Perceptions of clinical utility of an Augmented Reality musical software among health care professionals.

PURPOSE: Augmented Reality musical software (GenVirtual) is a technology, which primarily allows users to develop music activities for rehabilitation. This study aimed to analyse the perceptions of health care professionals regarding the clinical utility of GenVirtual. A second objective was to identify improvements to GenVirtual software and similar technologies. METHOD: Music therapists, occupational therapists, physiotherapists and speech and language therapist who assist people with physical and cognitive disabilities were enrolled in three focus groups. The quantitative and qualitative data were collected through inductive thematic analysis. RESULTS: Three main themes were identified: the use of GenVirtual in health care areas; opportunities for realistic application of GenVirtual; and limitations in the use of GenVirtual. The registration units identified were: motor stimulation, cognitive stimulation, verbal learning, recreation activity, musicality, accessibility, motivation, sonic accuracy, interference of lighting, poor sound, children and adults. CONCLUSION: This research suggested that the GenVirtual is a complementary tool to conventional clinical practice and has great potential to motor and cognitive rehabilitation of children and adults. Implications for Rehabilitation Gaining health professional' perceptions of the Augmented Reality musical game (GenVirtual) give valuable information as to the clinical utility of the software. GenVirtual was perceived as a tool that could be used as enhancing the motor and cognitive rehabilitation process. GenVirtual was viewed as a tool that could enhance clinical practice and communication among various agencies, but it was suggested that it should be used with caution to avoid confusion and replacement of important services.

Texture analysis of high resolution MRI allows discrimination between febrile and afebrile initial precipitating injury in mesial temporal sclerosis.

A computational pipeline combining texture analysis and pattern classification algorithms was developed for investigating associations between high-resolution MRI features and histological data. This methodology was tested in the study of dentate gyrus images of sclerotic hippocampi resected from refractory epilepsy patients. Images were acquired using a simple surface coil in a 3.0T MRI scanner. All specimens were subsequently submitted to histological semiquantitative evaluation. The computational pipeline was applied for classifying pixels according to: a) dentate gyrus histological parameters and b) patients' febrile or afebrile initial precipitating insult history. The pipeline results for febrile and afebrile patients achieved 70% classification accuracy, with 78% sensitivity and 80% specificity [area under the reader observer characteristics (ROC) curve: 0.89]. The analysis of the histological data alone was not sufficient to achieve significant power to separate febrile and afebrile groups. Interesting enough, the results from our approach did not show significant correlation with histological parameters (which per se were not enough to classify patient groups). These results showed the potential of adding computational texture analysis together with classification methods for detecting subtle MRI signal differences, a method sufficient to provide good clinical classification. A wide range of applications of this pipeline can also be used in other areas of medical imaging.

Establishment of the Brazilian telehealth network for paediatric oncology.

A telemedicine network has been established in Brazil to support distance medical practice in paediatric oncology. ONCONET comprises a national network of universities, research institutes and medical institutions. The system is Web-based and hosted on a high-performance computing infrastructure based on clusters of computers. It is based on open-source software, designed to provide high performance, fault tolerance and high availability. The ONCONET began operation in 2004. Currently, 30 hospitals affiliated to the Brazilian Society for Paediatric Oncology are users of the ONCONET. Six hospitals are connected by broadband access through the National Education and Research Network and 24 by conventional Internet access. The Multimedia Patients Registry also became operational in 2004, and its database contains information on 3,200 patients from the 30 hospitals. The technological platform was notable for its low production cost. It thus appears to be a sustainable solution to the problem of delivering continuing medical education in a large country with widely dispersed health professionals.

Web-based patient records and treatment guidelines in paediatric oncology.

We have established a Web-based system in Brazil offering health information in childhood cancer and services such as electronic patient records and treatment protocols. The system was based on open-source software. The database has records for about 3,200 patients from 30 Brazilian hospitals. An evaluation by doctors from the six hospitals comprising the Neuroblastoma Cooperative Group was positive, mainly because the system allows easy online access, but also because the electronic register performs data validation when information is inserted. Our experience shows that it is possible to use a Web-based system to provide paediatric cancer services at a distance.

Radial basis functions-simulated annealing classification of mammographic calcifications.

We investigated several approaches to classify mammographic calcifications as malignant or benign: a supervised classifier, multi-layer perceptron (MLP), a supervised and unsupervised classifier, a classifier based upon adaptive resonance theory with linear discriminant analysis (ART2LDA), and a classifier based upon nonlinear and combinational optimization techniques: RBF (radial basis functions)-simulated annealing. The classifiers were trained using shape factors extracted from 143 mammographic calcifications (79 malignant and 64 benign), adopting the leave-one-cut procedure. The classifiers' performance was compared in terms of the area under the ROC curve. The best result of 0.97 was obtained with RBF-simulated annealing, which was significantly better than the results obtained with MLP and ART2LDA, which were, respectively, 0.70 and 0.71.