Method of Brain Structure Extraction for CT-Based Stroke Detection

Rutczynska, A.; Przelaskowski, Artur; Jasionowska, Magdalena; Ostrek, Grzegorz

doi:10.1007/978-3-642-13105-9_14

Cited by 5 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image data denoising and local contrast enhancement in multiscale domain of wavelets was proposed to extract hypodense areas in CT scans [14,16]. Rutczynska et al combined adaptive filtering (APAF implementation) and finite Gaussian Mixture Modeling (GMM) of brain structures with context-based enhancement [19]. Symmetry of tissue density distribution was statistically analyzed with a density-difference diagram calculated by digital subtraction of the histograms of the left and right hemispheres [20].…”

Section: Computerized Processing Of Imaged Hypodense Tissuementioning

confidence: 99%

Recovery of CT stroke hypodensity – An adaptive variational approach

Przelaskowski

2015

Computerized Medical Imaging and Graphics

Self Cite

View full text Add to dashboard Cite

Section: Computerized Processing Of Imaged Hypodense Tissuementioning

confidence: 99%

Recovery of CT stroke hypodensity – An adaptive variational approach

Przelaskowski

2015

Computerized Medical Imaging and Graphics

Self Cite

View full text Add to dashboard Cite

“…However, the disadvantage of this method is that patients have to endure prolonged CT scanning that may delay critical medical treatment for acute stroke patients and can result in progression of the stroke. Rutczyńska et al [ 17 ] proposed a method that uses regional growth in conjunction with Gaussian mixture models (GMM) to calculate the maximum expected value and then uses Bayes theorem to update the maximum chance of finding the stroke area. This method is only effective for large stroke region areas and fails to effectively detect areas of early stroke.…”

Section: Introductionmentioning

confidence: 99%

Ischemic Stroke Detection System with a Computer-Aided Diagnostic Ability Using an Unsupervised Feature Perception Enhancement Method

Tyan

Chin

et al. 2014

International Journal of Biomedical Imaging

View full text Add to dashboard Cite

We propose an ischemic stroke detection system with a computer-aided diagnostic ability using a four-step unsupervised feature perception enhancement method. In the first step, known as preprocessing, we use a cubic curve contrast enhancement method to enhance image contrast. In the second step, we use a series of methods to extract the brain tissue image area identified during preprocessing. To detect abnormal regions in the brain images, we propose using an unsupervised region growing algorithm to segment the brain tissue area. The brain is centered on a horizontal line and the white matter of the brain's inner ring is split into eight regions. In the third step, we use a coinciding regional location method to find the hybrid area of locations where a stroke may have occurred in each cerebral hemisphere. Finally, we make corrections and mark the stroke area with red color. In the experiment, we tested the system on 90 computed tomography (CT) images from 26 patients, and, with the assistance of two radiologists, we proved that our proposed system has computer-aided diagnostic capabilities. Our results show an increased stroke diagnosis sensitivity of 83% in comparison to 31% when radiologists use conventional diagnostic images.

show abstract

“…Their approach can be extended to other anatomical regions and vascular territories using image registration and multi-atlas labeling approach proposed in this paper. Rutczyńska et al [3] presented structures segmentation from brain CT by employing adaptive filtering, Gaussian mixture modeling and contextbased enhancement. Their approach was claimed better than region growing segmentation results.…”

Section: Introductionmentioning

confidence: 99%

Atlas image labeling of subcortical structures and vascular territories in brain CT images

Zhang

Nguyen

et al. 2013

2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

We propose a multi-atlas labeling method for subcortical structures and cerebral vascular territories in brain CT images. Each atlas image is registered to the query image by a non-rigid registration and the deformation is then applied to the labeling of the atlas image to obtain the labeling of the query image. Four label fusion strategies (single atlas, most similar atlas, major voting, and STAPLE) were compared. Image similarity values in non-rigid registration were calculated and used to select and rank atlases. Major voting fusion strategy gave the best accuracy, with DSC (Dice similarity coefficient) around 0.85 ± 0.03 for caudate, putamen, and thalamus. The experimental results also show that fusing more atlases does not necessarily yield higher accuracy and we should be able to improve accuracy and decrease computation cost at the same time by selecting a preferred set with the minimum number of atlases.

show abstract

Method of Brain Structure Extraction for CT-Based Stroke Detection

Cited by 5 publications

References 8 publications

Recovery of CT stroke hypodensity – An adaptive variational approach

Recovery of CT stroke hypodensity – An adaptive variational approach

Ischemic Stroke Detection System with a Computer-Aided Diagnostic Ability Using an Unsupervised Feature Perception Enhancement Method

Atlas image labeling of subcortical structures and vascular territories in brain CT images

Contact Info

Product

Resources

About