scholarly journals Radius-optimized efficient template matching for lesion detection from brain images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Subhranil Koley ◽  
Pranab K. Dutta ◽  
Iman Aganj
Keyword(s):  
Template Matching ◽  
Linear Time ◽  
Mathematical Formulation ◽  
Brain Lesion ◽  
Three Dimensional ◽  
Brain Lesions ◽  
Lesion Detection ◽  
Prediction Algorithm ◽  
Mathematical Framework ◽  
Satisfactory Outcome

AbstractComputer-aided detection of brain lesions from volumetric magnetic resonance imaging (MRI) is in demand for fast and automatic diagnosis of neural diseases. The template-matching technique can provide satisfactory outcome for automatic localization of brain lesions; however, finding the optimal template size that maximizes similarity of the template and the lesion remains challenging. This increases the complexity of the algorithm and the requirement for computational resources, while processing large MRI volumes with three-dimensional (3D) templates. Hence, reducing the computational complexity of template matching is needed. In this paper, we first propose a mathematical framework for computing the normalized cross-correlation coefficient (NCCC) as the similarity measure between the MRI volume and approximated 3D Gaussian template with linear time complexity, $${\mathbf{\mathcal{O}}}\left( {{\varvec{a}}_{{{\varvec{max}}}} {\varvec{N}}} \right)$$ O a max N , as opposed to the conventional fast Fourier transform (FFT) based approach with the complexity $${\mathbf{\mathcal{O}}}\left( {{\varvec{a}}_{{{\varvec{max}}}} {\varvec{N}}\log {\varvec{N}}} \right)$$ O a max N log N , where $${\varvec{N}}$$ N is the number of voxels in the image and $${\varvec{a}}_{{{\varvec{max}}}}$$ a max is the number of tried template radii. We then propose a mathematical formulation to analytically estimate the optimal template radius for each voxel in the image and compute the NCCC with the location-dependent optimal radius, reducing the complexity to $${\mathbf{\mathcal{O}}}\left( {\varvec{N}} \right)$$ O N . We test our methods on one synthetic and two real multiple-sclerosis databases, and compare their performances in lesion detection with FFT and a state-of-the-art lesion prediction algorithm. We demonstrate through our experiments the efficiency of the proposed methods for brain lesion detection and their comparable performance with existing techniques.

scholarly journals Radius-Optimized Efficient Template Matching for Lesion Detection from Brain Images

2020 ◽  
Author(s):  
Subhranil Koley ◽  
Pranab K. Dutta ◽  
Iman Aganj
Keyword(s):  
Template Matching ◽  
Linear Time ◽  
Mathematical Formulation ◽  
Brain Lesion ◽  
Three Dimensional ◽  
Brain Lesions ◽  
Lesion Detection ◽  
Prediction Algorithm ◽  
Mathematical Framework ◽  
Satisfactory Outcome

AbstractComputer-aided detection of brain lesions from volumetric magnetic resonance imaging (MRI) is in demand for fast and automatic diagnosis of neural diseases. The template-matching technique can provide satisfactory outcome for automatic localization of brain lesions; however, finding the optimal template size that maximizes similarity of the template and the lesion remains challenging. This increases the complexity of the algorithm and the requirement for computational resources, while processing large MRI volumes with three-dimensional (3D) templates. Hence, reducing the computational complexity of template matching is needed. In this paper, we first propose a mathematical framework for computing the normalized cross-correlation coefficient (NCCC) as the similarity measure between the MRI volume and approximated 3D Gaussian template with linear time complexity, 𝒪(amaxN), as opposed to the conventional fast Fourier transform (FFT) based approach with the complexity 𝒪(amaxNlog N), where N is the number of voxels in the image and amax is the number of tried template radii. We then propose a mathematical formulation to analytically estimate the optimal template radius for each voxel in the image and compute the NCCC with the location-dependent optimal radius, reducing the complexity to 𝒪(N). We test our methods on one synthetic and two real multiple-sclerosis databases, and compare its performance in lesion detection with FFT and a state-of-the-art lesion prediction algorithm. We demonstrate through our experiments the efficiency of the proposed method for brain lesion detection and its comparable performance with existing techniques.

