Repositório RCAAP
A novel method for predicting the risk of thrombosis and thromboembolism
INTRODUCTION: Thrombosis is a complex disease that is often silent and is characterized by thrombus formation within the blood vessel. It can lead to a venous obstruction in the body, severe sequelae and even death. Thrombus formation occurs when there is reduced blood flow and/or the release of procoagulant substances caused by external factors. In Brazil, the data on this pathology are still underestimated, and its incidence is approximately 0.8 cases/1000 inhabitants per year according to the literature. The aim of this study was to develop and validate a predictive method for the risk of thrombosis or thromboembolism according to various risk factors. METHODS: This is an observational and retrospective study based on a convenience sample of records. It was approved by the Institutional Review Board (IRB) of the University Mogi das Cruzes and the Heart Hospital of the São Paulo. The sample was classified according to the risk, and the assessment of concordance was performed by determining the Kappa coefficient and accuracy. RESULTS: Of the observed patients, 23 (46%) were women, and 86% were over 45 years old. The mean age of the patients was 60.8 years. Forty-eight percent of the patients underwent surgery for more than 30 minutes. In this study, the method categorized 29 (58%) patients as moderate risk, 10 as low risk and 11 as high risk. Two cases of thrombotic disease were sufficient for validation. CONCLUSION: The use of this software as a predictive method was feasible, providing fast filling, immediate scoring, flexibility and an upgrade over previous systems. The software will not substitute for diagnosis, which is a medical competence, but it may help as a warning of risk.
2014
Leite,Katia Cristina Marques,Ricardo Henrique
Computational neuroscience in perspective
No summary/description provided
2014
Almeida,Antônio-Carlos Guimarães de Rodrigues,Antônio Márcio Infantosi,Antonio Fernando Catelli
Lung disease detection using feature extraction and extreme learning machine
INTRODUCTION: The World Health Organization estimates that by 2030 the Chronic Obstructive Pulmonary Disease (COPD) will be the third leading cause of death worldwide. Computerized Tomography (CT) images of lungs comprise a number of structures that are relevant for pulmonary disease diagnosis and analysis. METHODS: In this paper, we employ the Adaptive Crisp Active Contour Models (ACACM) for lung structure segmentation. And we propose a novel method for lung disease detection based on feature extraction of ACACM segmented images within the cooccurrence statistics framework. The spatial interdependence matrix (SIM) synthesizes the structural information of lung image structures in terms of three attributes. Finally, we perform a classification experiment on this set of attributes to discriminate two types of lung diseases and health lungs. We evaluate the discrimination ability of the proposed lung image descriptors using an extreme learning machine neural network (ELMNN) comprising 4-10 neurons in the hidden layer and 3 neurons in the output layer to map each pulmonary condition. This network was trained and validated by applying a holdout procedure. RESULTS: The experimental results achieved 96% accuracy demonstrating the effectiveness of the proposed method on identifying normal lungs and diseases as COPD and fibrosis. CONCLUSION: Our results lead to conclude that the method is suitable to integrate clinical decision support systems for pulmonary screening and diagnosis.
2014
Ramalho,Geraldo Luis Bezerra Rebouças Filho,Pedro Pedrosa Medeiros,Fátima Nelsizeuma Sombra de Cortez,Paulo César
Effectiveness of ozonated water in the reprocessing of blood dialyzers
INTRODUCTION: Ozone is a potent antibacterial agent. Because ozone oxidizes organic material, it directly attacks microorganisms resulting in safe, fast and economical sterilization at low temperatures. This study evaluated the efficacy of ozonated water in the reprocessing of dialyzers obtained from a hemodialysis service in São José do Rio Preto. METHODS: A total of 23 blood dialyzers were collected at the conclusion of the morning hemodialysis shift. The equipment was collected after the maximum number of reuses, with the last disinfection performed with purified water (obtained by reverse osmosis and subsequent reverse ultrafiltration). The number and species of microorganisms in the dialyzers were evaluated before and after treatment with ozonated water. The ozonation of sterile deionized water was achieved by direct contact between the water and the ozone generating equipment. RESULTS:The mean number of microorganisms before sterilization was 1,47.10(9) colony forming units per ml (CFU/ml). After treatment with ozonated water, the number of microorganisms was 4,80.10¹ CFU/ml. CONCLUSION: Ozonated water is an effective decontaminant for most blood dialyzers.
