316 results match your criteria train rely

A review of medical image data augmentation techniques for deep learning applications.

J Med Imaging Radiat Oncol 2021 Jun 19. Epub 2021 Jun 19.

Institute of Medical Physics, University of Sydney, Sydney, New South Wales, Australia.

Research in artificial intelligence for radiology and radiotherapy has recently become increasingly reliant on the use of deep learning-based algorithms. While the performance of the models which these algorithms produce can significantly outperform more traditional machine learning methods, they do rely on larger datasets being available for training. To address this issue, data augmentation has become a popular method for increasing the size of a training dataset, particularly in fields where large datasets aren't typically available, which is often the case when working with medical images. Read More

View Article and Full-Text PDF

Comparison of foot strike sound between rearfoot, midfoot and forefoot strike runners.

J Athl Train 2021 Jun 15. Epub 2021 Jun 15.

Gait & Motion Analysis Laboratory, Department of Rehabilitation Sciences, The Hong Kong Polytechnic University, Hong Kong.

Context: There are three common foot strike techniques in runners. Whether these techniques generate different sounds at the point of impact with the ground may influence lower limb kinetics. No previous studies have determined whether such relationships exist. Read More

View Article and Full-Text PDF

Harmonized Segmentation of Neonatal Brain MRI.

Front Neurosci 2021 25;15:662005. Epub 2021 May 25.

Centre for the Developing Brain, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom.

Deep learning based medical image segmentation has shown great potential in becoming a key part of the clinical analysis pipeline. However, many of these models rely on the assumption that the train and test data come from the same distribution. This means that such methods cannot guarantee high quality predictions when the source and target domains are dissimilar due to different acquisition protocols, or biases in patient cohorts. Read More

View Article and Full-Text PDF

Quantification of Osteoclasts in Culture, Powered by Machine Learning.

Front Cell Dev Biol 2021 25;9:674710. Epub 2021 May 25.

Department of Anatomy and Anthropology, Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.

osteoclastogenesis is a central assay in bone biology to study the effect of genetic and pharmacologic cues on the differentiation of bone resorbing osteoclasts. To date, identification of TRAP+ multinucleated cells and measurements of osteoclast number and surface rely on a manual tracing requiring specially trained lab personnel. This task is tedious, time-consuming, and prone to operator bias. Read More

View Article and Full-Text PDF

Streamlined magnetic resonance fingerprinting: Fast whole-brain coverage with deep-learning based parameter estimation.

Neuroimage 2021 Jun 5;238:118237. Epub 2021 Jun 5.

Department of Medical Biophysics, University of Toronto, 101 College St Suite 15-701, Toronto, ON M5G 1L7, Canada; Hurvitz Brain Sciences Research Program, Sunnybrook Research Institute, Toronto, ON, Canada.

Magnetic resonance fingerprinting (MRF) is a quantitative MRI (qMRI) framework that provides simultaneous estimates of multiple relaxation parameters as well as metrics of field inhomogeneity in a single acquisition. However, current challenges exist in the forms of (1) scan time; (2) need for custom image reconstruction; (3) large dictionary sizes; (4) long dictionary-matching time. This study aims to introduce a novel streamlined magnetic-resonance fingerprinting (sMRF) framework based on a single-shot echo-planar imaging (EPI) sequence to simultaneously estimate tissue T1, T2, and T2* with integrated B1 correction. Read More

View Article and Full-Text PDF

Interpretability Versus Accuracy: A Comparison of Machine Learning Models Built Using Different Algorithms, Performance Measures, and Features to Predict Levels in Agricultural Water.

Front Artif Intell 2021 14;4:628441. Epub 2021 May 14.

Department of Food Science, Cornell University, Ithaca, NY, United States.

Since is considered a fecal indicator in surface water, government water quality standards and industry guidance often rely on monitoring to identify when there is an increased risk of pathogen contamination of water used for produce production (e.g., for irrigation). Read More

View Article and Full-Text PDF

High through-plane resolution CT imaging with self-supervised deep learning.

