Ischemic Stroke Lesion Segmentation Using Local Gradient and Texture Features
نویسندگان
چکیده
This work proposes fully automatic ischemic stroke lesion segmentation in multimodality brain MRI by extending our prior brain tumor segmentation (BTS) work [1]. The extensions of the BTS method include development of relevant MR image intensity inhomogeneity correction, several new features and feature ranking methods. We characterized brain lesions with multiple features such as piece-wise triangular prism surface area (PTPSA), multi-fractal Brownian motion (mBm), structure tensor based local gradient, regular intensities and intensity differences of MRI modalities. As in BTS, we used classical Random Forest (RF) [2] to classify the brain tissues as lesion or background.The method is evaluated on 28 patients’ images having sub-acute ischemic stroke lesions from ISLES2015 SISS challenge dataset [3].
منابع مشابه
Automatic Ischemic Stroke Lesion Segmentation in Multi-spectral MRI Images Using Random Forests Classifier
This paper presents an automated segmentation framework for ischemic stroke lesion segmentation in multi-spectral MRI images. The framework is based on a random forests (RF), which is an ensemble learning technique that generates several classifiers and combines their results in order to make decisions. In RF, we employ several meaningful features such as intensities, entropy, gradient etc. to ...
متن کاملA hierarchical Convolutional Neural Network for Segmentation of Stroke Lesion in 3D Brain MRI
Introduction: Brain tumors such as glioma are among the most aggressive lesions, which result in a very short life expectancy in patients. Image segmentation is highly essential in medical image analysis with applications, particularly in clinical practices to treat brain tumors. Accurate segmentation of magnetic resonance data is crucial for diagnostic purposes, planning surgical treatments, a...
متن کاملCombination of CNN and Hand-crafted feature for Ischemic Stroke Lesion Segmentation
CNN can automatically learn discriminative local features and give superior performance than hand-crafted features in various applications such as image classification, semantic segmentation and object detection. CNN has also been applied to MRI brain image analysis and achieved state-of-the-art results for brain tumor region segmentation [3, 4], stroke lesion segmentation [4], and mircobleeds ...
متن کاملA hierarchical Convolutional Neural Network for Segmentation of Stroke Lesion in 3D Brain MRI
Introduction: Brain tumors such as glioma are among the most aggressive lesions, which result in a very short life expectancy in patients. Image segmentation is highly essential in medical image analysis with applications, particularly in clinical practices to treat brain tumors. Accurate segmentation of magnetic resonance data is crucial for diagnostic purposes, planning surgical treatments, a...
متن کاملSilent subcortical brain infarction
Introduction: The silent brain lesions detected by MRI were fairly common not only in first-ever stroke but also in normal elderly subjects. Some recent studies show the possible role of silent sub-cortical brain infarction in ischemic stroke. The aim of this study was to evaluate the frequency of silent sub-cortical brain infarction in acute first-ever ischemic stroke. Methods: In this descrip...
متن کامل