2014
Canada,Morian Lauana Miguelão Abelan,Ursulandrea Sanches Zangaro,Renato Amaro Kozusny-Andreani,Dora Inês Yamazaki,Roseli de Fátima Custódio
Assessment of walker-assisted gait based on Principal Component Analysis and wireless inertial sensors
INTRODUCTION:This study investigates a gait research protocol to assess the impact of a walker model with forearm supports on the kinematic parameters of the lower limb during locomotion. METHODS: Thirteen healthy participants without any history of gait dysfunction were enrolled in the experimental procedure. Spatiotemporal and kinematic gait parameters were calculated by using wireless inertial sensors and analyzed with Principal Component Analysis (PCA). The PCA method was selected to achieve dimension reduction and evaluate the main effects in gait performance during walker-assisted gait. Additionally, the interaction among the variables included in each Principal Component (PCs) derived from PCA is exposed to expand the understanding of the main differences between walker-assisted and unassisted gait conditions. RESULTS:The results of the statistical analysis identified four PCs that retained 65% of the data variability. These components were associated with spatiotemporal information, knee joint, hip joint and ankle joint motion, respectively. CONCLUSION: Assisted gait by a walker model with forearm supports was characterized by slower gait, shorter steps, larger double support phase and lower body vertical acceleration when compared with normal, unassisted walking.
2014
Martins,Maria Elias,Arlindo Cifuentes,Carlos Alfonso,Manuel Frizera,Anselmo Santos,Cristina Ceres,Ramón
Digital controller design considering hardware constraints: application in a paraplegic patient
INTRODUCTION: A methodology was developed for implementing closed-loop control algorithms and for evaluating the behavior of a system, considering certain component restrictions used in laboratory implementation. METHODS: Mathematical functions representing a model of the biological system were used for knee extension/flexion movements. A Proportional Integral Derivative (PID) controller and another one using the root locus method were designed to control a patient’s leg position by applying functional electrical stimulation (FES). The controllers were simulated in Matlab and ISIS Proteus. After the simulations were performed, the codes were embedded in a microcontroller, and tests were conducted on a paraplegic volunteer. To the best of the authors’ knowledge, this is the first time that ISIS Proteus software resources have been used prior to implementing a closed-loop system designed to control the leg position of patients. RESULTS:This method obviates the application of initial controller tests directly to patients. The response obtained in the experiment with a paraplegic patient complied with the specifications set in terms of the steady-state error, the settling time, and the percentage overshoot. The proposed procedure was successfully applied for the implementation of a controller used to control the leg position of a paraplegic person by electrical muscle stimulation. CONCLUSION:The methodology presented in this manuscript can contribute to the implementation of analog and digital controllers because hardware limitations are typically not taken into account in the design of controllers.
2014
Sanches,Marcelo Augusto Assunção Gaino,Ruberlei Kozan,Renan Fernandes Teixeira,Marcelo Carvalho Minhoto Carvalho,Aparecido Augusto de Covacic,Márcio Roberto Alves,Carlos Antonio Urban,Mateus Fernandes Réu Junqueira,Marcos Vinícius Nascimento Cardim,Rodrigo Assunção,Edvaldo Gentilho Junior,Edno
Evaluation of nuclear magnetic resonance spectroscopy variability
INTRODUCTION: The intrinsically high sensitivity of Magnetic Resonance Spectroscopy (MRS) causes considerable variability in metabolite quantification. In this study, we evaluated the variability of MRS in two research centers using the same model of magnetic resonance image scanner. METHODS: Two metabolic phantoms were created to simulate magnetic resonance spectra from in vivo hippocampus. The phantoms were filled with the same basic solution containing the following metabolites: N-acetyl-aspartate, creatine, choline, glutamate, glutamine and inositol. Spectra were acquired over 15 months on 26 acquisition dates, resulting in a total of 130 spectra per center. RESULTS: The phantoms did not undergo any physical changes during the 15-month period. Temporal analysis from both centers showed mean metabolic variations of 3.7% in acquisitions on the same day and of 8.7% over the 15-month period. CONCLUSION: The low deviations demonstrated here, combined with the high specificity of Magnetic Resonance Spectroscopy, confirm that it is feasible to use this technique in multicenter studies in neuroscience research.
