A fast and robust segmentation of magnetic resonance brain images using a combination of the pyramidal approach and level set method

We propose in this article an approach to optimize the processing time and to improve the quality of brain magnetic resonance images segmentation. Level set method (LSM) was adopted with a periodic reinitialization process to prevent the LS function from being too steep or too flat near the interface. Although it is used to maintain the stability of the interface evolution and gives interesting results, it requires a longer processing time. To overcome this disadvantage and reduce the processing time, we propose a hybridization with a regular Gaussian pyramid, which reduces the resolution of the initial image and prevents the possibility of local minima. To compare the different segmentation algorithms, we used six types of quality measurements: specificity, sensitivity, Dice similarity, the Jaccard index, and the correctly and incorrectly marked pixels. A comparison between the results obtained by LSM, LSM with reinitialization, the approach of Barman et al., An International Journal 1 (2011), particle swarm optimization based on the Chan and Vese model (Mandal et al., Engineering Applications of Artificial Intelligence 35 (2014), 199‐214) and by our hybrid approach reveals a clear efficiency of our hybridization strategy. The processing time was significantly reduced, and the quality of segmentation was improved. © 2016 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 26, 243–253, 2016     

A novel level set method for image segmentation by combining local and global information

A novel level set method integrating local and global statistical information is proposed in this paper. In our method, a new signed pressure force (SPF) function is constructed by two parts. One is the global average intensity of the image, which can accelerate the evolution of the curve when the contour far away from the object boundaries. The other is the intensity average of difference image between the averaging convolution image and the original image, which can guide the evolving curve to catch the boundaries of the objects. In addition, an adaptive weighting function is utilized to adjust the ratio between the global and local terms, which can eliminate the inconvenient selection of weighting parameter. By substituting the new SPF function for the edge stopping function of the geodesic active contour model, we obtain a novel adaptive hybrid segmentation model, which is capable of segmenting the images with intensity inhomogeneity. What is more, in our method, the level set function is initialized with a binary function, which reduces the computational cost for the re-initialization step. The experimental results and comparisons with several popular models on synthetic and real images indicate that our method achieves superior performance in segmenting images with noise, low contrast and intensity inhomogeneity.     

Multi-Scale 3D U-Nets: An approach to automatic segmentation of brain tumor

Gliomas segmentation is a critical and challenging task in surgery and treatment, and it is also the basis for subsequent evaluation of gliomas. Magnetic resonance imaging is extensively employed in diagnosing brain and nervous system abnormalities. However, brain tumor segmentation remains a challenging task, because differentiating brain tumors from normal tissues is difficult, tumor boundaries are often ambiguous and there is a high degree of variability in the shape, location, and extent of the patient. It is therefore desired to devise effective image segmentation architectures. In the past few decades, many algorithms for automatic segmentation of brain tumors have been proposed. Methods based on deep learning have achieved favorable performance for brain tumor segmentation. In this article, we propose a Multi-Scale 3D U-Nets architecture, which uses several U-net blocks to capture long-distance spatial information at different resolutions. We upsample feature maps at different resolutions to extract and utilize sufficient features, and we hypothesize that semantically similar features are easier to learn and process. In order to reduce the computational cost, we use 3D depthwise separable convolution instead of some standard 3D convolution. On BraTS 2015 testing set, we obtained dice scores of 0.85, 0.72, and 0.61 for the whole tumor, tumor core, and enhancing tumor, respectively. Our segmentation performance was competitive compared to other state-of-the-art methods.     

A novel brain image segmentation using intuitionistic fuzzy C means algorithm

A process of splitting the image into pixel bands is the image segmentation. As medical imaging contain uncertainties, there are difficulties in classification of images into homogeneous regions. There is a need for segmentation algorithm for removing the noise from the medical image segmentation. The very popular algorithm is Fuzzy C‐Means (FCM) algorithm used for image segmentation. Fuzzy sets, rough sets, and the combination of fuzzy and rough sets play a prominent role in formalizing uncertainty, vagueness, and incompleteness in diagnosis. But it will use intensity values only which will be highly sensitive to noise. In this article, an Intuitionistic FCM (IFCM) algorithm is presented for clustering. Intuitionistic fuzzy (IF) sets are generalized sets and their elements are characterized by a membership value as well as nonmembership value. This IFCM has an uncertainty parameter which is called hesitation degree and a new objective function is integrated in the standard FCM based on IF entropy. The IFCM will provide better performance than FCM for image segmentation.     

