Region-of-interest prediction for interactively streaming regions of high resolution video

2007 ◽  
Author(s):  
Aditya Mavlankar ◽  
David Varodayan ◽  
Bernd Girod
Keyword(s):  
High Resolution ◽  
Region Of Interest ◽  
Interest Prediction

Quantitative accuracy of serotonergic neurotrans-mission imaging with high-resolution 123I SPECT

2004 ◽  
Vol 43 (06) ◽  
pp. 185-189 ◽  
Author(s):  
J. T. Kuikka
Keyword(s):  
High Resolution ◽  
Scatter Correction ◽  
Region Of Interest ◽  
Binding Potential ◽  
Partial Volume ◽  
Therapeutic Drugs ◽  
Quantitative Accuracy ◽  
Critical Error ◽  
Statistical Noise

Summary Aim: Serotonin transporter (SERT) imaging can be used to study the role of regional abnormalities of neurotransmitter release in various mental disorders and to study the mechanism of action of therapeutic drugs or drugs’ abuse. We examine the quantitative accuracy and reproducibility that can be achieved with high-resolution SPECT of serotonergic neurotransmission. Method: Binding potential (BP) of 123I labeled tracer specific for midbrain SERT was assessed in 20 healthy persons. The effects of scatter, attenuation, partial volume, mis-registration and statistical noise were estimated using phantom and human studies. Results: Without any correction, BP was underestimated by 73%. The partial volume error was the major component in this underestimation whereas the most critical error for the reproducibility was misplacement of region of interest (ROI). Conclusion: The proper ROI registration, the use of the multiple head gamma camera with transmission based scatter correction introduce more relevant results. However, due to the small dimensions of the midbrain SERT structures and poor spatial resolution of SPECT, the improvement without the partial volume correction is not great enough to restore the estimate of BP to that of the true one.

Integrating Magnetic Resonance Imaging Postprocessing Results into Neuronavigation for Electrode Implantation and Resection of Subtle Focal Cortical Dysplasia in Previously Cryptogenic Epilepsy

Neurosurgery ◽  
2010 ◽  
Vol 66 (1) ◽  
pp. 187-195 ◽  
Author(s):  
Jörg Wellmer ◽  
Yaroslav Parpaley ◽  
Marec von Lehe ◽  
Hans-Jürgen Huppertz
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
High Resolution ◽  
Morphometric Analysis ◽  
Region Of Interest ◽  
Normal Database ◽  
Resonance Imaging ◽  
Electrode Implantation ◽  
Neuronavigation System ◽  
The Individual

Abstract OBJECTIVE Focal cortical dysplasias (FCDs) are highly epileptogenic lesions. Surgical removal is frequently the best treatment option for pharmacoresistant epilepsy. However, subtle FCDs may remain undetected even after high-resolution magnetic resonance imaging (MRI). Morphometric MRI analysis, which compares the individual brain with a normal database, can facilitate the detection of FCDs. We describe how the results of normal database–based MRI postprocessing can be used to guide stereotactic electrode implantation and subsequent resection of lesions that are suspected to be FCDs. METHODS A presurgical evaluation was conducted on a 19-year-old woman with pharmacoresistant hypermotor seizures. Conventional high-resolution MRI was classified as negative for epileptogenic lesions. However, morphometric analysis of the spatially normalized MRI revealed abnormal gyration and blurring of the gray-white matter junction, which was suggestive of a small and deeply seated FCD in the left frontal lobe. RESULTS The brain region highlighted by morphometric analysis was marked as a region of interest, transferred back to the original dimension of the individual MRI, and imported into a neuronavigation system. This allowed the region of interest–targeted stereotactic implantation of 2 depth electrodes, by which seizure onset was confirmed in the lesion. The electrodes also guided the final resection, which rendered the patient seizure-free. The lesion was histologically classified as FCD Palmini and Lüders IIB. CONCLUSION Transferring normal database–based MRI postprocessing results into a neuronavigation system is a new and worthwhile extension of multimodal neuronavigation. The combination of resulting regions of interest with functional and anatomic data may facilitate planning of electrode implantation for invasive electroencephalographic recordings and the final resection of small or deeply seated FCDs.

Infrared Target Tracking Algorithm Based on Multiple Feature Fusion and Region of Interest Prediction

2019 ◽  
Vol 48 (7) ◽  
pp. 710004 ◽  
Author(s):  
刘辉 LIU Hui ◽  
何勇 HE Yong ◽  
何博侠 HE Bo-xia ◽  
刘志 LIU Zhi ◽  
顾士晨 GU Shi-chen
Keyword(s):  
Target Tracking ◽  
Feature Fusion ◽  
Region Of Interest ◽  
Tracking Algorithm ◽  
Multiple Feature ◽  
Multiple Feature Fusion ◽  
Interest Prediction

High-Resolution Metabolic Mapping of the Cerebellum Using a Zoomed Magnetic Resonance Spectroscopic Imaging

2020 ◽  
Author(s):  
Uzay E. Emir ◽  
Jaiyta Sood ◽  
Mark Chiew ◽  
Albert Thomas ◽  
Sean P. Lane
Keyword(s):  
Magnetic Resonance ◽  
High Resolution ◽  
Region Of Interest ◽  
Spectroscopic Imaging ◽  
Magnetic Resonance Spectroscopic Imaging ◽  
Total N ◽  
Group Averaging ◽  
Full Intensity ◽  
Nominal Resolution ◽  
Very High