2014
Barreto,Felipe Rodrigues Otaduy,Maria Concepción García Salmon,Carlos Ernesto Garrido
Three-dimensional analysis of an orthodontic delta spring
INTRODUCTION: The purpose of this study was to analyze the force system, moment-force ratios (M/F) and von Mises stresses in an orthodontic delta spring using a 3D finite element model. The M/F ratio produced by an orthodontic spring is related to the different types of tooth movement that are likely to occur in the sagittal and occlusal planes. METHODS: Analyses were performed using a 3D finite element model, and a data acquisition system was used to validate the numerical results. RESULTS: Reactive forces between 0.0 and 2.0 N were observed along the x-axis, while null values were observed along the y- and z-axes. The maximum activation that ensured geometric stability and mechanical stresses below the elastic limit of the material was 10.0 mm. CONCLUSION: The results indicate that a delta spring can provide (i) uncontrolled tipping for activation of less than 1.0 mm; (ii) controlled counterclockwise tipping for activation between 1.0 and 4.5 mm; (iii) translation for activation between 4.5 and 5.0 mm; and (iv) controlled clockwise tipping in the sagittal plane for activation between 5.0 and 10.0 mm. No tooth movement was observed in the occlusal plane for the M/F ratios observed.
2014
Rodrigues,Fábio Rodrigo Mandello Borges,Paulo César Luersen,Marco Antônio Ferreira,Marcelo do Amaral
Corrosion and microstructural characterization of martensitic stainless steels submitted to industrial thermal processes for use in surgical tools
INTRODUCTION: The mechanical properties and corrosion resistance of a material are dependent on its microstructure and can be modified by phase transformation. When a phase transformation occurs in a material it usually forms at least one new phase, with physical-chemical characteristics that differ from the original phase. Moreover, most phase transformations do not occur instantly. This paper presents an evaluation of the phase transformation of martensitic stainless steels ASTM 420A and ASTM 440C when submitted to different thermal processes. METHODS: Dilatometry tests were performed with several continuous heating and cooling rates in order to obtain the profiles of the continuous heating transformation (CHT) and continuous cooling transformation (CCT) diagrams for these two types of steel. Also, the temperature ranges for the formation of the different phases (ferrite and carbides; ferrite; austenite and carbides; non-homogeneous and homogeneous austenite phases) were identified. Rockwell hardness (HRC) tests were performed on all thermally treated steels. Anodic and cathodic potential dynamic polarization measurements were carried out through immersion in enzymatic detergent as an electrolyte for different samples submitted to the thermal processes in order to select the best routes for the heat treatment and to recommend steels for the manufacture of surgical tools. RESULTS: The martensitic transformation temperature tends to increase with increasing temperature for the initiation of cooling. The 440C steel had a higher hardness value than the 420A steel at the austenitizing temperature of 1100 °C. Above the austenitizing temperature of 1100 °C, the material does not form martensite at the cooling rate used, which explains the sharp decline in the hardness values. CONCLUSION: The study reported herein achieved its proposed objectives, successfully investigating the issues and indicating solutions to the industrial problems addressed, which are frequently encountered in the manufacture of surgical instruments.
