Knowledge-based 3D segmentation of the brain in MR images for quantitative multiple sclerosis lesion tracking

1997 ◽  
Author(s):  
Elizabeth Fisher ◽  
Robert M. Cothren, Jr. ◽  
Jean A. Tkach ◽  
Thomas J. Masaryk ◽  
J. Fredrick Cornhill
Keyword(s):  
Multiple Sclerosis ◽  
Multiple Sclerosis Lesion ◽  
Mr Images ◽  
3D Segmentation ◽  
Knowledge Based ◽  
The Brain

5-37-06 Semiautomatic segmentation of MR images of the brain in multiple sclerosis

1997 ◽  
Vol 150 ◽  
pp. S328
Author(s):  
P. Dastidar ◽  
T. Vahvelainen ◽  
T. Heinonen ◽  
P. Ryymin ◽  
I. Elovaara ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Mr Images ◽  
Semiautomatic Segmentation ◽  
The Brain

scholarly journals Learning a CNN on multiple sclerosis lesion segmentation with self-supervision

2020 ◽  
Vol 2020 (17) ◽  
pp. 3-1-3-7
Author(s):  
Alexandre Fenneteau ◽  
Pascal Bourdon ◽  
David Helbert ◽  
Christine Fernandez-Maloigne ◽  
Christophe Habas ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Multiple Sclerosis Lesion ◽  
Image Size ◽  
Mr Images ◽  
Traffic Sign ◽  
Demyelinating Lesions ◽  
The Central Nervous System ◽  
Pros And Cons ◽  
Segmentation Task ◽  
High Level

Multiple Sclerosis (MS) is a chronic, often disabling, autoimmune disease affecting the central nervous system and characterized by demyelination and neuropathic alterations. Magnetic Resonance (MR) images plays a pivotal role in the diagnosis and the screening of MS. MR images identify and localize demyelinating lesions (or plaques) and possible associated atrophic lesions whose MR aspect is in relation with the evolution of the disease. We propose a novel MS lesions segmentation method for MR images, based on Convolutional Neural Networks (CNNs) and partial self-supervision and studied the pros and cons of using self-supervision for the current segmentation task. Investigating the transferability by freezing the firsts convolutional layers, we discovered that improvements are obtained when the CNN is retrained from the first layers. We believe such results suggest that MRI segmentation is a singular task needing high level analysis from the very first stages of the vision process, as opposed to vision tasks aimed at day-to-day life such as face recognition or traffic sign classification. The evaluation of segmentation quality has been performed on full image size binary maps assembled from predictions on image patches from an unseen database.

scholarly journals The Brain–Heart Link: A Case Report of a Critically Located Multiple Sclerosis Lesion in the Brainstem Leading to Recurrent Takotsubo Syndrome

2021 ◽  
Vol 8 ◽  
Author(s):  
Florentijn Risseeuw ◽  
Pegah Masrori ◽  
Ingrid Baar ◽  
Simon Nicolay ◽  
Constantijn Franssen ◽  
...  
Keyword(s):  
Risk Factors ◽  
Multiple Sclerosis ◽  
Respiratory Failure ◽  
Neurological Diseases ◽  
Stress Cardiomyopathy ◽  
Multiple Sclerosis Lesion ◽  
Takotsubo Syndrome ◽  
Aggressive Treatment ◽  
Cardiovascular Comorbidities ◽  
The Brain

Various central nervous system (CNS) diseases, including neurovascular and neuroinflammatory diseases, can lead to stress cardiomyopathy, also known as Takotsubo syndrome (TTS). We present a case of a 69-year-old woman with cardiovascular comorbidities, suffering from repeated episodes of TTS and respiratory failure due to a critical lesion in the brainstem, leading to a diagnosis of multiple sclerosis (MS). Despite aggressive treatment, intractable and recurrent symptoms in our patient occurred. Repeated bouts of autonomic dysfunction and respiratory failure ultimately led to installment of palliative care and the patient passing away. TTS should raise suspicion for underlying neurological diseases. Thorough questioning of previous neurological symptoms and extensive neurological workup is warranted. MS should be considered as a trigger of TTS also in elderly patients with cardiovascular risk factors.

scholarly journals Distribution of multiple sclerosis lesions detected by brain magnetic resonance imaging in Erbil city

2021 ◽  
Vol 25 (1) ◽  
pp. 446-455
Author(s):  
Dina Tawfeeq ◽  
Shawnam Dawood
Keyword(s):  
Magnetic Resonance Imaging ◽  
Multiple Sclerosis ◽  
Magnetic Resonance ◽  
Corpus Callosum ◽  
Brain Stem ◽  
Signal Intensity ◽  
Brain Regions ◽  
Multiple Sclerosis Lesion ◽  
Resonance Imaging ◽  
The Brain