Review of Brain Lesion Detection and Classification using Neuroimaging Analysis Techniques

2015 ◽  
Vol 74 (6) ◽  
Author(s):  
Norhashimah Mohd Saad ◽  
Syed Abdul Rahman Syed Abu Bakar ◽  
Ahmad Sobri Muda ◽  
Musa Mohd Mokji
Keyword(s):  
Differential Diagnosis ◽  
Magnetic Resonance ◽  
Brain Lesion ◽  
Brain Lesions ◽  
Lesion Detection ◽  
Subjective Time ◽  
Analysis Techniques ◽  
Indispensable Tool ◽  
Time Required ◽  
Processing Techniques

Neuroimaging plays an important role in the diagnosis brain lesions such as tumors, strokes and infections. Within this context, magnetic resonance diffusion-weighted imaging (DWI) is clinically recommended in the differential diagnosis of several brain lesions by providing detailed information regarding lesion based on the diffusion of water molecules. Conventionally, the differential diagnosis of brain lesions is performed visually by professional neuroradiologists during a highly subjective, time-consuming process. In response, computer-aided detection/diagnosis (CAD) has become a major topic of research and, in light of novel image processing techniques, has become a widespread, possibly indispensable tool for accurate diagnosis and reduce the time required. The objective of this review is to show the recent published techniques and state-of-the-art neuroimaging techniques for the human brain lesions. The review covers neuroimaging modalities, magnetic resonance imaging, DWI and analysis techniques for CAD in detecting and classifying of brain lesion. 

scholarly journals Contrast-Enhanced Black Blood MRI Sequence Is Superior to Conventional T1 Sequence in Automated Detection of Brain Metastases by Convolutional Neural Networks

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1016
Author(s):  
Jonathan Kottlors ◽  
Simon Geissen ◽  
Hannah Jendreizik ◽  
Nils Große Hokamp ◽  
Philipp Fervers ◽  
...  
Keyword(s):  
Neural Networks ◽  
Brain Metastases ◽  
Convolutional Neural Networks ◽  
Brain Lesion ◽  
Brain Lesions ◽  
Automated Detection ◽  
Lesion Detection ◽  
Black Blood ◽  
Mri Imaging ◽  
Contrast Enhanced

Background: in magnetic resonance imaging (MRI), automated detection of brain metastases with convolutional neural networks (CNN) represents an extraordinary challenge due to small lesions sometimes posing as brain vessels as well as other confounders. Literature reporting high false positive rates when using conventional contrast enhanced (CE) T1 sequences questions their usefulness in clinical routine. CE black blood (BB) sequences may overcome these limitations by suppressing contrast-enhanced structures, thus facilitating lesion detection. This study compared CNN performance in conventional CE T1 and BB sequences and tested for objective improvement of brain lesion detection. Methods: we included a subgroup of 127 consecutive patients, receiving both CE T1 and BB sequences, referred for MRI concerning metastatic spread to the brain. A pretrained CNN was retrained with a customized monolayer classifier using either T1 or BB scans of brain lesions. Results: CE T1 imaging-based training resulted in an internal validation accuracy of 85.5% vs. 92.3% in BB imaging (p < 0.01). In holdout validation analysis, T1 image-based prediction presented poor specificity and sensitivity with an AUC of 0.53 compared to 0.87 in BB-imaging-based prediction. Conclusions: detection of brain lesions with CNN, BB-MRI imaging represents a highly effective input type when compared to conventional CE T1-MRI imaging. Use of BB-MRI can overcome the current limitations for automated brain lesion detection and the objectively excellent performance of our CNN suggests routine usage of BB sequences for radiological analysis.

scholarly journals CSF proteome in multiple sclerosis subtypes related to brain lesion transcriptomes

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Maria L. Elkjaer ◽  
Arkadiusz Nawrocki ◽  
Tim Kacprowski ◽  
Pernille Lassen ◽  
Anja Hviid Simonsen ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Protein Phosphatase ◽  
Brain Lesion ◽  
Brain Lesions ◽  
Cns Diseases ◽  
Secondary Progressive ◽  
Apolipoprotein A ◽  
Proteomic Approach ◽  
Apolipoprotein C ◽  
Altered Proteins

AbstractTo identify markers in the CSF of multiple sclerosis (MS) subtypes, we used a two-step proteomic approach: (i) Discovery proteomics compared 169 pooled CSF from MS subtypes and inflammatory/degenerative CNS diseases (NMO spectrum and Alzheimer disease) and healthy controls. (ii) Next, 299 proteins selected by comprehensive statistics were quantified in 170 individual CSF samples. (iii) Genes of the identified proteins were also screened among transcripts in 73 MS brain lesions compared to 25 control brains. F-test based feature selection resulted in 8 proteins differentiating the MS subtypes, and secondary progressive (SP)MS was the most different also from controls. Genes of 7 out these 8 proteins were present in MS brain lesions: GOLM was significantly differentially expressed in active, chronic active, inactive and remyelinating lesions, FRZB in active and chronic active lesions, and SELENBP1 in inactive lesions. Volcano maps of normalized proteins in the different disease groups also indicated the highest amount of altered proteins in SPMS. Apolipoprotein C-I, apolipoprotein A-II, augurin, receptor-type tyrosine-protein phosphatase gamma, and trypsin-1 were upregulated in the CSF of MS subtypes compared to controls. This CSF profile and associated brain lesion spectrum highlight non-inflammatory mechanisms in differentiating CNS diseases and MS subtypes and the uniqueness of SPMS.