2014
Marcuci,José Renato Jatobá Souza,Elki Cristina de Camilo,Claudia Cristiane Di Lorenzo,Pedro Luiz Rollo,João Manuel Domingos de Almeida
Manufacture of custom-made cranial implants from DICOM® images using 3D printing, CAD/CAM technology and incremental sheet forming
INTRODUCTION: This work aims to pre-operatively manufacture custom-made low-cost implants and physical models (‘biomodels’) of fractured skulls. The pre-DOI: operative manufacturing of biomodels and implants allows physicians to study and plan surgery with a greater possibility of achieving the expected result. Customization contributes to both the esthetic and functional outcome of the implant because it considers the anatomy of each patient, while the low cost allows a greater number of people to potentially benefit. METHODS: From CT images of a fractured skull, a CAD model of the skull (biomodel) and a restorative implant were constructed digitally. The biomodel was then physically constructed with 3D Printing, and Incremental Sheet Forming (ISF) was used to manufacture the implant from a sheet of pure grade 2 titanium. Before cutting the implant’s final shape from a pre-formed sheet, heat treatment was performed to avoid deformations caused by residual stresses generated during the ISF process. RESULTS: A comparison of the dimensions of the implant and its respective CAD biomodel revealed geometric discrepancies that can affect both functional and aesthetic efficiency. Nevertheless, the final shape preserved symmetry between the right and left sides of the skull. Electron microscopy analysis did not indicate the presence of elements other than pure titanium. CONCLUSION: Dimensional variability can be decreased with changes in the manufacturing process (i.e., forming and cutting) and the heating ramp. Despite biomedical characteristics, there was no contamination of the implant by harmful chemical elements. 3D Printing was effective in making the biomodel, enabling pre-operative planning and improving physician-patient communication. Current results indicate that ISF is a process that can be used to obtain custom-made implants.
2014
Castelan,Jovani Schaeffer,Lirio Daleffe,Anderson Fritzen,Daniel Salvaro,Vanessa Silva,Fábio Pinto da
Is it possible to identify the gender and age group of adults from gait analysis with hip-knee cyclograms?
INTRODUCTION: Cyclograms are gait analysis tools that characterize the geometric aspect of the pattern of locomotion. Cyclograms are angle-angle diagrams that are very useful for representing cyclic patterns such as walking. This study is based on the hypothesis that parameters extracted from hip-knee cyclograms of individuals walking on a treadmill with 0° and 5° slopes can be used to determine the age group and sex of the volunteers. METHODS: In total, 40 physically active healthy adult volunteers, 20 young people (10 of each gender) and 20 elderly (10 of each gender), were divided into 4 groups, and the average value of area (A), perimeter (P) and the ratio P/√A of cyclogram were calculated, as well as the speed and cadence. RESULTS: The young male (YM) speeds were higher than the elderly male (EM) speeds (p=0.00), and the young female (YF) speeds were higher than the elderly female (EF) speeds (p=0.00). No difference in speed was found between YM and YF (p=0.59) or between EM and EF (p=0.95). The parameters extracted directly from the cyclogram allowed us to distinguish the studied groups according to age group (p<0.05), especially with the treadmill inclined at 5°, but it was not enough to determine gender (p>0.51). CONCLUSION: The hypothesis was partially confirmed because parameters extracted from the hip-knee cyclograms could differentiate volunteers by age group but not gender.
2014
Abreu,Ródney Silva Naves,Eduardo Lázaro Martins Caparelli,Thiago Bruno Mariano,Daniel Teodoro Gonçalves Dionísio,Valdeci Carlos
A mass-spring model of the auditory system in otosclerosis
INTRODUCTION: This paper aims to describe a model to simulate otosclerosis using a mass-spring model and to correlate the results with the clinical and audiological data on the disease. METHODS: A mass-spring model was used to represent the behavior of the auditory system simulating otosclerosis. The model consisted of six masses (air volume in the external auditory canal; tympanic membrane; malleus; incus; stapes, and cochlear fluid), springs and dashpots simulating the supporting ligaments and muscles. The parameters to simulate the disease were obtained from the literature; stapedial annular ligament stiffness was increased by 10-fold and to 100-fold and stapes mass increased by 5-fold. RESULTS: There was a decrease in stapes displacement in the lower frequencies when the stiffness of the stapedial annular ligament was increased. It was also found a reduction in stapes displacement in the higher frequencies with increased stapes mass. CONCLUSION:The increased stiffness of the stapedial annular ligament can be an indication of early stage disease, whereas increased bone growth suggests disease progression. The results of the simulation are in agreement with the clinical and audiological disease and support the need for further study of the stapedial annular ligament to find ways to evaluate its functioning and thus enable early detection of hearing losses caused by changes in that structure.
