Real-time, wide-field endoscopic quantitative imaging based on 3D profile corrected deep-learning SSOP

2021 ◽  
Author(s):  
L. Baratelli ◽  
E. Aguenounon ◽  
M. Flury ◽  
S. Gioux
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Quantitative Imaging ◽  
Wide Field ◽  
3D Profile

scholarly journals Real-time, wide-field and high-quality single snapshot imaging of optical properties with profile correction using deep learning

2020 ◽  
Vol 11 (10) ◽  
pp. 5701 ◽  
Author(s):  
Enagnon Aguénounon ◽  
Jason T. Smith ◽  
Mahdi Al-Taher ◽  
Michele Diana ◽  
Xavier Intes ◽  
...  
Keyword(s):  
Optical Properties ◽  
Deep Learning ◽  
Real Time ◽  
Wide Field ◽  
High Quality ◽  
Profile Correction ◽  
Snapshot Imaging ◽  
Single Snapshot

Abstract TMP56: Mapping the Dynamics of Brain Perfusion During and Following Transient Middle Cerebral Artery Occlusion (tMCAo) in the Rat Using Functional Ultrasound (fUS)

Stroke ◽  
2016 ◽  
Vol 47 (suppl_1) ◽  
Author(s):  
Jean-Claude Baron ◽  
Clement Brunner ◽  
Clothilde Isabel ◽  
Abraham Martin ◽  
Clara Dussaux ◽  
...  
Keyword(s):  
Real Time ◽  
Time Course ◽  
Cerebral Blood Volume ◽  
Quantitative Imaging ◽  
Neuronal Loss ◽  
Brain Perfusion ◽  
Artery Occlusion ◽  
Experimental Stroke ◽  
Wide Field ◽  
Spatiotemporal Resolution

Introduction: Following MCAo, tissue outcome varies depending on depth and duration of hypoperfusion and efficiency of reperfusion. However, the precise time-course of these events in relation to tissue and behavioral outcome remains unsettled due to lack of a wide field-of-view quantitative imaging technique able to map perfusion in the rodent brain at high spatiotemporal resolution. Here we used fUS, a novel approach to map cerebral blood volume (CBV) without contrast agent. Hypothesis: fUS will allow quantitative, near real-time mapping of CVB during and after tMCAo. Methods: 45min filament tMCAo was induced in adult SD rats; sham rats were also used. fUS was used to map the penetrating arterioles and venules of the ipsi- and contra-lateral motor (M1-2) and somatosensory (S1) cortex in coronal sections across the MCA territory at 80μm resolution. Three-min coronal scans were taken at different levels before, during and immediately after MCAo, and at 3 and 6 days thanks to a thinned-skull preparation. CBV was expressed relative to mirror ROI. In addition, a 1-hr movie (one frame/5s) was taken starting a few mins after reperfusion. Serial Neuroscore and 2 sensorimotor tasks were given over 3w post-MCAo, and then NeuN, IBa1 and GFAP immunofluorescence (IF) at post-mortem. Results: fUS showed a ∼80% CBV reduction in S1 during occlusion (p<0.001; n=7), with partial (∼60%, p<0.001) return of CBV on reperfusion, followed by a full return at days 3 and 6. As expected for this model, similar but less conspicuous CBV changes prevailed in M1-2. Continuous reperfusion was depicted in 5/7 rats (slope range: 8-25%/hr relative to prior CBV), but not in 2 rats. There were no significant changes in behavior relative to the sham group (n=4), and IF showed no infarction but marked selective neuronal loss (SNL) in the striatum in 5/7 rats and milder cortical SNL in 4/7 rats. Conclusions: fUS efficiently mapped the acute changes in CBV during occlusion and following reperfusion with high spatio-temporal resolution, allowing the charting of fine tissue reperfusion dynamics in the individual rat. fUS is ideal to longitudinally map real-time cerebral perfusion in experimental stroke from the hyper-acute through to the chronic stage.

Smart teaching mode based on particle swarm image recognition and human-computer interaction deep learning

2020 ◽  
Vol 39 (4) ◽  
pp. 5699-5711
Author(s):  
Shirong Long ◽  
Xuekong Zhao
Keyword(s):  
Feature Extraction ◽  
Particle Swarm Optimization ◽  
Deep Learning ◽  
Real Time ◽  
Image Recognition ◽  
Particle Swarm ◽  
Learning Technology ◽  
Search Performance ◽  
Swarm Optimization ◽  
Teaching Mode

The smart teaching mode overcomes the shortcomings of traditional teaching online and offline, but there are certain deficiencies in the real-time feature extraction of teachers and students. In view of this, this study uses the particle swarm image recognition and deep learning technology to process the intelligent classroom video teaching image and extracts the classroom task features in real time and sends them to the teacher. In order to overcome the shortcomings of the premature convergence of the standard particle swarm optimization algorithm, an improved strategy for multiple particle swarm optimization algorithms is proposed. In order to improve the premature problem in the search performance algorithm of PSO algorithm, this paper combines the algorithm with the useful attributes of other algorithms to improve the particle diversity in the algorithm, enhance the global search ability of the particle, and achieve effective feature extraction. The research indicates that the method proposed in this paper has certain practical effects and can provide theoretical reference for subsequent related research.

Real-time Worker Safety Management System Using Deep Learning-based Video Analysis Algorithm

2020 ◽  
Vol 9 (3) ◽  
pp. 25-30
Author(s):  
So Yeon Jeon ◽  
Jong Hwa Park ◽  
Sang Byung Youn ◽  
Young Soo Kim ◽  
Yong Sung Lee ◽  
...  
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Video Analysis ◽  
Management System ◽  
Safety Management ◽  
Worker Safety ◽  
Safety Management System ◽  
Analysis Algorithm

Real Time Gender and Age Prediction using Deep Learning Techniques

2020 ◽  
Vol 9 (6) ◽  
pp. 797-801
Keyword(s):  
Deep Learning ◽  
Face Recognition ◽  
Real Time ◽  
Vital Role ◽  
Learning Techniques ◽  
Gender And Age ◽  
The Face ◽  
And Gender ◽  
Gender Detection ◽  
Age Prediction

Face recognition plays a vital role in security purpose. In recent years, the researchers have focused on the pose illumination, face recognition, etc,. The traditional methods of face recognition focus on Open CV’s fisher faces which results in analyzing the face expressions and attributes. Deep learning method used in this proposed system is Convolutional Neural Network (CNN). Proposed work includes the following modules: [1] Face Detection [2] Gender Recognition [3] Age Prediction. Thus the results obtained from this work prove that real time age and gender detection using CNN provides better accuracy results compared to other existing approaches.

Sign in / Sign up

Export Citation Format

Share Document