Brain MR Image Lesion Identification Using Threshold-Based Segmentation Techniques

Fuzzy c-means (FCM) is a popular clustering method for image segmentation. However, FCM has difficulties in handling artifacts in brain magnetic resonance imaging (MRI), especially when it comes to bias field and noise. We propose a novel multiple-surface-approximation-based FCM with interval membership method for simultaneous bias correction and segmentation of Brain MRI. First, multiple surface representation of bias field is embedded into FCM to estimate and correct bias field. Then memberships of the improved FCM are extended to intervals. After the extension, clustering centers of different MR brain tissues could be solved more properly by the proposed method. Moreover, the proposed method is less sensitive to noise by introducing effects of neighboring pixels. Experiments conducted on artificial images and synthetic and real clinical Brain MRI show that the proposed method is effective and obtains better results of both bias field correction and segmentation than comparing methods.

Ischemic stroke lesion segmentation using stacked sparse autoencoder

Although deep learning methods have been widely applied in medical image lesion segmentation, it is still challenging to apply it for segmenting ischemic stroke lesions, which are different from brain tumors in lesion characteristics, segmentation difficulty, algorithm maturity, and segmentation accuracy. Three main stages are used to describe the manifestations of stroke. For acute ischemic stroke, the size of the lesions is similar to that of the brain tumor, and the current deep learning methods have been able to achieve a high segmentation accuracy. For sub-acute and chronic ischemic stroke, the segmentation results of mainstream deep learning algorithms are still unsatisfactory as lesions in these stages are small and diffuse. By using three scientific search engines including CNKI, Web of Science and Google Scholar, this paper aims to comprehensively understand the state-of-the-art deep learning algorithms applied to segment ischemic stroke lesions. For the first time, this paper discusses the current situation, challenges, and development directions of deep learning algorithms applied to ischemic stroke lesion segmentation in different stages. In the future, a system that can directly identify different stroke stages and automatically select the suitable network architecture for the stroke lesion segmentation needs to be proposed.

Automatic segmentation of Magnetic Resonance Images (MRI) for tissue classification becomes more challenging when the image is corrupted with noise and intensity non-uniformity (INU). Several fuzzy clustering based statistical retrospective methods exist for simultaneous correction and segmentation of images but most of them fail to be robust in presence of noise, outliers and INU artifacts. In this paper, a hybridization of rough c-means and spatial fuzzy c-means clustering is presented whose objective function has been modified to accommodate INU field as well. While the membership function of fuzzy sets enables efficient handling of overlapping partitions, the concept of lower and upper approximations of rough sets deals with uncertainty, vagueness, and incompleteness in class definition. The experiments conducted on brain MR images show promising results in terms of segmentation accuracy and class separability. The usefulness of proposed algorithm is also investigated on high field MR images. The proposed algorithm Rough-Theoretic Bias-Corrected Fuzzy C-Means Algorithm (R-BCFCM) has significant performance improvement over other similar methods from rough-fuzzy family and can be employed for MRI corrupted with high intensity non-uniformity and noise.

In this paper, a new method is proposed to decrease sensitiveness to motion noise and uncertainty in magnetic resonance imaging (MRI) segmentation especially when only one brain image is available. The method is approached with considering spatial neighborhood information by fusing the information of pixels with their neighbors with Dempster–Shafer (DS) theory. The basic probability assignment (BPA) of each single hypothesis is obtained from the membership function of applying fuzzy c-means (FCM) clustering to the gray levels of the MRI. Then multiple hypotheses are generated according to the single hypothesis. Then we update the objective pixel’s BPA by fusing the BPA of the objective pixel and those of its neighbors to get the final result. Some examples in MRI segmentation are demonstrated at the end of the paper, in which our method is compared with some previous methods. The results show that the proposed method is more effective than other methods in motion-blurred MRI segmentation.

Medical image segmentation and reconstruction of prostate tumor based on 3D AlexNet

Segmentation of brain magnetic resonance imaging (MRI) data plays an important role in the computer-aided diagnosis and neuroscience research. Fuzzy c-means (FCM) clustering algorithm is one of the most usually used techniques for brain MRI image segmentation because of its fuzzy nature. However, the conventional FCM method fails to carry out segmentation well enough due to intensity inhomogeneity in MRI data. To overcome this issue, we propose an improved algorithm based on FCM clustering for segmentation of brain MRI data. Specifically, we modify the conventional FCM algorithm to allow for intensity inhomogeneity by introducing the regularization of the neighborhood influence and bias field. Results show that our proposed algorithm obtains reasonable segmentation of white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) from MRI data, which is superior to the expectation-maximization (EM) and conventional FCM methods.