2014
Fragoso,Lygia Bueno Magalhães,Max de Castro Las Casas,Estevam Barbosa de Santos,Juliana Nunes Rabelo,Alessandra Terra Vasconcelos Oliveira,Rafaella Cristina
Measurement and evaluation of human exposure to vibration transmitted to hand-arm system during leisure cyclist activity
INTRODUCTION: The cycling activity has increased in recent years, either as a means of leisure or physical activity or as means of transport. Discomfort is one of the main complaints for cyclists, especially when related to the type o pavement they use while riding. This work presents a study of measurement and evaluation of human exposure to hand-arm vibration in the leisure cyclist activity in different pavements in order to classify according to vibration discomfort and to vibration injury risk. METHODS: Vibration measurements are performed for three pavement types, asphalt (AS), precast concrete slab (PC), and interlocking concrete blocks (BI), using two bicycle models (time trial speed racing bike, S and mountain bike, MB), and cyclists with different physical characteristics. It is performed a quantitative analysis of each configuration - pavement type × bike model × cyclist - where the daily vibration exposure A(8) is evaluated, as defined in ISO 5349-1 Standard, for 2h daily exposure. It is also evaluated the maximum daily exposure in order to reach limit values, as defined by Directive 2002/44/EC. RESULTS: Based on a subjective analysis (survey), it is evaluated the comfort degree for vibration exposure for each tested pavement, according to a survey within cyclists. Finally, the results are compared using both quantitative and subjective analysis. CONCLUSIONS: Not surprisingly, it has been noticed that the most comfortable pavement type is the asphalt pavement (AS), followed by the precast concrete pavement (PC) and by the interlocking concrete blocks pavement (BI), confirming the opinion pool within cyclists. As a new finding, for some pavement types, bikes and daily journey activities, the vibration levels may reach health limit levels which justify the originality of the work and the importance as guidance for healthy public decisions for new cycle paths.
2014
Gomes,Herbert Martins Savionek,Daniel
Proposing the novelty classifier for face recognition
INTRODUCTION: Face recognition, one of the most explored themes in biometry, is used in a wide range of applications: access control, forensic detection, surveillance and monitoring systems, and robotic and human machine interactions. In this paper, a new classifier is proposed for face recognition: the novelty classifier. METHODS: The performance of a novelty classifier is compared with the performance of the nearest neighbor classifier. The ORL face image database was used. Three methods were employed for characteristic extraction: principal component analysis, bi-dimensional principal component analysis with dimension reduction in one dimension and bi-dimensional principal component analysis with dimension reduction in two directions. RESULTS: In identification mode, the best recognition rate with the leave-one-out strategy is equal to 100%. In the verification mode, the best recognition rate was also 100%. For the half-half strategy, the best recognition rate in the identification mode is equal to 98.5%, and in the verification mode, 88%. CONCLUSION: For face recognition, the novelty classifier performs comparable to the best results already published in the literature, which further confirms the novelty classifier as an important pattern recognition method in biometry.
2014
Costa Filho,Cicero Ferreira Fernandes Falcão,Thiago de Azevedo Costa,Marly Guimarães Fernandes Pereira,José Raimundo Gomes
Study of muscle fatigue in isokinetic exercise with estimated conduction velocity and traditional electromyographic indicators
INTRODUCTION: In the study of human biomechanics, it is often desirable to evaluate fatigue in the muscles that are involved in performing a particular task. Identifying the phenomena responsible for this condition is a problem that in most cases is complex and requires appropriate research mechanisms. Isokinetic dynamometry (ID) and surface electromyography (SEMG) are two techniques widely used in studies on strength and muscle fatigue. Their effectiveness is conditioned upon a good understanding of their limitations and the adoption of procedures to fully exploit the potential of each one. The main goal of the present study is to verify whether the electromyographic parameters, especially the conduction velocity (CV), are sensitive to the fatigue instauration process within sets of maximal isokinetic contractions. CV is a basic physiological parameter directly related to muscle activity and still little explored in experiments combining ID and SEMG. METHODS: Instrumentation architecture that combines ID and SEMG was used to estimate electromyographic and biomechanical parameters in protocols of maximum intensity isokinetic knee extension exercises. This architecture allows for limiting the parameter estimates to a specific region of isokinetic exercise, called the isokinetic load range (ILR), where one can consider that the angular velocity is constant and the SEMG signals are cyclo-stationary. Electromyographic signals were acquired using an array of electrodes. CONCLUSION: The results suggest that CV and the other SEMG parameters, including amplitude and frequency descriptors, are sensitive to detect a fatigue process only in protocols that restrict the analysis to ILR and that also bring the subject to a state of fatigue quickly.
