Wyniki wyszukiwania - BazTech

1

CCsNeT: Automated Corpus Callosum segmentation using fully convolutional network based on U-Net

Chandra Anjali, Verma Shrish, Raghuvanshi A.S., Bodhey Narendra Kuber

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 1

187--203

EN

Background: Corpus Callosum (CC) is the most prominent white matter bundle in the human brain that connects the left and right cerebral hemispheres. The present paper proposes a novel method for CC segmentation from 2D T1- weighted mid-sagittal brain MRI. The robust segmentation of CC in the mid-sagittal plane plays a vital role in the quantitative study of CC structural features related to various neurological disorders such as Autism, epilepsy, Alzheimer’s disease, and more. Methodology: In this perspective, the current work proposes a Fully Convolutional Network (FCN), a deep learning architecture-based U-Net model for automated CC segmentation from 2D brain MRI images referred to as CCsNeT. The architecture consists of a 35-layers deep, fully convolutional network with two paths, namely contracting and extracting, connected in a U-shape that automatically extracts spatial information. Results: This attempt uses the benchmark brain MRI database comprising ABIDE and OASIS for the experimental investigation. Compared to existing CC segmentation methodologies, the proposed CCsNeT presented improved results achieving Dice Coefficient = 96.74%, and Sensitivity = 97.01% with ABIDE dataset and were further validated against the variants of U-Net model U-Net++, MultiResU-Net, and CE-Net. Further, the performance of CCsNeT has been validated on OASIS and Real-Time Images dataset. Conclusion: Finally, the proposed CCsNeT extracts important CC characteristics such as CC area (CCA) and total brain area (TBA) to categorize the considered 2D MRI slices into control and autism spectrum disorder (ASD) groups, thereby minimizing the inter-observer and intra-observer variability.

2

Computer-aided detection of mesial temporal sclerosis based on hippocampus and cerebrospinal fluid features in MR images

Wang Huiquan, Ahmed S. Nizam, Mandal Mrinal

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 1

122--132

EN

Mesial temporal sclerosis (MTS) is the commonest brain abnormalities in patients with intractable epilepsy. Its diagnosis is usually performed by neuroradiologists based on visual inspection of magnetic resonance imaging (MRI) scans, which is a subjective and time-consuming process with inter-observer variability. In order to expedite the identification of MTS, an automated computer-aided method based on brain MRI characteristics is proposed in this paper. It includes brain segmentation and hippocampus extraction followed by calculating features of both hippocampus and its surrounding cerebrospinal fluid. After that, support vector machines are applied to the generated features to identify patients with MTS from those without MTS. The proposed technique is developed and evaluated on a data set comprising 15 normal controls, 18 left and 18 right MTS patients. Experimental results show that subjects are correctly classified using the proposed classifiers with an accuracy of 0.94 for both left and right MTS detection. Overall, the proposed method could identify MTS in brain MR images and show a promising performance, thus showing its potential clinical utility.

3

Cerebral edema segmentation using textural feature

Chaudhari Archana, Kulkarni Jayant

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 3

599--612

EN

Diagnostic imaging provides a vital tool in detection and analysis of Brain pathologies. Magnetic resonance imaging (MRI) provides an effective means for non-invasive mapping of anatomy and pathology in the brain. Pathologies like cerebral edema and tumors can spread in different tissues in the brain and can affect cognitive and other functions in the body. Accurate segmentation is therefore a challenging task. Human Brain consists of different soft tissues. These tissues can be characterized using different textures. The work presents an automatic method for segmentation using textural feature of the MR image. The texture of MR image is exploited using the gray co-occurrence matrix (GLCM). GLCM creates a textural feature map by taking into account the spatial dependence of the pixels and its angular relationship between the neighboring cell pairs. Local entropy as second order textural feature is used to capture the texture of MR image. Entropy computes the randomness in pixel intensities and helps in defining a unique texture of edema for segmentation. The marked contrast enhancement obtained in FLAIR sequence of the MR image is captured as textural information by local entropy and GLCM combination. The proposed method obtains a definite textural signature of edema as well as tumor for threshold selection. Experiments on publically available BRATS database yields an average accuracy of 96%, specificity of 97%, sensitivity of 61%, Dice Coefficient as 50% and structural similarity index of 0.88 for edema. The proposed method demonstrates encouraging results in automatic segmentation of edema as well as tumor core.