Analysis of Ischemic Stroke MR Images by Means of Brain Atlases of Anatomy and Blood Supply Territories

2006 ◽  
Vol 13 (8) ◽  
pp. 1025-1034 ◽  
Author(s):  
Wieslaw L. Nowinski ◽  
Guoyu Qian ◽  
Bhanu Prakash Kirgaval Nagaraja ◽  
Arumugam Thirunavuukarasuu ◽  
Qingmao Hu ◽  
...  
2011 ◽  
Vol 4 (2) ◽  
pp. 105-109 ◽  
Author(s):  
Gurpreet S Sandhu ◽  
Pankit T Parikh ◽  
Daniel P Hsu ◽  
Kristine A Blackham ◽  
Robert W Tarr ◽  
...  

Author(s):  
Rajinikanth V. ◽  
Suresh Chandra Satapathy ◽  
Nilanjan Dey ◽  
Hong Lin

An ischemic stroke (IS) naturally originates with rapid onset neurological shortfall, which can be verified by analyzing the internal regions of brain. Computed tomography (CT) and magnetic resonance image (MRI) are the commonly used non-invasive medical examination techniques used to record the brain abnormalities for clinical study. In order to have a pre-opinion regarding the brain abnormality in clinical level, it is essential to use a suitable image processing tool to appraise the digital CT/MR images. In this chapter, a hybrid image processing technique based on the social group optimization assisted Tsallis entropy and watershed segmentation (WS) is proposed to examine ischemic stroke region from digital CT/MR images. For the experimental study, the digital CT/MRI datasets like Radiopedia, BRATS-2013, and ISLES-2015 are considered. Experimental result of this study confirms that, proposed hybrid approach offers superior results on the considered image datasets.


2002 ◽  
Vol 43 (2) ◽  
pp. 211 ◽  
Author(s):  
Hyun Sook Kim ◽  
Dong Ik Kim ◽  
Jong Doo Lee ◽  
Eun Kee Jeong ◽  
Tae Sub Chung ◽  
...  
Keyword(s):  

2004 ◽  
Vol 100 (3) ◽  
pp. 541-546 ◽  
Author(s):  
Erich O. Richter ◽  
Tasnuva Hoque ◽  
William Halliday ◽  
Andres M. Lozano ◽  
Jean A. Saint-Cyr

Object. The subthalamic nucleus (STN) is a target in surgery for Parkinson disease, but its location according to brain atlases compared with its position on an individual patient's magnetic resonance (MR) images is incompletely understood. In this study both the size and location of the STN based on MR images were compared with those on the Talairach and Tournoux, and Schaltenbrand and Wahren atlases. Methods. The position of the STN relative to the midcommissural point was evaluated on 18 T2-weighted MR images (2-mm slices). Of 35 evaluable STNs, the most anterior, posterior, medial, and lateral borders were determined from axial images, dorsal and ventral borders from coronal images. These methods were validated using histological measurements in one case in which a postmortem examination was performed. The mean length of the anterior commissure—posterior commissure was 25.8 mm. Subthalamic nucleus borders derived from MR imaging were highly variable: anterior, 4.1 to −3.7 mm relative to the midcommissural point; posterior, 4.2 to 10 mm behind the midcommissural point; medial, 7.9 to 12.1 mm from the midline; lateral, 12.3 to 15.4 mm from the midline; dorsal, 0.2 to 4.2 mm below the intercommissural plane; and ventral, 5.7 to 9.9 mm below the intercommissural plane. The position of the anterior border on MR images was more posterior, and the medial border more lateral, than its position in the brain atlases. The STN was smaller on MR images compared with its size in atlases in the anteroposterior (mean 5.9 mm), mediolateral (3.7 mm), and dorsoventral (5 mm) dimensions. Conclusions. The size and position of the STN are highly variable, appearing to be smaller and situated more posterior and lateral on MR images than in atlases. Care must be taken in relying on coordinates relative to the commissures for targeting of the STN.


