Machine learning applications to predict two-phase flow patterns.

Recent advances in artificial intelligence with traditional machine learning algorithms and deep learning architectures solve complex classification problems. This work presents the performance of different artificial intelligence models to classify two-phase flow patterns, showing the best alternatives for this specific classification problem using two-phase flow regimes (liquid and gas) in pipes. Flow patterns are affected by physical variables such as superficial velocity, viscosity, density, and superficial tension. They also depend on the construction characteristics of the pipe, such as the angle of inclination and the diameter. We selected 12 databases (9,029 samples) to train and test machine learning models, considering these variables that influence the flow patterns. The primary dataset is Shoham (1982), containing 5,675 samples with six different flow patterns. An extensive set of metrics validated the results obtained. The most relevant characteristics for training the models using Shoham (1982) dataset are gas and liquid superficial velocities, angle of inclination, and diameter. Regarding the algorithms, the Extra Trees model classifies the flow patterns with the highest degree of fidelity, achieving an accuracy of 98.8%.

Brain and lesion segmentation in multiple sclerosis using fully convolutional neural networks: A large-scale study.

OBJECTIVE: To investigate the performance of deep learning (DL) based on fully convolutional neural network (FCNN) in segmenting brain tissues in a large cohort of multiple sclerosis (MS) patients. METHODS: We developed a FCNN model to segment brain tissues, including T2-hyperintense MS lesions. The training, validation, and testing of FCNN were based on ~1000 magnetic resonance imaging (MRI) datasets acquired on relapsing-remitting MS patients, as a part of a phase 3 randomized clinical trial. Multimodal MRI data (dual-echo, FLAIR, and T1-weighted images) served as input to the network. Expert validated segmentation was used as the target for training the FCNN. We cross-validated our results using the leave-one-center-out approach. RESULTS: We observed a high average (95% confidence limits) Dice similarity coefficient for all the segmented tissues: 0.95 (0.92-0.98) for white matter, 0.96 (0.93-0.98) for gray matter, 0.99 (0.98-0.99) for cerebrospinal fluid, and 0.82 (0.63-1.0) for T2 lesions. High correlations between the DL segmented tissue volumes and ground truth were observed (R2 > 0.92 for all tissues). The cross validation showed consistent results across the centers for all tissues. CONCLUSION: The results from this large-scale study suggest that deep FCNN can automatically segment MS brain tissues, including lesions, with high accuracy.

Tim50a, a nuclear isoform of the mitochondrial Tim50, interacts with proteins involved in snRNP biogenesis.

BACKGROUND: The Cajal body (CB) is a nuclear suborganelle involved in the biogenesis of small nuclear ribonucleoproteins (snRNPs), which are vital for pre-mRNA splicing. Newly imported Sm-class snRNPs traffic through CBs, where the snRNA component of the snRNP is modified, and then target to other nuclear domains such as speckles and perichromatin fibrils. It is not known how nascent snRNPs localize to the CB and are released from this structure after modification. The marker protein for CBs, coilin, may play a role in snRNP biogenesis given that it can interact with snRNPs and SMN, the protein mutated in Spinal Muscular Atrophy. Loss of coilin function in mice leads to significant viability and fertility problems and altered CB formation. RESULTS: In this report, we identify a minor isoform of the mitochondrial Tim50, Tim50a, as a coilin interacting protein. The Tim50a transcript can be detected in some cancer cell lines and normal brain tissue. The Tim50a protein differs only from Tim50 in that it contains an additional 103 aa N-terminal to the translation start of Tim50. Importantly, a putative nuclear localization signal is found within these 103 residues. In contrast to Tim50, which localizes to the cytoplasm and mitochondria, Tim50a is strictly nuclear and is enriched in speckles with snRNPs. In addition to coilin, Tim50a interacts with snRNPs and SMN. Competition binding experiments demonstrate that coilin competes with Sm proteins of snRNPs and SMN for binding sites on Tim50a. CONCLUSION: Tim50a may play a role in snRNP biogenesis given its cellular localization and protein interaction characteristics. We hypothesize that Tim50a takes part in the release of snRNPs and SMN from the CB.