AbstractPurposeThe human cerebellum plays an important role in functional activity cerebrum which is ranging from motor to cognitive activities since due to its relaying role between spinal cord and cerebrum. The cerebellum poses many challenges to magnetic resonance spectroscopic imaging (MRSI) due to the caudal location, the susceptibility to physiological artifacts and partial volume artifact due to its complex anatomical structure. Thus, in present study, we propose a high-resolution MRSI acquisition scheme for the cerebellum.MethodsA zoomed or reduced-field of view (rFOV) metabolite-cycled full-intensity magnetic resonance spectroscopic imaging (MRSI) at 3T with a nominal resolution of 62.5 μL was developed. Single-slice rFOV MRSI data were acquired from the cerebellum of 5 healthy subjects with a nominal resolution of 2.5□×□2.5□mm2 in 9□minutes 36. Spectra were quantified with LCModel. A spatially unbiased atlas template of the cerebellum was used for analyzing metabolite distributions in the cerebellum.ResultsThe high quality of the achieved spectra enabled to generate a high-resolution metabolic map of total N-acetylaspartate, total creatine, total choline, glutamate+glutamine and myo-inositol with Cramér-Rao lower bounds below 50%. A spatially unbiased atlas template of the cerebellum-based region of interest (ROIs) analysis resulted in spatially dependent metabolite distributions in 9 ROIs. The group-averaging across subjects in the Montreal Neurological Institute-152 template space allowed to generate a very high-resolution metabolite maps in the cerebellum.ConclusionThese findings indicate that very high-resolution metabolite probing of cerebellum is feasible using rFOV or zoomed MRSI at 3T.

Region of Interest Prediction Method under Dynamic Characteristics of Vehicles

2019 ◽  
Author(s):  
Shaosong Li ◽  
Yunsheng Tian ◽  
Zheng Li ◽  
Zhixin Yu ◽  
Bangcheng Zhang ◽  
...  
Keyword(s):  
Dynamic Characteristics ◽  
Prediction Method ◽  
Region Of Interest ◽  
Interest Prediction

scholarly journals Ensemble Sensitivity Analysis Applied to a Southern Plains Convective Event

2015 ◽  
Vol 143 (1) ◽  
pp. 230-249 ◽  
Author(s):  
Christopher N. Bednarczyk ◽  
Brian C. Ancell
Keyword(s):  
Sensitivity Analysis ◽  
High Resolution ◽  
Wrf Model ◽  
Region Of Interest ◽  
Thermodynamic Characteristics ◽  
Forecast Errors ◽  
Synoptic Scale ◽  
Southern Plains ◽  
Synoptic Features ◽  
Upper Level

Abstract Forecast sensitivity of an April 2012 severe convection event in northern Texas is investigated with a high-resolution Weather Research and Forecasting (WRF) Model–based ensemble Kalman filter (EnKF). Through ensemble sensitivity analysis (ESA), which relates a forecast metric to initial and early forecast errors by linear regression, features of the flow are revealed that reflect dynamical relationships with the forecast convection. Results indicate that ESA can be successfully applied to high-resolution forecasts of convection, and the most important features are related to the synoptic-scale flow such as positioning of an upper-level low and lower-level thermodynamic characteristics of air masses. Comparisons of the maximum and minimum convectively active members in the region of interest show that the fields generated by ESA are consistent with the actual evolution of the event: members with more eastward progression of the synoptic-scale system produced a stronger convection forecast. The forecast metric of interest is modified in several ways to further evaluate the strength of the results of the sensitivity analysis. Three different variables acting as convection proxies (reflectivity, vertical velocity, and precipitation) are tested along with changing the location of the forecast metric and its spatial size. These additional tests highlight the same synoptic features of the flow with the only major differences reflecting the importance of magnitude versus position of the convective forecast.

scholarly journals REGION OF INTEREST DETECTION BASED ON HISTOGRAM SEGMENTATION FOR SATELLITE IMAGE

2016 ◽  
Vol XLI-B7 ◽  
pp. 249-255
Author(s):  
Warinthorn Kiadtikornthaweeyot ◽  
Adrian R. L. Tatnall
Keyword(s):  
Image Segmentation ◽  
High Resolution ◽  
Satellite Images ◽  
Satellite Image ◽  
Region Of Interest ◽  
Satellite Imaging ◽  
Proposed Model ◽  
High Resolution Satellite Images ◽  
Image Area ◽  
Interest Detection

High resolution satellite imaging is considered as the outstanding applicant to extract the Earth’s surface information. Extraction of a feature of an image is very difficult due to having to find the appropriate image segmentation techniques and combine different methods to detect the Region of Interest (ROI) most effectively. This paper proposes techniques to classify objects in the satellite image by using image processing methods on high-resolution satellite images. The systems to identify the ROI focus on forests, urban and agriculture areas. The proposed system is based on histograms of the image to classify objects using thresholding. The thresholding is performed by considering the behaviour of the histogram mapping to a particular region in the satellite image. The proposed model is based on histogram segmentation and morphology techniques. There are five main steps supporting each other; Histogram classification, Histogram segmentation, Morphological dilation, Morphological fill image area and holes and ROI management. The methods to detect the ROI of the satellite images based on histogram classification have been studied, implemented and tested. The algorithm is be able to detect the area of forests, urban and agriculture separately. The image segmentation methods can detect the ROI and reduce the size of the original image by discarding the unnecessary parts.

Sign in / Sign up

Export Citation Format

Share Document