2011 ◽  
Vol 65 (5) ◽  
pp. 257-263 ◽  
Author(s):  
Hyang-I Park ◽  
Jae-Kwan Cha ◽  
Myung-Jin Kang ◽  
Dae-Hyun Kim ◽  
Nam-Tae Yoo ◽  
...  

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Bin Zhao ◽  
Zhiyang Liu ◽  
Guohua Liu ◽  
Chen Cao ◽  
Song Jin ◽  
...  

Acute ischemic stroke (AIS) has been a common threat to human health and may lead to severe outcomes without proper and prompt treatment. To precisely diagnose AIS, it is of paramount importance to quantitatively evaluate the AIS lesions. By adopting a convolutional neural network (CNN), many automatic methods for ischemic stroke lesion segmentation on magnetic resonance imaging (MRI) have been proposed. However, most CNN-based methods should be trained on a large amount of fully labeled subjects, and the label annotation is a labor-intensive and time-consuming task. Therefore, in this paper, we propose to use a mixture of many weakly labeled and a few fully labeled subjects to relieve the thirst of fully labeled subjects. In particular, a multifeature map fusion network (MFMF-Network) with two branches is proposed, where hundreds of weakly labeled subjects are used to train the classification branch, and several fully labeled subjects are adopted to tune the segmentation branch. By training on 398 weakly labeled and 5 fully labeled subjects, the proposed method is able to achieve a mean dice coefficient of 0.699 ± 0.128 on a test set with 179 subjects. The lesion-wise and subject-wise metrics are also evaluated, where a lesion-wise F1 score of 0.886 and a subject-wise detection rate of 1 are achieved.


Author(s):  
Sunil Babu Melingi ◽  
V. Vijayalakshmi

Background: The sub-acute ischemic stroke is the most basic illnesses reason for death on the planet. We evaluate the impact of segmentation technique during the time of breaking down the capacities of the cerebrum. </P><P> Objective: The main objective of this paper is to segment the ischemic stroke lesions in Magnetic Resonance (MR) images in the presence of other pathologies like neurological disorder, encephalopathy, brain damage, Multiple sclerosis (MS). Methods: In this paper, we utilize a hybrid way to deal with segment the ischemic stroke from alternate pathologies in magnetic resonance (MR) images utilizing Random Decision Forest (RDF) and Gravitational Search Algorithm (GSA). The RDF approach is an effective machine learning approach. Results: The RDF strategy joins two parameters; they are; the number of trees in the forest and the number of leaves per tree; it runs quickly and proficiently when dealing with vast data. The GSA algorithm is utilized to optimize the RDF data for choosing the best number of trees and the number of leaves per tree in the forest. Conclusion: This paper provides a new hybrid GSA-RDF classifier technique to segment the ischemic stroke lesions in MR images. The experimental results demonstrate that the proposed technique has the Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Bias Error (MBE) ranges are 16.5485 %, 7.2654 %, and 2.4585 %individually. The proposed RDF-GSA algorithm has better precision and execution when compared with the existing ischemic stroke segmentation method.


2015 ◽  
Vol 21 (2) ◽  
pp. 215-217 ◽  
Author(s):  
Zhen-Sheng Liu ◽  
Long-Jiang Zhou ◽  
Yong Sun ◽  
Xiong-Wei Kuang ◽  
Wei Wang ◽  
...  

We reported a case of acute embolic occlusion of the middle cerebral artery with a patent accessory middle cerebral artery. Because of the presence of sufficient collateral blood supply from the accessory middle cerebral artery, the patient only underwent transient ischemic attack and did not need endovascular treatment. There was mild infarction in the basal ganglia and temporal lobe, NIHSS score of the patient at discharge seven days after stroke onset was 0, and modified Rankin scale score at 90 days was 0.


Sign in / Sign up

Export Citation Format

Share Document