Skull segmentation of UTE MR images by probabilistic neural network for attenuation correction in PET/MR

2013 ◽  
Vol 702 ◽  
pp. 114-116 ◽  
Author(s):  
A. Santos Ribeiro ◽  
E. Rota Kops ◽  
H. Herzog ◽  
P. Almeida
Keyword(s):  
Neural Network ◽  
Attenuation Correction ◽  
Probabilistic Neural Network ◽  
Mr Images

Alzheimer disease detection from structural MR images using FCM based weighted probabilistic neural network

2018 ◽  
Vol 13 (1) ◽  
pp. 87-110 ◽  
Author(s):  
Baskar Duraisamy ◽  
Jayanthi Venkatraman Shanmugam ◽  
Jayanthi Annamalai
Keyword(s):  
Neural Network ◽  
Alzheimer Disease ◽  
Probabilistic Neural Network ◽  
Disease Detection ◽  
Mr Images

scholarly journals An Efficient Method for Automatic Classification of Brain MRI using Feature Selection and Modified Probabilistic Neural Network

2019 ◽  
Vol 9 (2) ◽  
pp. 976-981
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Probabilistic Neural Network ◽  
Brain Mri ◽  
Mr Images ◽  
Tumor Identification ◽  
Texture Characteristics ◽  
Minimization Technique ◽  
Occurrence Matrix

In the brain tumor MRI images, the identification, segmentation and detection of the infectious area is a tedious and lengthy task. As segmentation is called intensity inhomogeneity by an intrinsic object. In this paper we suggest an energy efficient minimization technique for joint domain assessment and segmentation of MR images called multiplicative intrinsic component optimization (MICO). In this work, we focused on quicker implementation with a robust removal of gray-level co-occurrence matrix (GLCM). Optimal texture characteristics are obtained by the Spatial Gray Dependence (SGLDM) technique from ordinary and tumor areas. With very large feature sets, the choice of features is redundant because the precision frequently worsens without choice of features. However, when only the feature selection is used, the precision of classification is significantly improved. However, by reducing the time needed for classification computations and improving classification precision by removing redundant, false or incorrect characteristics. A fresh function choice and weighting technique, supported by the decomposition developmental multi-objective algorithm, are provided in this work. These characteristics are provided for the MPNN classification. Modified probabilistic neural network (MPNN) classification was used in brain MRI images for training and testing for precision in tumor identification. The simulation findings accomplished almost 98% precision in the identification of ordinary and abnormal tissue from brain MR images showing the efficiency of the method suggested.

scholarly journals Texture analysis ofT1- andT2-weighted MR images and use of probabilistic neural network to discriminate posterior fossa tumours in children

2014 ◽  
Vol 27 (6) ◽  
pp. 632-639 ◽  
Author(s):  
Eleni Orphanidou-Vlachou ◽  
Nikolaos Vlachos ◽  
Nigel P. Davies ◽  
Theodoros N. Arvanitis ◽  
Richard G. Grundy ◽  
...  
Keyword(s):  
Neural Network ◽  
Texture Analysis ◽  
Posterior Fossa ◽  
Probabilistic Neural Network ◽  
Mr Images ◽  
Posterior Fossa Tumours

scholarly journals Attenuation correction for brain PET imaging using deep neural network based on Dixon and ZTE MR images

2018 ◽  
Vol 63 (12) ◽  
pp. 125011 ◽  
Author(s):  
Kuang Gong ◽  
Jaewon Yang ◽  
Kyungsang Kim ◽  
Georges El Fakhri ◽  
Youngho Seo ◽  
...  
Keyword(s):  
Neural Network ◽  
Attenuation Correction ◽  
Pet Imaging ◽  
Deep Neural Network ◽  
Mr Images ◽  
Brain Pet

Classification and Identification of Power System Disturbances Using Wavalet and Artificial Neural Network Technique

2005 ◽  
Vol 2 (2) ◽  
pp. 25
Author(s):  
Noraliza Hamzah ◽  
Wan Nor Ainin Wan Abdullah ◽  
Pauziah Mohd Arsad
Keyword(s):  
Neural Network ◽  
Power Quality ◽  
Probabilistic Neural Network ◽  
Microsoft Excel ◽  
Waveform Data ◽  
The Neural Network ◽  
Harmonic Voltage ◽  
Power Quality Disturbances ◽  
Electronic Load ◽  
Wavelet Technique

Power Quality disturbances problems have gained widespread interest worldwide due to the proliferation of power electronic load such as adjustable speed drives, computer, industrial drives, communication and medical equipments. This paper presents a technique based on wavelet and probabilistic neural network to detect and classify power quality disturbances, which are harmonic, voltage sag, swell and oscillatory transient. The power quality disturbances are obtained from the waveform data collected from premises, which include the UiTM Sarawak, Faculty of Science Computer in Shah Alam, Jati College, Menara UiTM, PP Seksyen 18 and Putra LRT. Reliable Power Meter is used for data monitoring and the data is further processed using the Microsoft Excel software. From the processed data, power quality disturbances are detected using the wavelet technique. After the disturbances being detected, it is then classified using the Probabilistic Neural Network. Sixty data has been chosen for the training of the Probabilistic Neural Network and ten data has been used for the testing of the neural network. The results are further interfaced using matlab script code.  Results from the research have been very promising which proved that the wavelet technique and Probabilistic Neural Network is capable to be used for power quality disturbances detection and classification.