A fully automated hybrid methodology using Cuckoo‐based fuzzy clustering technique for magnetic resonance brain image segmentation

This article aims at developing an automated hybrid algorithm using Cuckoo Based Search (CBS) and interval type‐2 fuzzy based clustering, so as to exhibit efficient magnetic resonance (MR) brain image segmentation. An automatic MR brain image segmentation facilitates and enables a radiologist to have a brief review and easy analysis of complicated tumor regions of imprecise gray level regions with minimal user interface. The tumor region having severe intensity variations and suffering from poor boundaries are to be detected by the proposed hybrid technique that could ease the process of clinical diagnosis and this tends to be the core subject of this article. The ability of the proposed technique is compared using standard comparison parameters such as mean squared error, peak signal to noise ratio, computational time, Dice Overlap Index, and Jaccard T animoto C oefficient Index. The proposed CBS combined with interval type‐2 fuzzy based clustering produces a sensitivity of 0.7143 and specificity of 0.9375, which are far better than the conventional techniques such as kernel based, entropy based, graph‐cut based, and self‐organizing maps based clustering. Appreciable segmentation results of tumor region that enhances clinical diagnosis is made available through this article and two of the radiologists who have hands on experience in the field of radiology have extended their support in validating the efficiency of the proposed methodology and have given their consent in utilizing the proposed methodology in the processes of clinical oncology.     

Oriented distance regularized level set evolution for image segmentation

The conventional distance regularized level set evolution method has been very popular in image segmentation, but usually it cannot converge to the desired boundary when there are multiple and unwanted boundaries in the image. By observation, the gradient direction between the target boundaries and the unwanted boundaries are usually different in one image. The gradient direction information of the boundaries can guide the orientation of the level set function evolution. In this study, the authors improved the conventional distance regularized level set evolution method, introduced new edge indicator functions and proposed an oriented distance regularized level set evolution method for image segmentation. The experiment results show the proposed method has a better segmentation result in images with multiple boundaries. Moreover, alternately selecting the edge indicator functions we proposed during the level set evolution can lead the zero level set contour to converge to the desired boundaries in complicated images.     

Brain tumor segmentation using a deep Shuffled-YOLO network

Brain tumor is an anomalous proliferation of cells in the brain that can evolve to malignant and benign tumors. Currently, segmentation of brain tumor is the most important surgical and pharmaceutical procedures. However, manually segmenting brain tumors is hard because it is hard to find erratically shaped tumors with only one modality; the MRI modalities are integrated to provide multi-modal images with data that can be utilized to segment tumors. The recent developments in machine learning and the accessibility of medical diagnostic imaging have made it possible to tackle the challenges of segmenting brain tumors with deep neural networks. In this work, a novel Shuffled-YOLO network has been proposed for segmenting brain tumors from multimodal MRI images. Initially, the scalable range-based adaptive bilateral filer (SCRAB) pre-processing technique was used to eliminate the noise artifacts from MRI while preserving the edges. In the segmentation phase, we propose a novel deep Shuffled-YOLO architecture for segmenting the internal tumor structures that include non-enhancing, edema, necrosis, and enhancing tumors from the multi-modality MRI sequences. The experimental fallouts reveal that the proposed Shuffled-YOLO network achieves a better accuracy range of 98.07% for BraTS 2020 and 97.04% for BraTS 2019 with very minimal computational complexity compared to the state-of-the-art models.     

Fully automatic method for segmentation of brain tumor from multimodal magnetic resonance images using wavelet transformation and clustering technique

Fully automatic brain tumor segmentation is one of the critical tasks in magnetic resonance imaging (MRI) images. This proposed work is aimed to develop an automatic method for brain tumor segmentation process by wavelet transformation and clustering technique. The proposed method using discrete wavelet transform (DWT) for pre‐ and post‐processing, fuzzy c‐means (FCM) for brain tissues segmentation. Initially, MRI images are preprocessed by DWT to sharpen the images and enhance the tumor region. It assists to quicken the FCM clustering technique and classified into four major classes: gray matter (GM), white matter (WM), cerebrospinal fluid (CSF), and background (BG). Then check the abnormality detection using Fuzzy symmetric measure for GM, WM, and CSF classes. Finally, DWT method is applied in segmented abnormal region of images respectively and extracts the tumor portion. The proposed method used 30 multimodal MRI training datasets from BraTS2012 database. Several quantitative measures were calculated and compared with the existing. The proposed method yielded the mean value of similarity index as 0.73 for complete tumor, 0.53 for core tumor, and 0.35 for enhancing tumor. The proposed method gives better results than the existing challenging methods over the publicly available training dataset from MICCAI multimodal brain tumor segmentation challenge and a minimum processing time for tumor segmentation. © 2016 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 26, 305–314, 2016     

Severity detection and infection level identification of tuberculosis using deep learning

Tuberculosis (TB) is a highly infectious disease and is one of the major health problems all over the world. The accurate detection of TB is a major challenge faced by most of the existing methods. This work addresses these issues and developed an effective mechanism for detecting TB using deep learning. Here, the color space transformation is applied for transforming the red green and blue image to LUV space, where L stands for luminance, U and V represent chromaticity values of color images. Then, adaptive thresholding is carried out for image segmentation and various features, like coverage, density, color histogram, area, length, and texture features, are extracted to enable effective classification. After the feature extraction, the size of the features is reduced using principal component analysis. The extracted features are subjected to fractional crow search-based deep convolutional neural network (FC-SVNN) for the classification. Then, the image level features, like bacilli count, bacilli area, scattering coefficients and skeleton features are considered to perform severity detection using proposed adaptive fractional crow (AFC)-deep CNN. Finally, the inflection level is determined using entropy, density and detection percentage. The proposed AFC-Deep CNN algorithm is designed by modifying FC algorithm using self-adaptive concept. The proposed AFC-Deep CNN shows better performance with maximum accuracy value as 0.935.     

