Search

Brain tumor segmentation from magnetic resonance (MR) image is vital for both the diagnosis and treatment of brain cancers. To alleviate noise sensitivity and improve stability of segmentation, an effective hybrid clustering algorithm combined with fast guided filter is proposed for brain tumor segmentation in this paper. Preprocessing is performed using adaptive Wiener filtering combined with a fast guided filter. Then simple linear iterative clustering (SLIC) is utilized for pre-segmentation to effectively remove scatter. During the clustering, K-means + + and Gaussian kernel-based fuzzy C-means (K + + GKFCM) clustering algorithm are combined to segment, and the fast-guided filter is introduced into the clustering. The proposed algorithm not only improves the robustness of the algorithm to noise, but also improves the stability of the segmentation. In addition, the proposed algorithm is compared with other current segmentation algorithms. The results show that the proposed algorithm performs better in terms of accuracy, sensitivity, specificity and recall. [ABSTRACT FROM AUTHOR]

Breast tumor is one of the causes of women's death in the world after cardiovascular diseases. Recently, the diagnosis and treatment planning of this kind of tumors are based on magnetic resonance imaging techniques, which are the reference imaging modality in breast tumors analysis since it can better differentiate soft tissues (compared to mammography and ultrasound). Segmentation of the breast cancer is a very important task for cancer response prediction in neoadjuvant chemotherapy treatment based either on texture analysis or parametric response maps. In most of the previous works in the literature, the segmentation is generally done with manual annotation of tumor regions, which is time-consuming and error-prone. In this paper, we propose a new strategy for an automatic segmentation of breast tumors in MRI images. We propose first to separate the two breasts, and then, we use the Expectation–Maximization Algorithm to segment and detect the tumor lesion. [ABSTRACT FROM AUTHOR]

Image segmentation in brain magnetic resonance imaging (MRI) largely relates to dividing brain tissue into components like white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Using the segmentation outputs, medical images can be 3D reconstructed and visualized efficiently. It is common for MRI pictures to have issues such as partial volume effects, asymmetrical grayscale, and noise. As a result, high accuracy in brain MRI picture segmentation is challenging to achieve in practical applications. In this paper, we developed an effective algorithm for brain MRI image segmentation utilizing a combination of statistical and partial differential equation-based approaches, based on a neuro-mechanical model. The findings of this work demonstrate that by combining various segmentation approaches, it is possible to quickly segment brain MRI data at a degree of precision necessary for different applications. Here, we show that when we use nonlinear filtering, k -means clustering, and active contour modeling, we can get very good results when we segment brain MRI images. It is clear that the proposed approach has higher segmentation performance and can properly separate brain tissue from a large number of MRI images. [ABSTRACT FROM AUTHOR]

In the current medical image segmentation network, the combination of CNN and Transformer has become a mainstream trend. However, the inherent limitations of convolution operation in CNN and insufficient information interaction in Transformer affect the segmentation performance of the network. To solve these problems, an integrated self-attention and convolution medical image segmentation network (ISC-TransUNet) is proposed in this paper. The network consists of encoder, decoder and jump connection. First, the encoder uses a hybrid structure of BoTNet and Transformer to capture more comprehensive image information and reduce additional computing overhead. Then, the decoder uses an upper sampler cascaded by multiple DUpsampling upper blocks to accurately recover the pixel-level prediction. Finally, the feature fusion of encoder and decoder at different resolutions is realized by ResPath jump connection, which reduces the semantic difference between encoder and decoder. Through experiments on the Synapse multi-organ segmentation dataset, compared with the baseline model TransUNet, Dice similarity coefficient of ISC-TransUNet was improved by 1.13%, Hausdorff distance was reduced by 2.38%, and weight was maintained. The experimental results show that the network can effectively segment tissues and organs in medical images, which has important theoretical significance and application value for intelligent clinical diagnosis and treatment. [ABSTRACT FROM AUTHOR]

Diabetes affects retinal structure of a diabetic patient by generating various lesions. Early detection of these lesions can avoid the loss of vision. Automation of detection process can be made easily feasible to masses by the use of fundus imaging. Detection of exudates is significant in diabetic retinopathy (DR) as they are earlier signs and can cause blindness. Finding the exact location as well as correct number of exudates play vital role in the overall treatment of a patient. This paper presents an algorithm for automatic detection of exudates for DR. The algorithm combines the advantages of supervised and unsupervised techniques. It uses fuzzy-C means (FCM) segmentation on coarse level and mahalanobis metric for finer classification of segmented pixels. Mahalanobis criterion gives significance to most relevant features and thus proves a better classifier. The results are validated using DIARETDB0 and DIARETDB1 databases and the ground truth provided with it. This evaluation provided 95.77% detection accuracy. [ABSTRACT FROM AUTHOR]