scholarly journals Accurate Transmission-Less Attenuation Correction Method for Amyloid-β Brain PET Using Deep Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (15) ◽  
pp. 1836
Author(s):  
Bo-Hye Choi ◽  
Donghwi Hwang ◽  
Seung-Kwan Kang ◽  
Kyeong-Yun Kim ◽  
Hongyoon Choi ◽  
...  
Keyword(s):  
Neural Network ◽  
Attenuation Correction ◽  
Complex Structure ◽  
Scatter Correction ◽  
Amyloid Β ◽  
Correction Method ◽  
Percentage Error ◽  
Similarity Coefficients ◽  
Brain Pet ◽  
Positron Emission

The lack of physically measured attenuation maps (μ-maps) for attenuation and scatter correction is an important technical challenge in brain-dedicated stand-alone positron emission tomography (PET) scanners. The accuracy of the calculated attenuation correction is limited by the nonuniformity of tissue composition due to pathologic conditions and the complex structure of facial bones. The aim of this study is to develop an accurate transmission-less attenuation correction method for amyloid-β (Aβ) brain PET studies. We investigated the validity of a deep convolutional neural network trained to produce a CT-derived μ-map (μ-CT) from simultaneously reconstructed activity and attenuation maps using the MLAA (maximum likelihood reconstruction of activity and attenuation) algorithm for Aβ brain PET. The performance of three different structures of U-net models (2D, 2.5D, and 3D) were compared. The U-net models generated less noisy and more uniform μ-maps than MLAA μ-maps. Among the three different U-net models, the patch-based 3D U-net model reduced noise and cross-talk artifacts more effectively. The Dice similarity coefficients between the μ-map generated using 3D U-net and μ-CT in bone and air segments were 0.83 and 0.67. All three U-net models showed better voxel-wise correlation of the μ-maps compared to MLAA. The patch-based 3D U-net model was the best. While the uptake value of MLAA yielded a high percentage error of 20% or more, the uptake value of 3D U-nets yielded the lowest percentage error within 5%. The proposed deep learning approach that requires no transmission data, anatomic image, or atlas/template for PET attenuation correction remarkably enhanced the quantitative accuracy of the simultaneously estimated MLAA μ-maps from Aβ brain PET.

scholarly journals Magnetic Resonace–Based Attenuation Correction for Micro–Single-Photon Emission Computed Tomography

2012 ◽  
Vol 11 (2) ◽  
pp. 7290.2011.00036 ◽  
Author(s):  
Vincent Keereman ◽  
Yves Fierens ◽  
Christian Vanhove ◽  
Tony Lahoutte ◽  
Stefaan Vandenberghe
Keyword(s):  
Attenuation Correction ◽  
Single Photon ◽  
Photon Emission ◽  
The Body ◽  
Emission Computed Tomography ◽  
Micro Ct ◽  
Mr Images ◽  
Brain Scans ◽  
The Brain ◽  
Photon Emission Computed Tomography

Attenuation correction is necessary for quantification in micro–single-photon emission computed tomography (micro-SPECT). In general, this is done based on micro–computed tomographic (micro-CT) images. Derivation of the attenuation map from magnetic resonance (MR) images is difficult because bone and lung are invisible in conventional MR images and hence indistinguishable from air. An ultrashort echo time (UTE) sequence yields signal in bone and lungs. Micro-SPECT, micro-CT, and MR images of 18 rats were acquired. Different tracers were used: hexamethylpropyleneamine oxime (brain), dimercaptosuccinic acid (kidney), colloids (liver and spleen), and macroaggregated albumin (lung). The micro-SPECT images were reconstructed without attenuation correction, with micro-CT-based attenuation maps, and with three MR-based attenuation maps: uniform, non-UTE-MR based (air, soft tissue), and UTE-MR based (air, lung, soft tissue, bone). The average difference with the micro-CT-based reconstruction was calculated. The UTE-MR-based attenuation correction performed best, with average errors ≤ 8% in the brain scans and ≤ 3% in the body scans. It yields nonsignificant differences for the body scans. The uniform map yields errors of ≤ 6% in the body scans. No attenuation correction yields errors ≥ 15% in the brain scans and ≥ 25% in the body scans. Attenuation correction should always be performed for quantification. The feasibility of MR-based attenuation correction was shown. When accurate quantification is necessary, a UTE-MR-based attenuation correction should be used.

Sign in / Sign up

Export Citation Format

Share Document