Comparison of wavelet transformations to enhance convolutional neural network performance in brain tumor segmentation.

INTRODUCTION AND GOAL TO BACKGROUND: Due to the importance of segmentation of MRI images in identifying brain tumors, various methods including deep learning have been introduced for automatic brain tumor segmentation. On the other hand, using a combination of methods can improve their performance. Among them is the use of wavelet transform as an auxiliary element in deep networks. The analysis of the requirements of such combinations has been addressed in this study. METHOD: In this developmental study, different wavelet functions were used to compress brain MRI images and finally as an auxiliary element in improving the performance of the convolutional neural network in brain tumor segmentation. RESULTS: Based on the results of the tests performed, the Daubechies1 function was most effective in enhancing network performance in segmenting MRI images and was able to balance the performance and computational overload. CONCLUSION: Choosing the wavelet function to optimize the performance of a convolutional neural network should be based on the requirements of the problem, also taking into account some considerations such as computational load, processing time, and performance of the wavelet function in optimizing CNN output in the intended task.

A machine learning approach identified a diagnostic model for pancreatic cancer through using circulating microRNA signatures.

Late diagnosis of pancreatic cancer (PC) due to the limited effectiveness of modern testing approaches, causes many patients to miss the chance of surgery and consequently leads to a high mortality rate. Pivotal improvements in circulating microRNA expression levels in PC patients make it possible to diagnose and treat patients at earlier stages. A list of circulating miRNAs was identified in this study using bioinformatics methods in association with pancreatic cancer through analyzing four GEO microarray datasets. The value of top miRNAs was then assessed via using a machine learning method. Taking the advantage of a combinatorial approach consisting of Particle Swarm Optimization (PSO) + Artificial Neural Network (ANN) and Neighborhood Component Analysis (NCA) iterations on a collection of top differentially expressed circulating miRNAs in PC patients, facilitated ranking them by significance. MiRNA's functional analysis in the final index was performed by predicting target genes and constructing PPI networks. Remarkably, the final model consist of miR-663a, miR-1469, miR-92a-2-5p, miR-125b-1-3p and miR-532-5p showed great diagnostic results on investigated cases and the validation set (Accuracy: 0.93, Sensitivity: 0.93, and Specificity: 0.92). Kaplan-Meier survival assessments of the top-ranked miRNAs revealed that three miRNAs, hsa-miR-1469, hsa-miR-663a and hsa-miR-532-5p, had meaningful associations with the prognosis of patients with pancreatic cancer. This miRNA index may serve as a non-invasive and potential PC diagnostic model, although experimental testing is needed.

Promotion of prehospital emergency care through clinical decision support systems: opportunities and challenges.

Clinical decision support systems are interactive computer systems for situational decision making and can improve decision efficiency and safety of care. We investigated the role of these systems in enhancing prehospital care. This narrative review included full-text articles published since 2000 that were available in databases/e-journals including Web of Science, PubMed, Science Direct, and Google Scholar. Search keywords included "clinical decision support system," "decision support system," "decision support tools," "prehospital care," and "emergency medical services." Non-journal articles were excluded. We revealed 14 relevant studies that used such a support system in prehospital emergency medical service. Owing to the dynamic nature of emergency situations, decision timing is critical. Four key factors demonstrated the ability of clinical decision support systems to improve decision-making, reduce errors, and improve the safety of prehospital emergency activity: computer-based, offer support as a natural part of the workflow, provide decision support in the time and place of decision making, and offer practical advice. The use of clinical decision support systems in prehospital care resulted in accurate diagnoses, improved patient triage and patient outcomes, and reduction of prehospital time. By improving emergency management and rescue operations, the quality of prehospital care will be enhanced.

Performance comparison of machine learning techniques in sleep scoring based on wavelet features and neighboring component analysis.

INTRODUCTION: Sleep scoring is an important step in the treatment of sleep disorders. Manual annotation of sleep stages is time-consuming and experience-relevant and, therefore, needs to be done using machine learning techniques. METHODS: Sleep-EDF polysomnography was used in this study as a dataset. Support vector machines and artificial neural network performance were compared in sleep scoring using wavelet tree features and neighborhood component analysis. RESULTS: Neighboring component analysis as a combination of linear and non-linear feature selection method had a substantial role in feature dimension reduction. Artificial neural network and support vector machine achieved 90.30% and 89.93% accuracy, respectively. DISCUSSION AND CONCLUSION: Similar to the state of the art performance, the introduced method in the present study achieved an acceptable performance in sleep scoring. Furthermore, its performance can be enhanced using a technique combined with other techniques in feature generation and dimension reduction. It is hoped that, in the future, intelligent techniques can be used in the process of diagnosing and treating sleep disorders.

The power features of Masseter muscle activity in tension-type and migraine without aura headache during open-close clench cycles.

INTRODUCTION: Different types of headaches and TMJ click influence the masseter muscle activity. The aim of this study was to assess the trend of energy level of the electromyography (EMG) activity of the masseter muscle during open-close clench cycles in migraine without aura (MOA) and tension-type headache (TTH) with or without TMJ click. METHODS: Twenty-five women with MOA and twenty four women with TTH participated in the study. They matched with 25 healthy subjects, in terms of class of occlusion and prevalence of temporomandibular joint (TMJ) with click. The EMG of both masseter muscles were recorded during open-close clench cycles at a rate of 80 cycles per minute for 15 seconds. The mouth opening was restricted to two centimeters by mandibular motion frame. Signal processing steps have been done on the EMG as: noise removing, smoothing, feature extraction, and statistical analyzing. The six statistical parameters of energy computed were mean, Variance, Skewness, Kurtosis, and first and second half energy over all signal energy. RESULTS: A three-way ANOVA indicated that during all the cycles, the mean of energy was more and there was a delay in showing the peak of energy in the masseter of the left side with clicked TMJ in MOA group compared to the two other groups, while this pattern occurred inversely in the side with no-clicked TMJ (P < 0.009). The variation of energy was significantly less in MOA group compared to the two other groups in the no-clicked TMJ (P < 0.003). However, the proportion of the first or second part of signal energy to all energy showed that TTH group had less energy in the first part and more energy in the second part in comparison to the two other groups (P < 0.05). CONCLUSION: The study showed different changes in the energy distribution of masseter muscle activity during cycles in MOA and TTH. MOA, in contrast to TTH, had lateralization effect on EMG and interacted with TMJ click.