Development of a Biomechanical Device for Parameter Quantification Associated with the Sit-to-Stand Movement.

The "sit-to-stand" (STS) movement is essential during activities of daily living (ADL). In individuals with physical-motor diseases, its execution and repetition increases activity levels, which is crucial for a good motor rehabilitation process and daily training. Interestingly, there are no sit-to-stand devices that allow a quantitative assessment of the key variables that happen during STS, and there is a need to come up with a new device. This work presents a developed biomechanical support device that measures the force of the upper limbs during the STS movement, aiming to motivate and encourage people undergoing physical therapy in the lower limbs. The device uses two instrumented beams and allows real-time visualization of both arms' applied force and it records the data for post-processing. The device was tested with a well-defined protocol on a group of 34 healthy young volunteers and an elderly group of 16 volunteers from a continuing care unit. The system showed robust strength and stiffness, good usability, and a user interface that acquired and recorded data effectively, allowing one to observe force-time during the execution of the movement through the application interface developed and in recording data for post-processing. Asymmetries in the applied forces in the STS movement between the upper limbs were identified, particularly in volunteers of the continuing care unit. From the application and the registered data, it can be observed that volunteers with motor problems in the lower limbs performed more strength in their arms to compensate. As expected, the maximum average strength of the healthy volunteers (both arms: force = 105 Newton) was higher than that of the volunteers from the continuing care unit (right arm: force = 54 Newton; left arm: force = 56 Newton). Among others, moderate correlations were observed between weight-applied and height-applied forces and there was a moderately high correlation between the Sequential Clinical Assessment of Respiratory Function (SCAR-F score) and time to perform the movement. Based on the obtained results, the developed device can be a helpful tool for monitoring the evaluation of a patient with limitations in the upper and lower limbs. In addition, the developed system allows for easy evolution, such as including a barometric platform and implementing serious games that can stimulate the execution of the STS movement.

Brain Tumour Segmentation based on Extremely Randomized Forest with high-level features.

Gliomas are among the most common and aggressive brain tumours. Segmentation of these tumours is important for surgery and treatment planning, but also for follow-up evaluations. However, it is a difficult task, given that its size and locations are variable, and the delineation of all tumour tissue is not trivial, even with all the different modalities of the Magnetic Resonance Imaging (MRI). We propose a discriminative and fully automatic method for the segmentation of gliomas, using appearance- and context-based features to feed an Extremely Randomized Forest (Extra-Trees). Some of these features are computed over a non-linear transformation of the image. The proposed method was evaluated using the publicly available Challenge database from BraTS 2013, having obtained a Dice score of 0.83, 0.78 and 0.73 for the complete tumour, and the core and the enhanced regions, respectively. Our results are competitive, when compared against other results reported using the same database.