scholarly journals Automatic cerebrovascular segmentation methods-a review

2021 ◽  
Vol 10 (3) ◽  
pp. 576
Author(s):  
Fatma Taher ◽  
Neema Prakash
Keyword(s):  
Blood Vessels ◽  
Complex Shape ◽  
Automatic Segmentation ◽  
Cerebrovascular Diseases ◽  
And Topology ◽  
Cerebrovascular Segmentation ◽  
Segmentation Methods ◽  
3D Cnn ◽  
Cerebrovascular System ◽  
The Brain

Cerebrovascular diseases are one of the serious causes for the increase in mortality rate in the world which affect the blood vessels and blood supply to the brain. In order, diagnose and study the abnormalities in the cerebrovascular system, accurate segmentation methods can be used. The shape, direction and distribution of blood vessels can be studied using automatic segmentation. This will help the doctors to envisage the cerebrovascular system. Due to the complex shape and topology, automatic segmentation is still a challenge to the clinicians. In this paper, some of the latest approaches used for segmentation of magnetic resonance angiography images are explained. Some of such methods are deep convolutional neural network (CNN), 3dimentional-CNN (3D-CNN) and 3D U-Net. Finally, these methods are compared for evaluating their performance. 3D U-Net is the better performer among the described methods.

A Statistical Local Binary Fitting Model for Blood Vessel Segmentation

2013 ◽  
Vol 756-759 ◽  
pp. 3430-3434
Author(s):  
Shi Feng Zhao ◽  
Ming Quan Zhou ◽  
Kang Wang
Keyword(s):  
Blood Vessels ◽  
High Efficiency ◽  
Medical Images ◽  
Curve Evolution ◽  
Cerebrovascular Segmentation ◽  
Statistical Distribution Function ◽  
Local Binary Fitting Model ◽  
The Brain ◽  
Aided Diagnosis

Network structure such as blood vessels in medical images are important features for computer-aided diagnosis and follow-up of many diseases. In this study, a new model-based segmentation method is proposed to detect blood vessels in medical images. The Local Binary Fitting (LBF) model with statistical distribution function is used for this purpose. The brain tissues and cerebral vessels in the image are modeled by Gaussian distribution and uniform distribution respectively. The region distribution combined with the LBF model is used in curve evolution. And the level set method is developed to implement the curve evolution to assure high efficiency of the cerebrovascular segmentation. Comparisons with the LBF method show that our model can achieve better results.

scholarly journals 3DMSNET: 3D CNN Based Brain MRI Segmentation

2019 ◽  
Vol 8 (5S3) ◽  
pp. 107-110
Keyword(s):  
Nearest Neighbor ◽  
Automatic Segmentation ◽  
Brain Mri ◽  
Self Similarity ◽  
Brain Images ◽  
Multi Scale ◽  
Segmentation Methods ◽  
Scale Network ◽  
Automatic Methods ◽  
3D Cnn

Segmentation of the brain images has become an important task to analyze the abnormality in infants. Automatic methods are important as the infant brain growth has to be tracked and it is almost impossible for an individual to manually segment the MRI data on particular intervals. The manual segmentation tasks are time-consuming and require highly skilled professionals to segment images. Automatic segmentation methods have gained huge support for segmenting MRI images. Several segmentation methods lack accuracies due to nearest neighbor or self-similarity problems. The CNNs have outperformed the traditional methods and are proving to be more reliable day by day. The proposed method is a patch-based method which uses 3DMSnet (3D Multi-Scale Network) for segmentation. The model is evaluated on BrainWeb and other publicly available datasets.

scholarly journals AResU-Net: Attention Residual U-Net for Brain Tumor Segmentation

Symmetry ◽  
2020 ◽  
Vol 12 (5) ◽  
pp. 721 ◽  
Author(s):  
Jianxin Zhang ◽  
Xiaogang Lv ◽  
Hengbo Zhang ◽  
Bin Liu
Keyword(s):  
Brain Tumor ◽  
Automatic Segmentation ◽  
Attention Mechanism ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Local Responses ◽  
Segmentation Methods ◽  
Comparable Performance ◽  
Magnetic Resonance Imaging Mri ◽  
The Brain

Automatic segmentation of brain tumors from magnetic resonance imaging (MRI) is a challenging task due to the uneven, irregular and unstructured size and shape of tumors. Recently, brain tumor segmentation methods based on the symmetric U-Net architecture have achieved favorable performance. Meanwhile, the effectiveness of enhancing local responses for feature extraction and restoration has also been shown in recent works, which may encourage the better performance of the brain tumor segmentation problem. Inspired by this, we try to introduce the attention mechanism into the existing U-Net architecture to explore the effects of local important responses on this task. More specifically, we propose an end-to-end 2D brain tumor segmentation network, i.e., attention residual U-Net (AResU-Net), which simultaneously embeds attention mechanism and residual units into U-Net for the further performance improvement of brain tumor segmentation. AResU-Net adds a series of attention units among corresponding down-sampling and up-sampling processes, and it adaptively rescales features to effectively enhance local responses of down-sampling residual features utilized for the feature recovery of the following up-sampling process. We extensively evaluate AResU-Net on two MRI brain tumor segmentation benchmarks of BraTS 2017 and BraTS 2018 datasets. Experiment results illustrate that the proposed AResU-Net outperforms its baselines and achieves comparable performance with typical brain tumor segmentation methods.

