth extraction. Computed tomography is the imaging method most often used for diagnosis and treatment is basically antibiotic. Surgery is thus rarely necessary.

RELATIONSHIP BETWEEN THE PRESENCE OF HELICOBACTER PYLORI WITH INFLAMMATORY ENDOSCOPIC CHANGES IN GASTRODUODENAL MUCOSA.

Background: The influence of Helicobacter pylori (HP) in inflammatory disorders of the digestive mucosa has been the subject of several studies since socioeconomic, personal and environmental factors were implicated in the bacteria transmission. Aim: To correlate the inflammatory endoscopic findings with HP infection and the onset of mucosal diseases mucous of the upper digestive tract. Method: Comparative observational study, in which were collected data from 2247 patients who underwent upper endoscopy and biopsies for HP with urease test. The patients were divided into two groups: HP+ and HP- (control) in which endoscopic findings were observed for the following changes: esophagitis, esophageal ulcer, gastritis, erosive gastritis, gastric ulcer, bulboduodenitis, bulbar ulcer and without disease. Results: As for esophagitis, there was little disparity in the distribution favorable to HP+ group (HP+ =67.11% and HP- =69.89%) and esophageal ulcer (HP+ =0% and HP- =0, 21%). Gastritis was favorable to HP- group (HP+ =78.34% and HP- =73.63%), as well as erosive gastritis (HP+ = 67,11% and HP- = 64,55%), in bulboduodenitis (HP+ =1,87% and HP- 1,23%), in gastric ulcer (HP+ =2,14% and HP- =2,03%) and in the absence of alterations in the HP+ group (4.81%) with the HP- control group (6,30%), in which there was little disproportion in favor of HP- group, but without statistical significance. As for the bulbar ulcer (HP +=10.16% and HP- =4.48%), there was statistically significant (p=0.00001). Conclusion: There is no difference between HP+ and HP- groups in inflammatory changes in endoscopic gastroduodenal mucosa, except for the relationship between HP and bulbar ulcer.

Racional: A influência do Helicobacter pylori (HP) nas alterações inflamatórias das mucosas digestivas tem sido objeto de vários estudos uma vez que fatores socioeconômicos, pessoais e ambientais são implicados na transmissão da bactéria, facilitando-a. Objetivo: Relacionar os achados inflamatórios endoscópicos com a infecção pelo HP e o aparecimento de doenças mucosas do trato digestivo alto. Método: Estudo observacional comparativo, o qual foram coletados dados de 2247 pacientes submetidos à endoscopia digestiva alta e biópsias para HP com teste de urease. Os pacientes foram divididos em dois grupos: HP+ e o controle HP-dentro dos quais foram observados os achados endoscópicos referentes às seguintes alterações: esofagite, úlcera esofágica, gastrite, gastrite erosiva, úlcera gástrica, bulboduodenite, úlcera bulbar e sem doença. Resultados: Quanto à esofagite, observou-se pequena desproporção na distribuição, favorável ao grupo HP+ (HP+ =67,11% e HP- =69,89%) bem como na úlcera esofágica (HP+ =0% e HP- =0,21%). Na gastrite foi favorável ao grupo HP- (HP+ =78.34% e HP- =73.63%), assim como na gastrite erosiva (HP+ = 67,11% e HP- = 64,55%), na bulboduodenite (HP+ = 1,87% e HP- 1,23%), na úlcera gástrica (HP+ =2,14% e HP- =2,03%) e na ausência de alterações no grupo HP+ (4.81%) com o grupo controle HP- (6,30%), nos quais há pequena desproporção favorável ao grupo HP-, porém, sem significância estatística. Já quanto à úlcera bulbar (HP+ =10,16% e HP- =4,48%), houve significância estatística (p=0,00001). Conclusão: Não há diferenciação entre os grupos HP+ e HP- nas alterações endoscópicas inflamatórias na mucosa gastroduodenal, exceto para a relação entre HP e úlcera bulbar.

Relationship between the presence of helicobacter pylori with inflammatory endoscopic changes in gastroduodenal mucosa / Relação entre a presença do helicobacter pylori com alterações endoscópicas inflamatórias na mucosa gastroduodenal