scholarly journals Risk factors for hip dislocation in dyskinetic cerebral palsy

2021 ◽  
Vol 29 (1) ◽  
pp. 230949902110011
Author(s):  
Kyoko Okuno ◽  
Yukihiro Kitai ◽  
Toru Shibata ◽  
Hiroshi Arai
Keyword(s):  
Risk Factors ◽  
Cerebral Palsy ◽  
Birth Weight ◽  
Gestational Age ◽  
Brain Mri ◽  
Brain Lesion ◽  
Brain Lesions ◽  
Lesion Location ◽  
Hip Displacement ◽  
Gmfcs Level

Purpose: To investigate the risk factors for hip displacement in patients with dyskinetic cerebral palsy (DCP). Methods: We evaluated 81 patients with DCP, 45 males and 36 females, aged 10–22 years, risk factors for hip displacement were evaluated using multivariate logistic regression analysis with primary brain lesions, Gross Motor Function Classification System (GMFCS) level, gestational age, birth weight, Cobb’s angle, and complication of epilepsy as independent factors. Hip displacement was defined as migration percentage >30%. Primary brain lesions were classified into globus pallidus (GP), thalamus and putamen (TP), and others using brain magnetic resonance imaging (MRI). Perinatal and clinical features were compared between patients with GP lesions and those with TP lesions. Results: Hip displacement was observed in 53 patients (67%). Higher GMFCS levels (p = 0.013, odds ratio [OR] 2.6) and the presence of GP lesions (p = 0.04, OR 16.5) were independent risk factors for hip displacement. Patients with GP lesions showed significantly higher GMFCS levels, more frequent hip displacement, and lower gestational age and birth weight than those with TP lesions. Conclusion: Primary brain lesion location may be an important factor in predicting hip displacement among patients with DCP. Appropriate risk assessment using brain MRI may contribute to the early detection and intervention of hip displacement because brain lesion location can be assessed during infancy before GMFCS level is decided.

scholarly journals Estimation of 6D Object Pose Using a 2D Bounding Box

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2939
Author(s):  
Yong Hong ◽  
Jin Liu ◽  
Zahid Jahangir ◽  
Sheng He ◽  
Qing Zhang
Keyword(s):  
Neural Network ◽  
Loss Function ◽  
Three Dimensional ◽  
Unit Vector ◽  
Prediction Algorithm ◽  
Computational Time ◽  
Bounding Box ◽  
Dimensional Unit ◽  
Bounding Boxes ◽  
Rgb Image

This paper provides an efficient way of addressing the problem of detecting or estimating the 6-Dimensional (6D) pose of objects from an RGB image. A quaternion is used to define an object′s three-dimensional pose, but the pose represented by q and the pose represented by -q are equivalent, and the L2 loss between them is very large. Therefore, we define a new quaternion pose loss function to solve this problem. Based on this, we designed a new convolutional neural network named Q-Net to estimate an object’s pose. Considering that the quaternion′s output is a unit vector, a normalization layer is added in Q-Net to hold the output of pose on a four-dimensional unit sphere. We propose a new algorithm, called the Bounding Box Equation, to obtain 3D translation quickly and effectively from 2D bounding boxes. The algorithm uses an entirely new way of assessing the 3D rotation (R) and 3D translation rotation (t) in only one RGB image. This method can upgrade any traditional 2D-box prediction algorithm to a 3D prediction model. We evaluated our model using the LineMod dataset, and experiments have shown that our methodology is more acceptable and efficient in terms of L2 loss and computational time.