In this work, we developed an approach based on mathematical morphology and the k-means clustering algorithm to detect hard exudates (HEs) in images taken by retinography from different diabetic patients. The presence of exudates within the macular region is a hallmark of diabetic macular edema and is detected by diagnostics with high sensitivity. In ophthalmologic images, the segmentation of HEs is essential to characterize the shape of the lesion for analysis. In this domain, several approaches have been employed for exudate extraction. Some authors have used only the mathematical morphology, but this approach does not provide very good detection of exudates. In this paper, we combined the k-means clustering algorithm and the mathematical morphology. This approach was tested on a set of 50 ophthalmologic images. The obtained results were compared with manual segmentation by an ophthalmologist. [ABSTRACT FROM AUTHOR]

Background: Breast cancer is a common and dreadful disease in women. One in five cancers in Singaporean women is due to breast cancer. Breast health is every woman's right and responsibility. In average, every $100 spent on breast mammogram screening, an additional $33 was spent on evaluating possible false-positive results. Thermography, with its non-radiation, non-contact and low-cost basis has been demonstrated to be a valuable and safe early risk marker of breast pathology, and an excellent case management tool available today in the ongoing monitoring and treatment of breast disease. The surface temperature and the vascularization pattern of the breast could indicate breast diseases and early detection saves lives. To establish the surface isotherm pattern of the breast and the normal range of cyclic variations of temperature distribution can assist in identifying the abnormal infrared images of diseased breasts. Before these thermograms can be analyzed objectively via computer algorithm, they must be digitized and segmented. The authors present a method to segment thermograms and extract useful region from the background. Thermography could detect the presence of tumors much earlier and of much smaller size than mammography. This paper thus aims to develop an intelligent diagnostic system based on thermography for the detection of tumors in breast. Methods: We have examined about 50 normal, healthy female volunteers in Nanyang Technological University and 130 patients in Singapore General Hospital. We did the examinations for some of them continuously for two months. From these examinations, we obtained about 1000 thermograms for contact and 800 thermograms for non-contact approaches. Standard ambient conditions were observed for all examinations. The thermograms obtained were analyzed. The first step in processing these thermograms is image segmentation. Its aim is to discern the useful region from the background. In general, autonomous segmentation is one of the most difficult tasks in image processing. This step in the process determines the eventual success or failure of the analysis. In this work, two different techniques have been presented to extract the objects from the background. Results: After analyzing these thermograms and with reference to some relevant well-documented papers, we were able to classify the thermograms. The step is very useful in identifying the normal or suspected (abnormal) thermograms. A series of thermograms was studied with the help of the in-house developed computer software. On the basis of the anatomic and vascular symmetry, the surface temperature distributions of both left and right breasts were compared. The surface isotherm pattern of breasts can indicate the local metabolism and vascularity of the underlying tissues, and the change in local blood or glandular activities can be reflected in the surface temperature of breast. We evaluated the temperature distribution pattern and the menstrual cyclic variation of temperature with time. All these results can be used to detect breast cancer. Conclusion: Automatic identification of object and surface boundary of breast thermal images is a difficult and challenging task. Both the traditional snake and gradient vector flow snake failed to detect the boundary of these images successfully. In this work, a new method is proposed in conjunction with image pre-processing, image transition, image derivative, filtering and gradient vector flow snake. This novel method can easily detect the boundary of the breast thermal image with good agreement. [ABSTRACT FROM AUTHOR]

Segmentation of the left ventricle in ultrasound images for viewing through different axes is a critical aspect. This paper proposes the development of novel active contour models with shape constraint to segment the left ventricle in three different axis views of the ultrasound images. The shapes observed in all the axis views of the left ventricle were not similar. According to the cardiac cycle, the valve opening in the end-diastolic phase influenced the left ventricle segmentation; hence, a shape constraint was embedded in the active contour model to keep ventricle's shape, especially in the Apical long-axis view and Apical four-chamber view. Furthermore, for different axes views, diverse active contour models were proposed to fit each situation. The shape constraint in each function for different views exhibited a specific shape during the function iteration. In order to speed up the algorithm evolution, previous results were used for the initialization of the present active contour. We evaluated the proposed method on 57 patients with three different views: Apical long-axis view, Apical four-chamber view and Short-axis view at the papillary muscle level and obtained the Dice similarity coefficients of 0. 8 6 ± 0. 0 5 , 0. 9 0 ± 0. 0 6 and 0. 9 0 ± 0. 0 6 and the Hausdorff distance metrics of 1 0. 1 1 ± 4. 6 6 , 7. 4 1 ± 4. 4 6 and 9. 9 8 ± 6. 5 8 , respectively. The qualitative and quantitative evaluations showed an advantage of our method in terms of segmentation accuracy. [ABSTRACT FROM AUTHOR]

The aim of our work is the segmentation of healthy and pathological brains to obtain brain structures and extract strokes. We used real magnetic resonance (MR) images weighted on diffusion. The brain was isolated, and the images were filtered by an anisotropic filter, and then segmented by support vector machines (SVMs). We first applied the method on synthetic images to test the performance of the algorithm and adjust the parameters. Then, we compared our results with those obtained by a cooperative approach proposed in a previous paper. [ABSTRACT FROM AUTHOR]