ABSTRACT Background: The influence of Helicobacter pylori (HP) in inflammatory disorders of the digestive mucosa has been the subject of several studies since socioeconomic, personal and environmental factors were implicated in the bacteria transmission. Aim: To correlate the inflammatory endoscopic findings with HP infection and the onset of mucosal diseases mucous of the upper digestive tract. Method: Comparative observational study, in which were collected data from 2247 patients who underwent upper endoscopy and biopsies for HP with urease test. The patients were divided into two groups: HP+ and HP- (control) in which endoscopic findings were observed for the following changes: esophagitis, esophageal ulcer, gastritis, erosive gastritis, gastric ulcer, bulboduodenitis, bulbar ulcer and without disease. Results: As for esophagitis, there was little disparity in the distribution favorable to HP+ group (HP+ =67.11% and HP- =69.89%) and esophageal ulcer (HP+ =0% and HP- =0, 21%). Gastritis was favorable to HP- group (HP+ =78.34% and HP- =73.63%), as well as erosive gastritis (HP+ = 67,11% and HP- = 64,55%), in bulboduodenitis (HP+ =1,87% and HP- 1,23%), in gastric ulcer (HP+ =2,14% and HP- =2,03%) and in the absence of alterations in the HP+ group (4.81%) with the HP- control group (6,30%), in which there was little disproportion in favor of HP- group, but without statistical significance. As for the bulbar ulcer (HP +=10.16% and HP- =4.48%), there was statistically significant (p=0.00001). Conclusion: There is no difference between HP+ and HP- groups in inflammatory changes in endoscopic gastroduodenal mucosa, except for the relationship between HP and bulbar ulcer.

RESUMO Racional: A influência do Helicobacter pylori (HP) nas alterações inflamatórias das mucosas digestivas tem sido objeto de vários estudos uma vez que fatores socioeconômicos, pessoais e ambientais são implicados na transmissão da bactéria, facilitando-a. Objetivo: Relacionar os achados inflamatórios endoscópicos com a infecção pelo HP e o aparecimento de doenças mucosas do trato digestivo alto. Método: Estudo observacional comparativo, o qual foram coletados dados de 2247 pacientes submetidos à endoscopia digestiva alta e biópsias para HP com teste de urease. Os pacientes foram divididos em dois grupos: HP+ e o controle HP-dentro dos quais foram observados os achados endoscópicos referentes às seguintes alterações: esofagite, úlcera esofágica, gastrite, gastrite erosiva, úlcera gástrica, bulboduodenite, úlcera bulbar e sem doença. Resultados: Quanto à esofagite, observou-se pequena desproporção na distribuição, favorável ao grupo HP+ (HP+ =67,11% e HP- =69,89%) bem como na úlcera esofágica (HP+ =0% e HP- =0,21%). Na gastrite foi favorável ao grupo HP- (HP+ =78.34% e HP- =73.63%), assim como na gastrite erosiva (HP+ = 67,11% e HP- = 64,55%), na bulboduodenite (HP+ = 1,87% e HP- 1,23%), na úlcera gástrica (HP+ =2,14% e HP- =2,03%) e na ausência de alterações no grupo HP+ (4.81%) com o grupo controle HP- (6,30%), nos quais há pequena desproporção favorável ao grupo HP-, porém, sem significância estatística. Já quanto à úlcera bulbar (HP+ =10,16% e HP- =4,48%), houve significância estatística (p=0,00001). Conclusão: Não há diferenciação entre os grupos HP+ e HP- nas alterações endoscópicas inflamatórias na mucosa gastroduodenal, exceto para a relação entre HP e úlcera bulbar.

Polianeurismas de aorta abdominal, artérias ilíacas e artérias de membros inferiores / Polianeurysms of abdominal aorta, iliac arteries and lower limb arteries

Polianeurismas são dilatações arteriais simultâneas ou sequenciais.Neste relato, homem, 64 anos, hipertenso e dislipidêmico,histórico dealcoolismo e tabagismo, procurou atendimento com dor em flanco direito irradiada para fossa ilíaca direita. Ecografia de abdômen mostrou litíases renais e aneurismas em artérias ilíacas comuns e internas. Realizada angiorressonância que mostrou dilatações em aorta abdominal, ilíacas comuns, ilíacas internas, femorais comuns e poplíteas. Foram colocadasendopróteses em aorta abdominal e ilíacas e o paciente evoluiu com endoleak em ilíaca interna direita. Como este não regrediu espontaneamente, foi colocado stent revestido, selando o vazamento. Posteriormente,realizada aneurismectomia femoral esquerda.Atualmente, paciente em acompanhamento dos aneurismas de femoral comum direita e poplíteas. O tratamento endovascular leva à menor agressão cirúrgica e menor tempo necessário para a recuperação do paciente.Evidencia-se a importância deste trabalho ao descrever o desenvolvimento da doença, além dos procedimentos realizados para a resolução das principais dilatações.

Polianeurysms are a sequential or simultaneous arterial dilatation. This is a case report of a man, 64 years-old, hypertensive and dyslipidemic, history as alcoholism and tabagism, who sought treatment with right flank pain expanded to the right iliac fossa. Ultrasound of abdomen presented kidney lithiasis and aneurysms of iliac arteries. An angioresonace showed dilatation of abdominal aorta, iliac, femoral and popliteal arteries. Stents were placed in the aorta and iliac arteries. The patient developed an endoleak in the right iliac artery and, as it did not repair spontaneously, another stent had to be placed. Subsequently, an aneurysmectomy was performed in the left femoral artery. Currently, aneurysms at the right femoral and popliteal arteries are being monitored. Endovascular treatment leads to less surgical aggression and time for the patient´s recovery. This work is important because of its description of the disease development and the methods used to solve the main dilatations.