The Use of Photogrammetry in Piping Design

1983 ◽  
Vol 197 (2) ◽  
pp. 125-138 ◽  
Author(s):  
P A Bracewell ◽  
U R Klement
Keyword(s):  
Information Retrieval ◽  
Mathematical Formulation ◽  
Three Dimensional ◽  
Cost Effective ◽  
Process Industry ◽  
Process Plant ◽  
Definition Of ◽  
High Degree ◽  
Positional Data

Piping design for ‘revamp’ projects in the process industry requires the retrieval of large amounts of ‘as-built’ data from existing process plant installations. Positional data with a high degree of accuracy are required. Photogrammetry, the science of measurement from photographs, was identified in Imperial Chemical Industries plc (ICI) as a suitable tool for information retrieval. The mathematical formulation enabling the definition of three-dimensional positions from photographic information is described. The process of using ICI's photogrammetric system for the definition of complete objects such as structures and pipes is illustrated. The need for specialized photogrammetric software for design purposes is explained. A case study describing how the photogrammetric system has been applied is described and graphical outputs from this exercise are shown. It is concluded that this particular photogrammetric system has proved to be a cost effective and accurate tool for the retrieval of ‘as-built’ information.

scholarly journals Three-dimensional cultured mesenchymal stem cells enhance repair of ischemic stroke through inhibition of microglia

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Yuejiao Li ◽  
Yankai Dong ◽  
Ye Ran ◽  
Yanan Zhang ◽  
Boyao Wu ◽  
...  
Keyword(s):  
Stem Cells ◽  
Mesenchymal Stem Cells ◽  
Ischemic Stroke ◽  
Proinflammatory Cytokines ◽  
Infarct Volume ◽  
Brain Lesion ◽  
Three Dimensional ◽  
Artery Occlusion ◽  
Rna Seq ◽  
The Brain

Abstract Background We show previously that three-dimensional (3D) spheroid cultured mesenchymal stem cells (MSCs) exhibit reduced cell size thus devoid of lung entrapment following intravenous (IV) infusion. In this study, we determined the therapeutic effect of 3D-cultured MSCs on ischemic stroke and investigated the mechanisms involved. Methods Rats underwent middle cerebral artery occlusion (MCAO) and reperfusion. 1 × 106 of 3D- or 2D-cultured MSCs, which were pre-labeled with GFP, were injected through the tail vain three and seven days after MCAO. Two days after infusion, MSC engraftment into the ischemic brain tissues was assessed by histological analysis for GFP-expressing cells, and infarct volume was determined by MRI. Microglia in the lesion were sorted and subjected to gene expressional analysis by RNA-seq. Results We found that infusion of 3D-cultured MSCs significantly reduced the infarct volume of the brain with increased engraftment of the cells into the ischemic tissue, compared to 2D-cultured MSCs. Accordingly, in the brain lesion of 3D MSC-treated animals, there were significantly reduced numbers of amoeboid microglia and decreased levels of proinflammatory cytokines, indicating attenuated activation of the microglia. RNA-seq of microglia derived from the lesions suggested that 3D-cultured MSCs decreased the response of microglia to the ischemic insult. Interestingly, we observed a decreased expression of mincle, a damage-associated molecular patterns (DAMPs) receptor, which induces the production of proinflammatory cytokines, suggestive of a potential mechanism in 3D MSC-mediated enhanced repair to ischemic stroke. Conclusions Our data indicate that 3D-cultured MSCs exhibit enhanced repair to ischemic stroke, probably through a suppression to ischemia-induced microglial activation.

Brain Lesion detection and Analysis- A Review

2021 ◽  
Author(s):  
V. Vinay Kumar ◽  
P. Grace Kanmani Prince
Keyword(s):  
Brain Lesion ◽  
Lesion Detection

Cerebral Mechanisms in Obsessive-Compulsive Disorder

CNS Spectrums ◽  
1998 ◽  
Vol 3 (7) ◽  
pp. 44-46
Author(s):  
Juan Carlos Goldar ◽  
Dario Rojas ◽  
Mariano Outes
Keyword(s):  
Obsessive Compulsive Disorder ◽  
Brain Lesion ◽  
Brain Lesions ◽  
Cingulate Gyrus ◽  
Cerebral Function ◽  
Obsessive Compulsive ◽  
Compulsive Disorder ◽  
Level Change ◽  
Clinical Level ◽  
Cerebral Mechanisms

AbstractBrain lesions cause different level change in cerebral function. They may conflict with the existing antagonistic mechanisms between the dorsal and ventral brain. At a clinical level, a dorsal brain lesion may constitute praxis disorders, while a ventral lesion may represent preventive inhibition. Further instinctive symptoms originate in the cingulate gyrus and its connections with the thalamic peduncle. This area may be an importan obsessive-compulsive disorder (OCD) pathway, that is utilized therapeutically during neurosurgical interventions in OCD.

Sign in / Sign up

Export Citation Format

Share Document