Phys Med Biol 2021 May 28. Epub 2021 May 28.

Department of Radiology and Sciences Imaging Department of Radiology Oncology, Emory University, Atlanta, Georgia, UNITED STATES.

CT images for radiotherapy planning are usually acquired in thick slice to reduce imaging dose, especially for pediatric patients, and to lessen the need for contouring and treatment planning on more slices. However, low through-plane resolution may degrade the accuracy of dose calculations. In this paper, a self-supervised deep learning workflow is proposed to synthesize high through-plane resolution CT images by learning from their high in-plane resolution features. Read More

View Article and Full-Text PDF

Using a bimanual lever-driven wheelchair for arm movement practice early after stroke: A pilot, randomized, controlled, single-blind trial.

Clin Rehabil 2021 May 24:2692155211014362. Epub 2021 May 24.

Department of Neurology, University of California, Los Angeles, CA, USA.

Objective: Many patients with subacute stroke rely on the nonparetic arm and leg to propel manual wheelchairs. We designed a bimanual, lever-driven wheelchair (LARA) to promote overground mobility and hemiparetic arm exercise. This study measured the feasibility of using LARA to increase arm movement, achieve mobility, and improve arm motor recovery (clinicaltrials. Read More

View Article and Full-Text PDF

Islamic Trauma Healing: Integrating Faith and Empirically Supported Principles in a Community-Based Program.

Cogn Behav Pract 2021 Mar 20;28(2):167-192. Epub 2020 Nov 20.

University of Washington.

Access to adequate, much less state-of-the-art, mental health care is a global problem. Natural disasters, civil war, and terrorist conflict have forcibly displaced millions of Muslims and have resulted in a remarkable level of individual and communitywide trauma exposure. As a result, many are at risk for posttraumatic stress and other trauma-related disorders. Read More

View Article and Full-Text PDF

Track-to-Learn: A general framework for tractography with deep reinforcement learning.

Med Image Anal 2021 May 3;72:102093. Epub 2021 May 3.

Faculté des Sciences, Université de Sherbrooke, Sherbrooke, QC, CA, J1K 2R1.

Diffusion MRI tractography is currently the only non-invasive tool able to assess the white-matter structural connectivity of a brain. Since its inception, it has been widely documented that tractography is prone to producing erroneous tracks while missing true positive connections. Recently, supervised learning algorithms have been proposed to learn the tracking procedure implicitly from data, without relying on anatomical priors. Read More

View Article and Full-Text PDF

Standardized and reproducible measurement of decision-making in mice.

Elife 2021 May 20;10. Epub 2021 May 20.

UCL Institute of Ophthalmology, University College London, London, United Kingdom.

Progress in science requires standardized assays whose results can be readily shared, compared, and reproduced across laboratories. Reproducibility, however, has been a concern in neuroscience, particularly for measurements of mouse behavior. Here, we show that a standardized task to probe decision-making in mice produces reproducible results across multiple laboratories. Read More

View Article and Full-Text PDF

Cholinergic and Noradrenergic Modulation of Corticothalamic Synaptic Input From Layer 6 to the Posteromedial Thalamic Nucleus in the Rat.

Front Neural Circuits 2021 26;15:624381. Epub 2021 Apr 26.

Nencki Institute of Experimental Biology, Polish Academy of Sciences, Warsaw, Poland.

Cholinergic and noradrenergic neuromodulation of the synaptic transmission from cortical layer 6 of the primary somatosensory cortex to neurons in the posteromedial thalamic nucleus (PoM) was studied using an slice preparation from young rats. Cholinergic agonist carbachol substantially decreased the amplitudes of consecutive excitatory postsynaptic potentials (EPSPs) evoked by a 20 Hz five pulse train. The decreased amplitude effect was counteracted by a parallel increase of synaptic frequency-dependent facilitation. Read More

View Article and Full-Text PDF

Awe/Gratitude as an Experiential Aspect of Spirituality and Its Association to Perceived Positive Changes During the COVID-19 Pandemic.

