Recent machine learning advancements in sensor-based mobility analysis: Deep learning for Parkinson's disease assessment.

The development of wearable sensors has opened the door for long-term assessment of movement disorders. However, there is still a need for developing methods suitable to monitor motor symptoms in and outside the clinic. The purpose of this paper was to investigate deep learning as a method for this monitoring. Deep learning recently broke records in speech and image classification, but it has not been fully investigated as a potential approach to analyze wearable sensor data. We collected data from ten patients with idiopathic Parkinson's disease using inertial measurement units. Several motor tasks were expert-labeled and used for classification. We specifically focused on the detection of bradykinesia. For this, we compared standard machine learning pipelines with deep learning based on convolutional neural networks. Our results showed that deep learning outperformed other state-of-the-art machine learning algorithms by at least 4.6 % in terms of classification rate. We contribute a discussion of the advantages and disadvantages of deep learning for sensor-based movement assessment and conclude that deep learning is a promising method for this field.

Refractive effects on optical measurement of alveolar volume: a 2-D ray-tracing approach.

Lung imaging and assessment of alveoli geometry in the lung tissue is of great importance. Optical coherence tomography (OCT) is a real-time imaging technique used for this purpose, based on near-infrared interferometry, that can image several layers of distal alveoli in the lung tissue. The OCT measurements use low coherence interferometry, where light reflections from surfaces in the tissue are used to construct 2D images of the tissue. OCT images provide better depth compared to other optical microscopy techniques such as confocal reflectance and two-photon microscopy. Therefore, it is important to detect and verify optical distortions that happens with OCT, including refractive effect at the tissue-air alveoli wall interface which is not taken into account in the OCT imaging model. In this paper, the refractive effect at the tissue-air interface of the alveoli wall is modeled using exact ray tracing and direct implementation of Snell's law, and differences between alveoli area computed from OCT imaging and those measured by exact ray tracing of the OCT signal are analyzed.

Pixel-based comparison of spinal cord MR diffusion anisotropy with axon packing parameters.

Water diffusion in nerve fibers is strongly influenced by axon architecture. In this study, fractional diffusion anisotropy and transverse and longitudinal diffusion coefficients were measured in excised human cervical spinal cord with MR line-scan diffusion imaging, at 625 microm in-plane resolution and 3 mm slice thickness. A pixel-based comparison of fractional diffusion anisotropy, transverse diffusion coefficient, and longitudinal diffusion coefficient data with axon packing parameters derived from corresponding stained histological sections was performed for four slices. The axon packing parameters, axon density, axon area-fraction, and average axon size for entire specimen cross-sections were calculated by computerized segmentation of optical microscopy data obtained at 0.53 microm resolution. Salient features could be recognized on fractional diffusion anisotropy, transverse diffusion coefficient, axon density, axon area fraction, and average axon size maps. For white matter regions only, the average correlation coefficients for fractional diffusion anisotropy compared to histology-based parameters axon density and axon area fraction were 0.37 and 0.21, respectively. For transverse diffusion coefficient compared to axon density and axon area fraction, they were -0.40 and -0.36, and for longitudinal diffusion coefficient compared to axon density and axon area fraction, -0.14 and -0.30. All average correlation coefficients for average axon size were low. Correlation coefficients for collectively analyzed white and gray matter regions were significantly higher than correlation coefficients derived from analysis of white matter regions only.