Background and objective: Many epidemiological studies and clinical manifestation studies of multiple sclerosis have been done in Iraq. Up to our knowledge, no such observational study to the radiological feature of the multiple sclerosis lesion has been done yet in Erbil in comparison to other worldwide studies. This study aimed to assess the distribution of multiple sclerosis lesions in brain regions detected by magnetic resonance imaging among Erbil population. Methods: This was a cross-sectional study conducted at the College of Medicine, Hawler Medical University, from April 2018 to July 2019. A review of magnetic resonance imaging scans of the brain of 120 patients was done. Special attention was directed toward identifying the variance in multiple sclerosis lesions distribution in the brain regions and their MR signal intensity characteristics. Results: Periventricular lesions were observed in more than 90% of the study sample. The next common was juxtacortical lesions (24.8%), followed by corpus callosum lesions (16.8 %), while brain stem lesions were the least observed proportions. No significant difference was detected in the distribution of multiple sclerosis lesions among ethnicities and genders, except for basal ganglia lesions, which were significantly more common in women (P = 0.016).The magnetic resonance imaging signal intensity of the lesion was significantly variable among disease duration. Conclusion: The T2 hyper intense lesions were most commonly seen in the periventricular region. Juxtacortical and corpus callosum lesions were also frequently observed. The proportions of the brain stem and cerebellum lesions appeared to be lower in comparison to previous studies. Keywords: Multiple Sclerosis; Magnetic Resonance Imaging; Distribution; Lesion.

FULLY AUTOMATED PEELING TECHNIQUE FOR T1-WEIGHTED, HIGH-QUALITY MR HEAD SCANS

2004 ◽  
Vol 04 (02) ◽  
pp. 141-156 ◽  
Author(s):  
RAVINDA G. N. MEEGAMA ◽  
JAGATH C. RAJAPAKSE
Keyword(s):  
White Matter ◽  
Healthy Subjects ◽  
Three Dimensional ◽  
Magnetic Resonance Images ◽  
Mr Images ◽  
3D Segmentation ◽  
High Quality ◽  
Anatomical Structures ◽  
Present Technique ◽  
The Brain

In order to conduct many non-intrusive clinical studies of the human brain, an accurate model that is capable of extracting the brain matter from magnetic resonance images (MRI) is required. We present a fully automated two-stage procedure to extract the brain matter accurately from a database of T1-weighted, high-quality MRI of healthy subjects. The procedure is initiated using a three dimensional (3D) segmentation process to separate the brain from other anatomical structures. The extracted brain is then subjected to an adaptive filter to remove cerebro-spinal fluid that fills sulcal cavities. The experiments clearly demonstrate the capability of the present technique in accurately peeling the brain. The accuracy of the results is tested using relative gray and white matter concentrations of both simulated and real MR images.

scholarly journals Multiple Sclerosis Lesion Segmentation Using Statistical and Topological Atlases

2008 ◽  
Author(s):  
Navid Shiee ◽  
Pierre-Louis Bazin ◽  
Dzung L. Pham
Keyword(s):  
Multiple Sclerosis ◽  
Magnetic Resonance Images ◽  
Multiple Sclerosis Lesion ◽  
Lesion Segmentation ◽  
Brain Images ◽  
Analysis Techniques ◽  
Segmentation Methods ◽  
Fully Automatic ◽  
The Brain ◽  
Statistical Atlas

This paper presents a new fully automatic method for segmentation of brain images that possess multiple sclerosis (MS) lesions. Multichannel magnetic resonance images are used to delineate multiple sclerosis lesions while segmenting the brain into its major structures. The method is an atlas based segmentation technique employing a topological atlas as well as a statistical atlas. An advantage of this approach is that all segmented structures are topologically constrained, thereby allowing subsequent processing with cortical unfolding or diffeomorphic shape analysis techniques. Validation on data from two studies demonstrates that the method has an accuracy comparable with other MS lesion segmentation methods, while simultaneously segmenting the whole brain.

scholarly journals Segmentation of Multiple Sclerosis Lesion in Brain MR Images Using Fuzzy C-Means

2018 ◽  
Vol 9 (2) ◽  
pp. 37-45
Author(s):  
Saba Heidari Gheshlaghi ◽  
Abolfazl Madani ◽  
AmirAbolfazl Suratgar ◽  
Fardin Faraji
Keyword(s):  
Multiple Sclerosis ◽  
Multiple Sclerosis Lesion ◽  
Mr Images ◽  
Fuzzy C Means ◽  
Brain Mr Images
Sign in / Sign up

Export Citation Format

Share Document