Assessment of automatic segmentation accuracy with various point cloud density

2020 ◽  
Vol 961 (7) ◽  
pp. 47-55
Author(s):  
A.G. Yunusov ◽  
A.J. Jdeed ◽  
N.S. Begliarov ◽  
M.A. Elshewy
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Reference Data ◽  
Automatic Segmentation ◽  
Geometric Accuracy ◽  
Segmentation Method ◽  
Segmentation Methods ◽  
Segmentation Accuracy ◽  
Number Of Segments ◽  
Cloud Density

Laser scanning is considered as one of the most useful and fast technologies for modelling. On the other hand, the size of scan results can vary from hundreds to several million points. As a result, the large volume of the obtained clouds leads to complication at processing the results and increases the time costs. One way to reduce the volume of a point cloud is segmentation, which reduces the amount of data from several million points to a limited number of segments. In this article, we evaluated effect on the performance, the accuracy of various segmentation methods and the geometric accuracy of the obtained models at density changes taking into account the processing time. The results of our experiment were compared with reference data in a form of comparative analysis. As a conclusion, some recommendations for choosing the best segmentation method were proposed.

scholarly journals Fast, accurate, and reproducible automatic segmentation of the brain in T1-weighted volume MRI data

1999 ◽  
Vol 42 (1) ◽  
pp. 127-135 ◽  
Author(s):  
Louis Lemieux ◽  
Georg Hagemann ◽  
Karsten Krakow ◽  
Friedrich G. Woermann
Keyword(s):  
Automatic Segmentation ◽  
The Brain

Differential diagnosis of spontaneous intracranial hemorrhage in young

2021 ◽  
Vol 22 (1) ◽  
pp. 83-86
Author(s):  
O. A. Kicherova ◽  
◽  
L. I. Reikhert ◽  
O. N. Bovt ◽  
◽  
...  
Keyword(s):  
Hemorrhagic Stroke ◽  
Young Patients ◽  
Vascular Diseases ◽  
Cerebrovascular Diseases ◽  
Intracerebral Hematoma ◽  
Toxic Substances ◽  
Brain Substance ◽  
Secondary All ◽  
Visualization Techniques ◽  
The Brain

In recent years, cerebral vascular diseases have been increasingly detected in young patients. It is due not only to better physicians’ knowledge about this pathology, but also to the improvement of its diagnosis methods. Modern neuroimaging techniques allow us to clarify the nature of hemorrhage, to determine the volume and location of intracerebral hematoma, and to establish the degree of concomitant edema and dislocation of the brain. However, despite the high accuracy of the research, it is not always possible to establish the cause that led to a brain accident, which greatly affects the tactics of management and outcomes in this category of patients. A special feature of the structure of cerebrovascular diseases of young people is the high proportion of hemorrhagic stroke, the causes of which are most often arterio-venous malformations. Meanwhile, there are a number of other causes that can lead to hemorrhage into the brain substance. These include disorders of blood clotting, and various vasculitis, and exposure to toxic substances and drugs, and tumor formations (primary and secondary). All these pathological factors outline the range of diagnostic search in young patients who underwent hemorrhagic stroke. Diagnosis of these pathological conditions with the help of modern visualization techniques is considered to be easy, but this is not always the case. In this article, the authors give their own clinical observation of a hemorrhagic stroke in a young patient, which demonstrates the complexity of the diagnostic search in patients with this pathology.

TAMI-22. SEGMENTATION OF DISTINCT TUMOR HALLMARKS OF GLIOBLASTOMA ON DIGITAL HISTOPATHOLOGY USING A HIERARCHICAL DEEP LEARNING APPROACH

2021 ◽  
Vol 23 (Supplement_6) ◽  
pp. vi202-vi203
Author(s):  
Alvaro Sandino ◽  
Ruchika Verma ◽  
Yijiang Chen ◽  
David Becerra ◽  
Eduardo Romero ◽  
...  
Keyword(s):  
Deep Learning ◽  
Blood Vessels ◽  
Network Architecture ◽  
Automatic Segmentation ◽  
Area Under The Curve ◽  
Primary Treatment ◽  
Microvascular Proliferation ◽  
Vascular Proliferation ◽  
Testing Accuracy ◽  
Future Work