Front Psychiatry 2021 20;12:642716. Epub 2021 Apr 20.

Caritas Science and Christian Social Work, Faculty of Theology, Albert-Ludwig-University, Freiburg, Germany.

While the COVID-19 pandemic has affected the lives of almost all people worldwide, many people observed also positive changes in their attitudes and behaviors. This can be seen in the context of posttraumatic growth. These perceived changes refer to five main categories: Nature/Silence/Contemplation, Spirituality, Relationships, Reflection on life, and Digital media usage. Read More

View Article and Full-Text PDF

Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study.

NPJ Precis Oncol 2021 May 3;5(1):35. Epub 2021 May 3.

Department of Urology, Case Western Reserve University, Cleveland, OH, USA.

Existing tools for post-radical prostatectomy (RP) prostate cancer biochemical recurrence (BCR) prognosis rely on human pathologist-derived parameters such as tumor grade, with the resulting inter-reviewer variability. Genomic companion diagnostic tests such as Decipher tend to be tissue destructive, expensive, and not routinely available in most centers. We present a tissue non-destructive method for automated BCR prognosis, termed "Histotyping", that employs computational image analysis of morphologic patterns of prostate tissue from a single, routinely acquired hematoxylin and eosin slide. Read More

View Article and Full-Text PDF

An automated framework for image classification and segmentation of fetal ultrasound images for gestational age estimation.

Proc SPIE Int Soc Opt Eng 2021 Feb 15;11596. Epub 2021 Feb 15.

Department of Obstetrics and Gynecology, University of North Carolina at Chapel Hill.

Accurate assessment of fetal gestational age (GA) is critical to the clinical management of pregnancy. Industrialized countries rely upon obstetric ultrasound (US) to make this estimate. In low- and middle- income countries, automatic measurement of fetal structures using a low-cost obstetric US may assist in establishing GA without the need for skilled sonographers. Read More

View Article and Full-Text PDF
February 2021

Diagnostic feature training improves face matching accuracy.

J Exp Psychol Learn Mem Cogn 2021 Apr 29. Epub 2021 Apr 29.

School of Psychology.

Identifying unfamiliar faces is surprisingly error-prone, even for experienced professionals who perform this task regularly. Previous attempts to train this ability have been largely unsuccessful, leading many to conclude that face identity processing is hard-wired and not amenable to further perceptual learning. Here, we take a novel expert knowledge elicitation approach to training, based on the feature-based comparison strategy used by high-performing professional facial examiners. Read More

View Article and Full-Text PDF

An operant temperature sensory assay provides a means to assess thermal discrimination.

Mol Pain 2021 Jan-Dec;17:17448069211013633

Molecular Genetics Section, National Institute of Dental and Craniofacial Research/NIH, Bethesda, MD, USA.

Mouse behavioral assays have proven useful for the study of thermosensation, helping to identify receptors and circuits responsible for the transduction of thermal stimuli and information relay to the brain. However, these methods typically rely on observation of behavioral responses to various temperature stimuli to infer sensory ability and are often unable to disambiguate innocuous thermosensation from thermal nociception or to study thermosensory circuitry which do not produce easily detectable innate behavioral responses. Here we demonstrate a new testing apparatus capable of delivering small, rapid temperature change stimuli to the mouse's skin, permitting the use of operant conditioning to train mice to recognize and report temperature change. Read More

View Article and Full-Text PDF

A fused-image-based approach to detect obstructive sleep apnea using a single-lead ECG and a 2D convolutional neural network.

PLoS One 2021 26;16(4):e0250618. Epub 2021 Apr 26.

Biomedical Information Engineering Lab, The University of Aizu, Aizuwakamatsu, Fukushima, Japan.

Obstructive sleep apnea (OSA) is a common chronic sleep disorder that disrupts breathing during sleep and is associated with many other medical conditions, including hypertension, coronary heart disease, and depression. Clinically, the standard for diagnosing OSA involves nocturnal polysomnography (PSG). However, this requires expert human intervention and considerable time, which limits the availability of OSA diagnosis in public health sectors. Read More

View Article and Full-Text PDF

Deep convolutional autoencoder for the simultaneous removal of baseline noise and baseline drift in chromatograms.