2014
Schwartz,Fabiano Peruzzo Bottaro,Martim Celes,Rodrigo Souza Pereira,Maria Claudia Rocha Júnior,Valdinar de Araújo Nascimento,Francisco Assis de Oliveira
Robust evaluation of time since awakening using force platform posturography
INTRODUCTION: Sleepiness is responsible for a considerable proportion of traffic accidents. It is thus an important traffic safety issue to find a robust, objective and practical way to estimate the amount of time a person has been awake. To attempt to meet this goal, we investigated the relationship between sleepiness and posture control. METHODS: Subjects were kept awake for 36 hours and posturographic data during quiet standing were collected every two hours by means of a force platform. The standing surface (rigid surface or foam surface) and visual (eyes open or eyes closed) conditions were manipulated. RESULTS: In the more challenging conditions (with foam surface and/or eyes closed), the body sway variables derived from the center of the pressure measurement increased significantly when time since awakening became greater than 21 h in almost all subjects. CONCLUSION: Based on this result, we propose a practical protocol that could robustly assess whether time since awakening was greater than 21 h.
2014
Pham,Quang-Cuong Mello,Marco Túlio de Narciso,Fernanda Veruska Mônico Neto,Marcos Teixeira,Cristiane Westin Antonietti,Leandro Stetner Garbuio,Silvério Aparecido Fernandes Júnior,Sílvio de Araújo Koyama,Renata Guedes Duarte,Marcos Tufik,Sérgio
Impact evaluation of the geometry on measurements of solid radioactive waste exposure rates in nuclear medicine
INTRODUCTION: The objective of this paper is to verify the influence of the source geometry on Geiger Müller (GM) exposure rate data. This paper presents a validation of an application based on Monte Carlo (MC) data simulated using Geant4, based on a comparison of the exposure rates calculated via MC and Deterministic Calculations (DC) to experimental (measured) exposure rates. METHODS: Experimental data that were collected through measurements of standard sources were used for MC and DC validation. In addition, the best method of analyzing the impact of the real source geometry on calculations of a descarpack box of radioactive waste was verified. Furthermore, were estimated the exposure rates from a homogeneous solid waste box (used at clinical sites) and from a point source. These results were compared to confirm possible discrepancies related to source geometry in exposure rates collected using a GM detector. RESULTS: The investigated estimation methods were statistically compared; the MC presented higher agreement with the experimental data than did the deterministic calculations. The impact of considering a point source instead of the real geometry (descarpack box) was an underestimation of between 20% and 70%, depending on the source - detector distance and the isotope evaluated. CONCLUSION: The DC always presented a higher difference with respect to the experimental data than did the MC calculation. The use of realistic geometry proved to exert a significant impact on the exposure rate data for solid radioactive waste compared with the exposure rate induced by a point source; the exposure rate estimation obtained using the real geometry was always at least 16% higher than the estimation obtained for a point source, and some differences greater than 50% were found.
2014
Brambilla,Cláudia Régio Hoff,Gabriela
Automatic segmentation and classification of blood components in microscopic images using a fuzzy approach
INTRODUCTION: Automatic detection of blood components is an important topic in the field of hematology. Segmentation is an important step because it allows components to be grouped into common areas and processed separately. This paper proposes a method for the automatic segmentation and classification of blood components in microscopic images using a general and automatic fuzzy approach. METHODS: During pre-processing, the supports of the fuzzy sets are automatically calculated based on the histogram peaks in the green channel of the RGB image and the Euclidean distance between the leukocyte nuclei centroids and the remaining pixels. During processing, fuzzification associates the degree of pertinence of the gray level of each pixel in the regions defined in the histogram with the proximity of the leukocyte nucleus centroid closest to the pixel. The fuzzy rules are then applied, and the image is defuzzified, resulting in the classification of four regions: leukocyte nuclei, leukocyte cytoplasm, erythrocytes and blood plasma. In post-processing, false positives are reduced and the leukocytes (including the nucleus and cytoplasm), erythrocytes and blood plasma are segmented. RESULTS: A total of 530 microscopic images of blood smears were processed, and the results were compared with the results of manual segmentation by experts and the accuracy rates of other approaches. CONCLUSION: The method demonstrated average accuracy rates of 97.31% for leukocytes, 95.39% for erythrocytes and 95.06% for blood plasma, avoiding the limitations found in the literature and contributing to the practice of the segmentation of blood components.