Abstract PURPOSE Glioblastoma is a highly heterogeneous brain tumor. Primary treatment for glioblastoma involves maximally-safe surgical resection. After surgery, resected tissue slides are visually analyzed by neuro-pathologists to identify distinct histological hallmarks characterizing glioblastoma including high cellularity, necrosis, and vascular proliferation. In this work, we present a hierarchical deep learning-based strategy to automatically segment distinct Glioblastoma niches including necrosis, cellular tumor, and hyperplastic blood vessels, on digitized histopathology slides. METHODS We employed the IvyGap cohort for which Hematoxylin and eosin (H&E) slides (digitized at 20X magnification) from n=41 glioblastoma patients were available. Additionally, expert-driven segmentations of cellular tumor, necrosis, and hyperplastic blood vessels (along with other histological attributes) were made available. We randomly employed n=120 slides from 29 patients for training, n=38 slides from 6 cases for validation, and n=30 slides from 6 patients to feed our deep learning model based on Residual Network architecture (ResNet-50). ~2,000 patches of 224x224 pixels were sampled for every slide. Our hierarchical model included first segmenting necrosis from non-necrotic (i.e. cellular tumor) regions, and then from the regions segmented as non-necrotic, identifying hyperplastic blood-vessels from the rest of the cellular tumor. RESULTS Our model achieved a training accuracy of 94%, and a testing accuracy of 88% with an area under the curve (AUC) of 92% in distinguishing necrosis from non-necrotic (i.e. cellular tumor) regions. Similarly, we obtained a training accuracy of 78%, and a testing accuracy of 87% (with an AUC of 94%) in identifying hyperplastic blood vessels from the rest of the cellular tumor. CONCLUSION We developed a reliable hierarchical segmentation model for automatic segmentation of necrotic, cellular tumor, and hyperplastic blood vessels on digitized H&E-stained Glioblastoma tissue images. Future work will involve extension of our model for segmentation of pseudopalisading patterns and microvascular proliferation.

Perivascular (Virchow–Robin) spaces

2021 ◽  
pp. 86-89
Keyword(s):  
Blood Vessels ◽  
Shape Change ◽  
Lymphatic Drainage ◽  
Brain Regions ◽  
Mechanical Trauma ◽  
Normal Brain ◽  
Perivascular Spaces ◽  
Mr Images ◽  
Lenticulostriate Artery ◽  
The Brain

Perivascular spaces; also known as the Virchow-Robin Spaces, they are pleurally lined, interstitial fluid-filled areas that surround certain blood vessels in various organs, especially the perforating arteries in the brain, with an immunological function. Dilated perivascular spaces are divided into three types. The first of these is on the lenticulostriate artery, the second is in the cortex following the path of the medullary artery, and the third is in the midbrain. Perivascular spaces can be detected as areas of dilatation on MR images. Although a limited number of perivascular spaces can be seen in a normal brain, the increase in the number of these spaces has been associated with the incidence of various neurodegenerative diseases. Different theories have been suggested about the tendency of the perivascular spaces to expand. Current theories include mechanical trauma due to cerebrospinal fluid pulsing, elongation of penetrating blood vessels, unusual vascular permeability, and increased fluid exudation. In addition, the brain tissue atrophy that occurs with aging; It is thought to contribute to the widening of perivascular spaces by causing shrinkage of arteries, altered arterial wall permeability, obstruction of lymphatic drainage pathways and vascular demyelination. It is assumed that the clinical significance of the dilation tendencies of the perivascular spaces is based on shape change rather than size. These spaces have been mostly observed in brain regions such as corpus callosum, cingulate gyrus, dentate nucleus, substantia nigra and various arterial basins including lenticulostriate artery and mesencephalothalamic artery. In conclusion, when sections are taken on MR imaging, it is possible that perivascular spaces may be confused with microvascular diseases and some neurodegenerative changes. In addition, perivascular spaces can be seen without pathological significance. Therefore, it would be appropriate to investigate the etiological relationship by evaluating the radiological findings and clinical picture together.

Two Cases of Atheroma of the Blood Vessels at the Base of the Brain, with Remarks upon the Symptoms, Diagnosis, Prognosis, and Pathological Condition in that Affection

1870 ◽  
Vol 16 (73) ◽  
pp. 52-58
Author(s):  
J. T. Sabben
Keyword(s):  
Blood Vessels ◽  
Pathological Condition ◽  
Cerebral Arteries ◽  
General Paralysis ◽  
Brain Substance ◽  
The Brain

In publishing the following cases, recently under my charge, of mental derangement dependent upon atheromatous deposit in the coats of the larger cerebral arteries, without any apparent disease of the brain substance, I desire, if possible, to define the symptoms of that condition during life, so as to enable them to be distinguished from those of general paralysis, with which I believe them often to be confused.

scholarly journals Meningeal Tumors Induced in Calves with the Bovine Cutaneous Papilloma Virus

1969 ◽  
Vol 6 (2) ◽  
pp. 135-145 ◽  
Author(s):  
D. F. Brobst ◽  
G. C. Dulac
Keyword(s):  
Blood Vessels ◽  
Viral Antigen ◽  
Papilloma Virus ◽  
Meningeal Tumors ◽  
The Brain

Fibromatous tumors were induced in the meninges of calves by inoculating the meninges with a suspension of bovine cutaneous papillomas or by implanting bovine cutaneous papillomas into the brain. Meningeal tumors were observed to occur as early as 20 days after inoculation. Meningeal tumors from calves killed 90 and 145 days after inoculation extended into the brain along the course of blood vessels. Metastasis, however, was not observed. Evidence that the induced meningeal tumors contained viral antigen was lacking.

Sign in / Sign up

Export Citation Format

Share Document