RESUMO
INTRODUCTION: Low- to high-energy impact trauma may cause from small fissures up to extended bone losses, which can be classified as closed or opened injuries (when they are visible at a naked eye). OBJECTIVE: The aim of this study was to investigate the feasibility of clinical diagnosis of bone trauma through medical infrared thermography, in a hospital emergency room. METHODS: Forty-five patients with suspected diagnosis of bone fracture were evaluated by means of medical infrared images, and the data correlated with the gold standard radiographic images, in the anteroposterior, lateral, and oblique views, at the orthopedic emergency department. The control group consisted of thermal images of the contralateral reference limb of the volunteers themselves. Data were acquired with a medical grade infrared camera in the regions of interest (ROIs) of leg, hand, forearm, clavicle, foot, and ankle. RESULTS: In all patients evaluated with a diagnosis of bone fracture, the mean temperature of the affected limb showed a positive difference greater than 0.9 °C (towards the contralateral), indicating the exact location of the bone trauma according, while the areas diagnosed with reduced blood supply, showed a mean temperature with a negative variation. CONCLUSION: Clinical evaluation using infrared imaging indicates a high applicability potential as a tool to support quick diagnosis of bone fractures in patients with acute orthopedic trauma in an emergency medical setting. The thermal results showed important physiological data related to vascularization of the bone fracture and areas adjacent to the trauma well correlated to radiographic examinations.
Assuntos
Fraturas Ósseas , Termografia , Serviço Hospitalar de Emergência , Fraturas Ósseas/diagnóstico por imagem , Humanos , Raios Infravermelhos , Extremidade Inferior , Sensibilidade e Especificidade , Termografia/métodosRESUMO
BACKGROUND: Thermal imaging has been used as a clinical follow-up technique in several medical specialties. PURPOSE: The aim of this study was to investigate the feasibility of using medical thermography in the diagnosis and follow-up assessment of a severe orthopedic trauma that requires the use of an external circular fixator. PATIENTS AND METHODS: Twenty clinical follow-ups of thermal imaging correlated with X-ray images were performed in a male volunteer, diagnosed with bone nonunion, during 11 months of treatment, in the hospital trauma and reconstruction department. Data were acquired in the regions of interest of the proximal tibia, diaphysis and distal, with a Flir T530 medical grade infrared camera from Flir Systems®, and the data processed by the Matlab® 2019 custom made software. RESULTS: Statistical analysis was performed by Wilcoxon signed-rank test. The results showed a median temperature of 22.2°C, and thus some periods of interruption in the healing process between the third and twentieth clinical follow-up, and a significant increase of the temperature to 34.6°C synchronous with a diagnosis of bone infection by the eleventh clinical follow-up. The thermal images acquired during the 20 clinical follow-ups allow a correlation with the data from the X-ray exams and also with the contralateral limb of the evaluated patient, showing thermal alterations greater than 0.3°C, which are significant of physiological abnormality. CONCLUSION: The thermography exam can be a useful tool for applying on the follow-up of patients after trauma or bone fracture. The results showed important physiological data related to the vascularization necessary for bone repairing, being therefore a good indicator of the healing process. In addition, as infrared thermography does not use ionizing radiation, it can be used countlessly, in complement to the traditional X-ray exams that focus on anatomical data analysis.
RESUMO
Sign Language recognition systems aid communication among deaf people, hearing impaired people, and speakers. One of the types of signals that has seen increased studies and that can be used as input for these systems is surface electromyography (sEMG). This work presents the recognition of a set of alphabet gestures from Brazilian Sign Language (Libras) using sEMG acquired from an armband. Only sEMG signals were used as input. Signals from 12 subjects were acquired using a MyoTM armband for the 26 signs of the Libras alphabet. Additionally, as the sEMG has several signal processing parameters, the influence of segmentation, feature extraction, and classification was considered at each step of the pattern recognition. In segmentation, window length and the presence of four levels of overlap rates were analyzed, as well as the contribution of each feature, the literature feature sets, and new feature sets proposed for different classifiers. We found that the overlap rate had a high influence on this task. Accuracies in the order of 99% were achieved for the following factors: segments of 1.75 s with a 12.5% overlap rate; the proposed set of four features; and random forest (RF) classifiers.