Parameter optimization of improved fuzzy c-means clustering algorithm for brain MR image segmentation

The purpose of this study was to confirm the association between the serum vitamin D levels and ischemic stroke lesion size, functional ability, and cognitive function in elderly ischemic stroke patients. This study included Korean ischemic stroke patients aged 65 to 85 years. The size of the lesion was measured in brain images taken within 24 hours of hospitalization. The level of 25-(OH) Vitamin D (ng/mL), a metabolite of vitamin D, in the serum collected within 48 hours of hospitalization, and the modified Barthel index (MBI), gait performance, the muscle power of hip and knee extensors on the hemiplegic side, and mini-mental status examination (MMSE) were recorded within 1 week of the onset of the disease. Each factor was compared through correlation analysis, and the significance was confirmed using the Spearman correlation coefficient method. The association between the serum vitamin D levels and the size of the ischemic stroke lesion, the MBI, gait performance, the muscle power of hip and knee extensors on the hemiplegic side, and the MMSE were analyzed. It was confirmed that there was a significant correlation between all the factors (P < .005). In patients with serum vitamin D levels of ≥ 30 ng/mL, both the functional ability and cognitive functions were better than in patients lower than 30 ng/mL. We confirmed the lower the level of serum vitamin D levels, the larger the size of the ischemic stroke lesion when it occurred in elderly Koreans. And we confirmed that serum vitamin D levels affected the functional ability and cognitive function. And we recommend that elderly Koreans should maintain their blood vitamin D level above 30 ng/mL. We believe that this will help preserve the functional ability and cognitive function when ischemic stroke occurred.

A Quantum-Inspired Self-Supervised Network model for automatic segmentation of brain MR images

The brain is considered a main important part of human body as it participate to control all the activities of human. Under some unhealthy conditions the abnormal and uncontrolled growth of tissue may take place which is unnatural process. This kind of process taking place in human brain is referred as “brain tumor”. The brain tumor may be of cancerous (malignant) or may be of non-cancerous (Benign) and its detection is a very much important to reduced the death rate of humans suffering from tumor. The detection of brain tumor can be performed by using various image processing techniques like brain magnetic resonance imaging (MRI), Computed Tomography (CT), Electroencephalography (EEG), Positron Emission Tomography (PET), Magneto Encephalography (MEG) etc. Among these techniques the brain MRI is widely adopted in the world due to its significant features. But to detect tumor in the brain MRI, the processes like preprocessing, segmentation and classification are must. This paper deals with the various aspects of the brain tumor detection. The paper discusses the significant researches which are meant for brain tumor detection through MRI quality enhancement, MRI segmentation and MRI classification (as cancerous or not). The outcome of the paper discussed that there were no proper researches are performed to detect the brain tumor, focused on good quality of image, less researches on segmentation and classification of brain tumor. Finally the paper gives the future research scope to overcome the addressed research gap.

Improvement of automatic ischemic stroke lesion segmentation in CT perfusion maps using a learned deep neural network

A severe infection such as COVID-19 may trigger a stroke. The imaging and clinical features of patients with COVID-19 are not well-defined. We aimed to analyze neuroimaging and clinical features of stroke patients with COVID-19. The demographic and clinical data of 21 stroke cases with confirmed COVID-19 (StrokeCov) between April 2020-May 2021 were collected prospectively. An experienced stroke neurologist evaluated neuroimaging findings. A control group of gender, age, and risk factors adjusted 104 stroke patients were included. Mean age was 66.3 (±13.3) and 66.2 (±13) years in the StrokeCov group and control group (CG), with similar male-to-female ratios (85%) and without significant difference regarding diabetes, hypertension, hyperlipidemia, and atrial fibrillation between groups (p>0.05). Infarcts were most frequently seen in the territory of middle cerebral artery (8 patients; 40%), followed by multiple arterial territories (6 patients; 30%). Ischemic lesions were more frequently localized in both anterior and posterior vascular systems in StrokeCov group (3 patients; 15%) in comparison to CG (2 patients; 2%; p=0.02). Although, hemorrhagic transformation was observed more frequently in StrokeCov group (6 patients; 30%) than CG (11 patients; 10%; p=0.02); statistically significant difference was not seen in terms of acute and preventive treatments given to both groups. The mRS scores on discharge were worse in the StrokeCov group (p<0.00). Ischemic stroke lesions in StrokeCov group are more likely to be localized on multiple arterial territories and develop hemorrhagic transformation. Poor clinical outcome and in-hospital death are more common in stroke due to COVID-19.

Brain tumor segmentation in Magnetic Resonance Imaging (MRI) scans provides vital information to radiologists in the diagnosis and staging of disease. However, these MRI scans are often corrupted with noise during its acquisition. Traditional approaches to this problem employ denoising which leads, in general, to edge smoothing and development of artifacts in MRI slices, thereby affecting tumor segmentation performance. In this paper, we employed graph signal processing (GSP) theory to first segment tumor core in each MRI slice using graph Laplacian followed by edge-aware denoising which is performed in synergy. The paper aims to present a novel technique to tackle the two problems of segmentation and denoising both under the GSP framework. The experimental results demonstrated on simulated and clinical brain MRI datasets, show highly competitive performance both in terms of tumor core segmentation under Dice and Sensitivity measures, and in terms of edge-aware denoising under PSNR and SSIM measures.

One of the fundamental and significant distinctiveness of an image is that, adjacent pixels are extremely correlated. The spatial information in the image improves the quality of clustering which is not utilized in the standard Fuzzy C-Means (FCM). FCM algorithm is not robust against noise. In this paper, we proposed an enhanced version of Fuzzy C-Means algorithm that incorporates spatial information into the membership function for clustering of brain MR images. The modified Fuzzy C-Means finds optimal clusters in an automatic way with the help of some cluster validity criteria. Additionally, spatial weighted information is incorporated in the spatial FCM. The spatial function is the weighted summation of the membership function in the neighborhood of each pixel under consideration. The advantages of this new method are: (a) it yields regions more homogeneous than those of other methods and (b) it removes noisy spots. It is less sensitive to noise as compared to other techniques. We tested our method on various brain MR images, and the technique has proved as a powerful method in the segmentation of noisy images.