J Chromatogr A 2021 Jun 23;1646:462093. Epub 2021 Mar 23.

University of Leuven (KU Leuven), Department for Pharmaceutical and Pharmacological Sciences, Pharmaceutical Analysis, Herestraat 49, 3000 Leuven, Belgium. Electronic address:

Enhancement of chromatograms, such as the reduction of baseline noise and baseline drift, is often essential to accurately detect and quantify analytes in a mixture. Current methods have been well studied and adopted for decades and have assisted researchers in obtaining reliable results. However, these methods rely on relatively simple statistics of the data (chromatograms) which in some cases result in significant information loss and inaccuracies. Read More

View Article and Full-Text PDF

Forecasting of the COVID-19 pandemic situation of Korea.

Genomics Inform 2021 Mar 25;19(1):e11. Epub 2021 Mar 25.

Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul 08826, Korea.

For the novel coronavirus disease 2019 (COVID-19), predictive modeling, in the literature, uses broadly susceptible exposed infected recoverd (SEIR)/SIR, agent-based, curve-fitting models. Governments and legislative bodies rely on insights from prediction models to suggest new policies and to assess the effectiveness of enforced policies. Therefore, access to accurate outbreak prediction models is essential to obtain insights into the likely spread and consequences of infectious diseases. Read More

View Article and Full-Text PDF

Contradistinguisher: A Vapnik's Imperative to Unsupervised Domain Adaptation.

IEEE Trans Pattern Anal Mach Intell 2021 Apr 6;PP. Epub 2021 Apr 6.

Recent domain adaptation works rely on an indirect way of first aligning the source and target domain distributions and then train a classifier on the labeled source domain to classify the target domain. However, the main drawback of this approach is that obtaining a near-perfect domain alignment in itself might be difficult/impossible (e.g. Read More

View Article and Full-Text PDF

Genome annotation across species using deep convolutional neural networks.

PeerJ Comput Sci 2020 15;6:e278. Epub 2020 Jun 15.

Laboratoire de Physique Théorique de la Matière Condensée (LPTMC), Sorbonne Université, Paris, France.

Application of deep neural network is a rapidly expanding field now reaching many disciplines including genomics. In particular, convolutional neural networks have been exploited for identifying the functional role of short genomic sequences. These approaches rely on gathering large sets of sequences with known functional role, extracting those sequences from whole-genome-annotations. Read More

View Article and Full-Text PDF

Editorial Commentary: Proficiency-Based Progression Surgical Simulation Training Is an Efficient Adjunct to High-Volume Clinical Experience.

Rachel M Frank

Arthroscopy 2021 04;37(4):1107-1109

University of Colorado School of Medicine.

The optimal way to train a future surgeon has been debated for years, with strategies ranging from the well-known "see one, do one, teach one" approach to more novel approaches that rely on metrics and proficiency. Recent research shows that surgical training with a proficiency-based progression curriculum is an efficient strategy for teaching arthroscopy procedural skills, and, further, may improve patient safety by reducing the technical errors that might otherwise occur before proficiency is achieved. While every surgical specialty has its nuances that must be mastered to provide safe, effective, and efficient care, for a variety of reasons, the skills needed to perform arthroscopy are incredibly difficult to learn, let alone achieve proficiency or master. Read More

View Article and Full-Text PDF

Promoting Generalized Learning in Balance Recovery Interventions.

Brain Sci 2021 Mar 22;11(3). Epub 2021 Mar 22.

Department of Kinesiology and Health Science, Utah State University, Logan, UT 84322, USA.

Recent studies have shown balance recovery can be enhanced via task-specific training, referred to as perturbation-based balance training (PBT). These interventions rely on principles of motor learning where repeated exposure to task-relevant postural perturbations results in more effective compensatory balance responses. Evidence indicates that compensatory responses trained using PBT can be retained for many months and can lead to a reduction in falls in community-dwelling older adults. Read More

View Article and Full-Text PDF

Harnessing machine learning to guide phylogenetic-tree search algorithms.