Segmentation and classification of brain tumor are time-consuming and challenging chore in clinical image processing. Magnetic Resonance Imaging (MRI) offers more information related to human soft tissues that assists in diagnosing brain tumor. Precise segmentation of the MRI images is vital to diagnose brain tumor by means of computer-aided medical tools. Afterwards suitable segmentation of MRI brain tumor images, tumor classification is performed that is a hard chore owing to complications. Therefore, Gannet Aquila Optimization Algorithm_deep maxout network (GAOA_DMN) and GAOA_K-Net+speech enhancement generative adversarial network (GAOA_K-Net+Segan) is presented for classification and segmentation of brain tumor utilizing MRI images. Here, pre-processing phase performs noise removal from input image utilizing the Laplacian filter and also the region of interest (ROI) extraction is also carried out. Then, segmentation of brain tumor is conducted by K-Net+Segan, which is combined by Motyka similarity. However, K-Net+Segan for segmentation is trained by GAOA that is an amalgamation of Gannet Optimization Algorithm (GOA) and Aquila Optimizer (AO). From segmented image, features are extracted for performing classification phase. At last, brain tumor classification is conducted by DMN, which is tuned by GAOA and thus, output is obtained. Furthermore, GAOA_K-Net+Segan obtained better outcomes in terms of segmentation accuracy whereas devised GAOA_DMN achieved maximum accuracy, true negative rate (TNR) and true positive rate (TPR) of 92.7%, 94.5% and 91.5%. [ABSTRACT FROM AUTHOR]

"Image-based" computational fluid dynamics (CFD) simulations provide insights into each patient's hemodynamic environment. However, the current standard procedures for creating CFD models start with manual segmentation and are time-consuming, hindering the clinical translation of image-based CFD simulations. This feasibility study adopts deep-learning-based image segmentation [hereafter referred to as Artificial Intelligence (AI) segmentation] to replace manual segmentation to accelerate the CFD model creation. Two published convolutional neural network-based AI methods (MIScnn and DeepMedic) were selected to perform CFD model extraction from three-dimensional (3D) rotational angiography data containing intracranial aneurysms. In this study, aneurysm morphological and hemodynamic results using the models generated by AI segmentation methods were compared with those obtained by two human users for the same data. Interclass coefficients (ICCs), Bland–Altman plots, and Pearson's correlation coefficients (PCCs) were combined to assess how well the AI-generated CFD models performed. We found that almost perfect agreement was obtained between the human and AI results for all 11 morphological parameters and five out of eight hemodynamic parameters, while a moderate agreement was obtained from the remaining three hemodynamic parameters. Given this level of agreement, using AI segmentation to create CFD models is feasible, given more developments. [ABSTRACT FROM AUTHOR]

Active Appearance Models (AAM), have been introduced by Cootes et al. [ IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001], and are used to learn objects characteristics during a training phase by building a compact statistical model representing shape and texture variation of the object. This Model is used to find the object location and shape-appearance parameters, in a test set. The selection of the initial position of the construct model in a test image is a very important task in this context. The goal of this work is to propose an automatic segmentation method applied to cardiovascular MR images using an AAM based segmentation approach. The AAM model was constructed using 20 end-diastolic and end-systolic short axis cardiac magnetic resonance images (MRI). Once the model is constructed, we select the best position in order to start the search step manually in the test image. That is why; in this paper, the localization of the left ventricular cavity in the test image is used to select the initial position of the construct model developed from the training images. So we propose an automatic approach to detect this spatial position by using two methods: (1) the circular Hough transform (CHT) and (2) the evaluation of the Hausdorff distance. [ABSTRACT FROM AUTHOR]

In this study, the effects of threshold variation in image segmentation of micro CT images of cancellous bone in the determination of the architectural parameters and stiffness were investigated. A total of 42 samples of 6 × 6 × 6 mm3 cubes with threshold values set between 500-1100 greyscale in increment of 100 of CT images of six human C5 vertebral bodies were analyzed. Threshold value of 800, based on Otsu's method, was set for the control group. From various threshold values, the respective architectural parameters, and the corresponding stiffness in three orthotropic directions (Exx, Eyy, Ezz) of each cube were computed from the voxel-based micro-finite element models under compressive simulation. The results showed that 1% variation of threshold value resulted in a 3.4% variation in BV/TV, 2% in Tb.N, 3.1% in Tb.Th, 2.9% in BS/BV, 1.8% in Tb.Sp, 29.2% in Exx, 28.7% Eyy and 27.7% in Ezz. Statistical analysis showed that 2.9% threshold variation caused significant change in BV/TV, Tb.Th, Exx, Eyy and Ezz values. The study shows that with threshold variation of more than 2.9%, significant differences in the architectural parameters and stiffness compared to those based on Otsu's method. [ABSTRACT FROM AUTHOR]