Search results for "learning."

Use of a Virtual Environment to Engage Motor and Postural Abilities in Elderly Subjects With and Without Mild Cognitive Impairment (MAAMI Project)

2016

Objectives: In the context of rehabilitation, the use of new technology such as Virtual Reality Technology (VRT) offers multiple possibilities to modulate the functional stimulation of subjects according to needs. Material and methods: In this study, the validity and reliability of our VRT system were investigated in fifteen healthy aged adults (HAA) and seven aged subjects with mild cognitive impairment (MCI). One implicit session was designed through two virtual environments (VEs) in order to induce the adapted activities associated with balance and postural control. In comparison, the same activities were achieved in explicit sessions with a physiotherapist. This cross-over study made us…

Water maze performance, exploratory activity, inhibitory avoidance and hippocampal plasticity in aged superior and inferior learners

2002

In 28- to 30-month-old rats, in vitro short-term and long-term potentiation (STP and LTP) were measured in area CA1 of the hippocampus in seven superior and seven inferior learners, that were selected from a pool of 40 rats based on water maze escape performance over a period of 9 days. The aim was to examine whether levels of STP and LTP could account for group differences in learning of water maze escape, spatial preference and wall (thigmotaxis)-avoidance and in short-term retention of an inhibitory avoidance task. There was no significant group difference in open-field exploration, i.e. the number of rearings. In contrast to expectation, the superior and inferior learners did not differ…

Efficient 3D Deep Learning for Myocardial Diseases Segmentation

2021

Automated myocardial segmentation from late gadolinium enhancement magnetic resonance images (LGE-MRI) is a critical step in the diagnosis of cardiac pathologies such as ischemia and myocardial infarction. This paper proposes a deep learning framework for improved myocardial diseases segmentation. In the first step, we build an encoder-decoder segmentation network that generates myocardium and cavity segmentations from the whole volume, followed by a 3D U-Net based on Shape prior to identifying myocardial infarction and myocardium ventricular obstruction (MVO) segmentations from the encoder-decoder prediction. The proposed network achieves good segmentation performance, as computed by avera…

Influence of high-definition anodal transcranial direct current stimulation (HD-atDCS) on motor learning of a high-speed bimanual task

2017

Procedural Memory Following Moderate-Severe Traumatic Brain Injury: Group Performance and Individual Differences on the Rotary Pursuit Task

2019

The impact of traumatic brain injury (TBI) on procedural memory has received significantly less attention than declarative memory. Although to date studies on procedural memory have yielded mixed findings, many rehabilitation protocols (e.g., errorless learning) rely on the procedural memory system, and assume that it is relatively intact. The aim of the current study was to determine whether individuals with TBI are impaired on a task of procedural memory as a group, and to examine the presence of individual differences in performance. We administered to a sample of 36 individuals with moderate-severe TBI and 40 healthy comparisons (HCs) the rotary pursuit task, and then examined their rat…

Deep Learning Predicts Molecular Subtype of Muscle-invasive Bladder Cancer from Conventional Histopathological Slides.

2020

Abstract Background Muscle-invasive bladder cancer (MIBC) is the second most common genitourinary malignancy, and is associated with high morbidity and mortality. Recently, molecular subtypes of MIBC have been identified, which have important clinical implications. Objective In the current study, we tried to predict the molecular subtype of MIBC samples from conventional histomorphology alone using deep learning. Design, setting, and participants Two cohorts of patients with MIBC were used: (1) The Cancer Genome Atlas Urothelial Bladder Carcinoma dataset including 407 patients and (2) our own cohort including 16 patients with treatment-naive, primary resected MIBC. This resulted in a total …

Initial Study on Implementation of the Low-Frequency Wave Markers for the Purpose of Diagnostic Tests’ Performance and Neurofeedback Therapy

2019

Abstract The paper focuses on automation of signal processing, which also considers analysis of biomedical data, such as EEG. The results of the study prove that this enables a better understanding of signal changes and makes it possible to address some specific disturbances. It also makes it possible to describe the relevant changes in signals mathematically and helps to create markers of various brain disorders. This paper presents the study at the initial stage and focuses on the mathematical markers of concentration disorders associated with Theta waves. The presented markers presented are based on Welch’s periodograms. The obtained results are very promising and further studies aimed a…

Joint damage and motor learning during unipedal stance in haemophilia arthropathy: report of two cases

2016

Validation of Knee KL-classifying Deep Neural Network with Finnish Patient Data

2021

Osteoarthritis (OA) is the most common form of joint disease in the world. The diagnosis of OA is currently made by human experts and suffers from subjectivity, but recently new promising detection algorithms have been developed. We validated the current state-of-the-art KL-classifying neural network model for knee OA using knee X-rays taken from postmenopausal women suffering from knee pain attributable to OA. The performance of the model on the clinical data was considerably lower compared to the previous results on population-based test data. This suggests that the performance of the current grading methods is not yet adequate to be applied in clinical settings. The present results also …

The Temporal Development of Early and Late CNV in a Simple Discrimination Paradigm: the Effects of Motor Preparation and Average Reaction Time

1980

Publisher Summary This chapter discusses the temporal development of early and late contingent negative variation (CNV) in a simple discrimination paradigm. The CNV typically arises when a warning stimulus is paired with an imperative stimulus which, in turn, is followed by a motor reaction. If the interstimulus interval is less than approximately 2 sec the CNV begins immediately after the positive deflection (P300) following the warning stimulus. It may appear as a steadily rising negative potential shift that reaches its peak with the presentation of the imperative stimulus, or as sustained negativity throughout the rest of the foreperiod. If the interstimulus interval is extended beyond …