Although feature tracking is a promising tool, there are still discrepancies in the results obtained using different software packages. This highlights a clear need for standardization of MRI acquisition parameters and feature tracking analysis methodologies. Validation, including physical and numerical phantoms, is still required to facilitate the use of feature tracking in routine clinical practice.

Obstructive Sleep Apnoea (OSA) is a breathing disorder that happens during sleep and general anaesthesia. This disorder can affect human life considerably. Early detection of OSA can protect human health from different diseases including cardiovascular diseases which may lead to sudden death. OSA is examined by physicians using Electrocardiography (ECG) signals, Electromyogram (EMG), Electroencephalogram (EEG), Electrooculography (EOG) and oxygen saturation. Previous studies of detecting OSA are focused on using feature engineering where a specific number of features from ECG signals are selected as an input to the machine learning model. In this study, we focus on detecting OSA from ECG signals where our proposed machine learning methods automatically extract the input as features from ECG signals. We proposed three architectures of deep learning approaches in this study: CNN, CNN with LSTM and CNN with GRU. These architectures utilized consecutive R interval and QRS complex amplitudes as inputs. Thirty-five recordings from PhysioNet Apnea-ECG database have been used to evaluate our models. Experimental results show that our architecture of CNN with LSTM performed best for OSA detection. The average classification accuracy, sensitivity and specificity achieved in this study are 89.11%, 89.91% and 87.78% respectively.

No abstract

Almutairi et al.: A comparison of cardiac motion analysis software packages: application to left ventricular deformation analysis in healthy subjects.

We developed new composites for photons shielding applications. The composite were prepared with epoxy resin, red clay and bismuth oxide nanoparticles (Bi2O3 NPs). In order to establish which ratio of red clay to Bi2O3 NPs provides the best shielding capabilities, several different ratios of red clay to Bi2O3 NPs were tested. The transmission factor (TF) was calculated for two different thicknesses of each sample. From the TF data, we found that epoxy resin materials have a high attenuation capacity at low energy. For ERB-10 sample (40%Epoxy + 50% Red clay + 10% Bi2O3 NPs), the TF values are 52.3% and 14.3% for thicknesses of 0.5 and 1.5 cm (at 0.06 MeV). The composite which contains the maximum amount of Bi2O3 nanoparticles (40%Epoxy + 50% Red clay + 10% Bi2O3 NPs, coded as ERB-30) has lower TF than the other composites. The TF data demonstrated that ERB-30 is capable of producing more effective attenuation from gamma rays. We also determined the linear attenuation coefficient (LAC) for the prepared composites and we found that the LAC increases for a given energy in proportion to the Bi2O3 NPs ratio. For the ERB-0 (free Bi2O3 NPs), the LAC at 0.662 MeV is 0.143 cm−1, and it increases to 0.805 cm−1 when 10% of Bi2O3 NPs is added to the epoxy resin composite. The half value layer (HVL) results showed that the thickness necessary to shield that photons to its half intensity can be significantly lowered by increasing the weight fraction of the Bi2O3 NPs in the epoxy resin composite from 0 to 30%. The HVL for ERB-20 and ERB-30 were compared with other materials such as (Epoxy as a matrix material and Al2O3, Fe2O3, MgO and ZrO2 as filler oxides in the matrix at 0.662 MeV. The HVL values for ERB-20 and ERB-30 are 4.385 and 3.988 cm and this is lower than all the selected epoxy polymers.