2014
Vale,Alessandra Mendes Pacheco Guerra Guerreiro,Ana Maria Guimarães Dória Neto,Adrião Duarte Cavalvanti Junior,Geraldo Barroso Leitão,Victor Cezar Lucena Tavares de Sá Martins,Allan Medeiros
A systematic review on the evaluation and characteristics of computer-aided diagnosis systems
INTRODUCTION: One of the challenges in developing Computer-Aided Diagnosis (CAD) systems is their accurate and comprehensive assessment. This paper presents the conduction and results of a systematic review (SR) that aims to verify the state of the art regarding the assessment of CAD systems. This survey provides a general analysis of the current status of the design, development and assessment of such systems and includes discussions on the most used metrics and approaches that could be utilized to obtain more objective evaluation methods. METHODS: The SR was conducted using the scientific databases, ACM Digital Library, IEEE Xplore Digital Library, ScienceDirect and Web of Science. Inclusion and exclusion criteria were defined and applied to each retrieved work to select those of interest. From 156 studies retrieved, 100 studies were included. Results: There is a number of abnormalities that have been used for the development of CAD systems. Images from computed tomographies and mammographies are the most encountered types of medical images. Additionally, a number of studies used public databases for CAD evaluations. The main evaluation metrics and methods applied to CAD systems include sensitivity, accuracy, specificity and receiver operating characteristic (ROC) analyses. In the assessed CAD systems that used the segmentation method, 30.0% applied the overlap measure. DISCUSSION: There remain several topics to explore for the assessment of CAD schemes. While some evaluation metrics are traditionally used, they require a prior knowledge of case characteristics to test CAD systems. We were not able to identify articles that use software testing to evaluate CAD systems. Thus, we realize that there is a gap between CAD assessments and traditional practices of software engineering. However, the scope of this research is limited to scientific and academic works and excludes commercial interests. Finally, we discuss potential research studies within this scope to create a more objective and efficient evaluation of CAD systems.
2014
Gonçalves,Vagner Mendonça Delamaro,Márcio Eduardo Nunes,Fátima de Lourdes dos Santos
Advances and perspectives of mechanomyography
INTRODUCTION: The evaluation of muscular tissue condition can be accomplished with mechanomyography (MMG), a technique that registers intramuscular mechanical waves produced during a fiber's contraction and stretching that are sensed or interfaced on the skin surface. OBJECTIVE: Considering the scope of MMG measurements and recent advances involving the technique, the goal of this paper is to discuss mechanomyography updates and discuss its applications and potential future applications. METHODS: Forty-three MMG studies were published between the years of 1987 and 2013. RESULTS: MMG sensors are developed with different technologies such as condenser microphones, accelerometers, laser-based instruments, etc. Experimental protocols that are described in scientific publications typically investigated the condition of the vastus lateralis muscle and used sensors built with accelerometers, third and fourth order Butterworth filters, 5-100Hz frequency bandpass, signal analysis using Root Mean Square (RMS) (temporal), Median Frequency (MDF) and Mean Power Frequency (MPF) (spectral) features, with epochs of 1 s. CONCLUSION: Mechanomyographic responses obtained in isometric contractions differ from those observed during dynamic contractions in both passive and functional electrical stimulation evoked movements. In the near future, MMG features applied to biofeedback closed-loop systems will help people with disabilities, such as spinal cord injury or limb amputation because they may improve both neural and myoelectric prosthetic control. Muscular tissue assessment is a new application area enabled by MMG; it can be useful in evaluating the muscular tonus in anesthetic blockade or in pathologies such as myotonic dystrophy, chronic obstructive pulmonary disease, and disorders including dysphagia, myalgia and spastic hypertonia. New research becomes necessary to improve the efficiency of MMG systems and increase their application in rehabilitation, clinical and other health areas.
2014
Krueger,Eddy Scheeren,Eduardo Mendonça Nogueira-Neto,Guilherme Nunes Button,Vera Lúcia da Silveira Nantes Nohama,Percy