Variações anatômicas dos troncos supra­aórticos com subclávia esquerda originando-se de divertículo de Kommerell / Anatomical variations of the supra aortic trunks with left subclavian originating from diverticulum of Kommerell

As variações dos troncos supra-aórticos são de diversos tipos. O divertículo de Kommerell (DK) é um aneurisma aórtico incomum na origem da artéria subclávia. Neste relato, mulher, 46 anos, apresentou parestesia progressiva há 4 anos em membro superior esquerdo (MSE) ao elevá-lo. Exame físico revelou manobra de Wright positiva em MSE. Angiotomografia mostroupresença de variações anatômicas dos troncos supra-aórticos e de DK na origem da artéria subclávia esquerda (ASE). Atualmente paciente segue em acompanhamento do aneurisma. As variações dos troncos supra-aórticos do presente relato associada são DK na origem da ASE com arco aórtico esquerdo são raras.Esta patologia pode ser assintomática, apresentar sintomas de dilatação e rotura aneurismática ou sintomas relacionados à compressão de estruturas adjacentes. O diagnóstico se da com métodos de imagem pouco invasivos. O tratamento geralmente é cirúrgico. A possibilidade de intercorrências fatais impõe uma avaliação clínica e imaginológica minuciosa para abordar o melhor tratamento.

Variations of the supra aortic trunks are of several types. Kommerell diverticulum (DK) is an unusual aortic aneurysm at the origin of the subclavian artery. In this report, woman, 46 years, had progressive paresthesia for 4 years in the left upperlimb (MSE) to raise it. Physical examination revealed positive Wright maneuver in MSE. CT angiography showed the presence of anatomical variations of the supra aortic trunks and DK at the origin of the left subclavian artery (ASE). Currently, the patient keeps on monitorating the aneurysm. Variations of the supra aortic trunks of this report associated with DK at the origin of ASE with left aortic arch are rare. This condition can be asymptomatic, present symptoms of aneurysmal dilation and rupture or symptoms related tocompression of adjacent structures. Diagnosisis with the minimally invasive imaging methods. The treatment is surgical. The possibility of fatal complications imposes a thorough clinical evaluation and by imaging to offer the best treatment.

Detecção de exsudatos em imagens de retina por técnicas de morfologia matemática e agrupamento nebuloso / Exudate detection in retina images by mathematical morphology techniques and fuzzy clustering

A retinopatia diabética (RD) é uma das principais complicações do diabetes mellitus, pois causa sérios danos à retina e consequentemente à visão, podendo inclusive resultar em cegueira. O diagnóstico da RD é realizado através da análise visual de imagens de retina, sendo os exsudatos (depósitos de gordura) os principais padrões rastreados pelo médico especialista. Vale destacar que o diagnóstico precoce, realizado através do monitoramento regular, associado ao tratamento adequado apresenta inúmeros benefícios na prevenção da deficiência visual. Neste trabalho, é proposto um algoritmo de detecção de exsudatos em imagens de retina, cuja validação experimental é realizada na base pública DIARETDB1. A escolha desta base se deve à disponibilidade da localização dos exsudatos na retina, o que constitui o padrão ouro para a validação dos algoritmos. A metodologia proposta combina agrupamento nebuloso e técnicas de morfologia matemática, além de prover a detecção do disco óptico considerando que o mesmo é um ponto de convergência dos vasos. Os resultados mostraram que o método de detecção de exsudatos apresentou taxas de acerto na avaliação por imagens e por regiões na ordem de 73,03% e 99,41%, respectivamente. Estes resultados confirmam que houve uma melhoria no desempenho na detecção, quando comparados, aos resultados de métodos disponíveis na literatura.

Diabetic retinopathy (DR) is one of the major complications of diabetes mellitus and, furthermore it causes severe damage to the retina and consequently to the vision. DR may lead to blindness and therefore it is important to prevent it or early detect and treat it. The diagnosis of DR is performed by visual analysis of retinal images being exudates (fat deposits) the main patterns traced by a specialist doctor. It is noteworthy that early diagnosis, through regular monitoring when coupled with proper treatment, results in numerous benefits in the prevention of visual impairment. Thus, this paper proposes an algorithm for exudate detection in retinal images, whose experimental validation is performed on retina images of the publicly available DIARETDB1 database. The reason for choosing this database is that it provides spatial coordinates of exudates in retina images which constitute ground truths for the algorithm validation. The proposed methodology combines fuzzy clustering and mathematical morphology techniques, and thus it provides a method for optic disk detection considering that it is as the convergent point of vessels. The exudate detection method presented successful rates of 73.03% and 99.41% concerning the use of the whole image and only partial regions, respectively. These results confirm the performance improvement provided by the proposed methodology, when comparing it to other methods available in the literature.