Nat Commun 2021 03 31;12(1):1983. Epub 2021 Mar 31.

The Shmunis School of Biomedicine and Cancer Research, Tel Aviv University, Ramat Aviv, Tel-Aviv, Israel.

Inferring a phylogenetic tree is a fundamental challenge in evolutionary studies. Current paradigms for phylogenetic tree reconstruction rely on performing costly likelihood optimizations. With the aim of making tree inference feasible for problems involving more than a handful of sequences, inference under the maximum-likelihood paradigm integrates heuristic approaches to evaluate only a subset of all potential trees. Read More

View Article and Full-Text PDF

On the modeling of thermal and free carrier nonlinearities in silicon-on-insulator microring resonators.

Opt Express 2021 Feb;29(3):4363-4377

The temporal dynamics of integrated silicon resonators has been modeled using a set of equations coupling the internal energy, the temperature and the free carrier population. Owing to its simplicity, Newton's law of cooling is the traditional choice for describing the thermal evolution of such systems. In this work, we theoretically and experimentally prove that this can be inadequate in monolithic planar devices, leading to inaccurate predictions. Read More

View Article and Full-Text PDF
February 2021

How do you feel? Using natural language processing to automatically rate emotion in psychotherapy.

Behav Res Methods 2021 Mar 22. Epub 2021 Mar 22.

Department of Educational Psychology, University of Utah, Salt Lake City, UT, USA.

Emotional distress is a common reason for seeking psychotherapy, and sharing emotional material is central to the process of psychotherapy. However, systematic research examining patterns of emotional exchange that occur during psychotherapy sessions is often limited in scale. Traditional methods for identifying emotion in psychotherapy rely on labor-intensive observer ratings, client or therapist ratings obtained before or after sessions, or involve manually extracting ratings of emotion from session transcripts using dictionaries of positive and negative words that do not take the context of a sentence into account. Read More

View Article and Full-Text PDF

Two methods to approximate the Koopman operator with a reservoir computer.

Chaos 2021 Feb;31(2):023116

Department of Mathematics and Namur Institute for Complex Systems (naXys), University of Namur, 5000 Namur, Belgium.

The Koopman operator provides a powerful framework for data-driven analysis of dynamical systems. In the last few years, a wealth of numerical methods providing finite-dimensional approximations of the operator have been proposed [e.g. Read More

View Article and Full-Text PDF
February 2021

Power analysis of transcriptome-wide association study: Implications for practical protocol choice.

PLoS Genet 2021 02 26;17(2):e1009405. Epub 2021 Feb 26.

Department of Biochemistry & Molecular Biology, Alberta Children's Hospital Research Institute, University of Calgary, Calgary, Canada.

The transcriptome-wide association study (TWAS) has emerged as one of several promising techniques for integrating multi-scale 'omics' data into traditional genome-wide association studies (GWAS). Unlike GWAS, which associates phenotypic variance directly with genetic variants, TWAS uses a reference dataset to train a predictive model for gene expressions, which allows it to associate phenotype with variants through the mediating effect of expressions. Although effective, this core innovation of TWAS is poorly understood, since the predictive accuracy of the genotype-expression model is generally low and further bounded by expression heritability. Read More

View Article and Full-Text PDF
February 2021

Unsupervised Anomaly Detection with Distillated Teacher-Student Network Ensemble.

Entropy (Basel) 2021 Feb 6;23(2). Epub 2021 Feb 6.

Beijing Laboratory of National Economic Security Early-Warning Engineering, Beijing Jiaotong University, Beijing 100044, China.

We address the problem of unsupervised anomaly detection for multivariate data. Traditional machine learning based anomaly detection algorithms rely on specific assumptions of normal patterns and fail to model complex feature interactions and relations. Recently, existing deep learning based methods are promising for extracting representations from complex features. Read More

View Article and Full-Text PDF
February 2021