Fuzzy C means integrated with spatial information and contrast enhancement for segmentation of MR brain images

This paper proposes a fully automated method for MR brain image segmentation into Gray Matter, White Matter and Cerebro‐spinal Fluid. It is an extension of Fuzzy C Means Clustering Algorithm which overcomes its drawbacks, of sensitivity to noise and inhomogeneity. In the conventional FCM, the membership function is computed based on the Euclidean distance between the pixel and the cluster center. It does not take into consideration the spatial correlation among the neighboring pixels. This means that the membership values of adjacent pixels belonging to the same cluster may not have the same range of membership value due to the contamination of noise and hence misclassified. Hence, in the proposed method, the membership function is convolved with mean filter and thus the local spatial information is incorporated in the clustering process. The method further includes pixel re‐labeling and contrast enhancement using non‐linear mapping to improve the segmentation accuracy. The proposed method is applied to both simulated and real T1‐weighted MR brain images from BrainWeb and IBSR database. Experiments show that there is an increase in segmentation accuracy of around 30% over the conventional methods and 6% over the state of the art methods.     

Multimodal brain tumor detection and classification using deep saliency map and improved dragonfly optimization algorithm

In the last decade, there has been a significant increase in medical cases involving brain tumors. Brain tumor is the tenth most common type of tumor, affecting millions of people. However, if it is detected early, the cure rate can increase. Computer vision researchers are working to develop sophisticated techniques for detecting and classifying brain tumors. MRI scans are primarily used for tumor analysis. We proposed an automated system for brain tumor detection and classification using a saliency map and deep learning feature optimization in this paper. The proposed framework was implemented in stages. In the initial phase of the proposed framework, a fusion-based contrast enhancement technique is proposed. In the following phase, a tumor segmentation technique based on saliency maps is proposed, which is then mapped on original images based on active contour. Following that, a pre-trained CNN model named EfficientNetB0 is fine-tuned and trained in two ways: on enhanced images and on tumor localization images. Deep transfer learning is used to train both models, and features are extracted from the average pooling layer. The deep learning features are then fused using an improved fusion approach known as Entropy Serial Fusion. The best features are chosen in the final step using an improved dragonfly optimization algorithm. Finally, the best features are classified using an extreme learning machine (ELM). The experimental process is conducted on three publically available datasets and achieved an improved accuracy of 95.14, 94.89, and 95.94%, respectively. The comparison with several neural nets shows the improvement of proposed framework.     

Leakage suppression in human airway tree segmentation using shape optimization based on fuzzy connectivity method

Human airway tree segmentation from computed tomography (CT) images is a very important step for virtual bronchoscopic applications. Imaging artifacts or thin airway walls decrease the contrast between the air and airway wall and make the segmented region to leak from inside of the airway to the parenchyma. This in turn begins the leakage phenomenon to build and then large parts of the lung parenchyma might be erroneously marked as the airway tree instead. Unfortunately, existing methods typically do not sufficiently extract the necessary peripheral airways needed to plan a procedure. In this article, we propose a new shape based human airway segmentation scheme to suppress the leakage into surrounding area which is based on fuzzy connectivity (FC) method. Complex medical image features such as weak boundary edges in the CT images of the lung parenchyma have fuzzy properties and can be described by FC in many extents. Our method aims to embed a mathematical shape optimization approach in a FC algorithm. Using the partial derivatives of the image data that is minimized with respect to the polar angle and cylindrical axis direction, a proper cost function based on cylindrical features of the airway branches is proposed. This approach retains the cylindrical properties of the airway branches during the segmentation process. The proposed cost function includes two parts named cylindrical‐shape feature and smoothed final error term. The former term arranges the underlying voxels on a cylindrical shape and the latter term controls and smoothes the final error considering the local minima's problem. To evaluate the efficiency of our proposed optimization technique in term of segmentation accuracy, the cost function is first applied to the simulated data with the spongy shape of leakage and the leakage origin. The impact of each term of the proposed cost function on the final error and the convergence of the algorithm are also evaluated. Then, the cost function with best proper parameters is applied to real image dataset. Comparisons of the results on multidetector CT chest scans show that our segmentation algorithm outperforms the fuzzy region growing algorithm. Quantitative comparisons with manually segmented airway trees also indicate high sensitivity of our segmentation algorithm on peripheral airways. On the basis of the results, it is concluded that the proposed method is able to detect more branches up to the sixth generation with no leakage which provides 2–3 more generations of airways than several other methods do. The extracted airway trees enable image‐guided bronchoscopy to go deeper into the human lung periphery than past studies. The novelty of our proposed method is to apply a shape optimization approach embedded in an efficient FC segmentation algorithm. Hence, our method prevents leakage from its origination in contrast to most previously published works that just set their algorithms to repeat the segmentation steps to reduce leakage. As our results indicate leakage suppression in human airway segmentation instead of readjusting the segmentation parameters, more airway branches can be extracted with correct shape. © 2013 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 23, 71–84, 2013     

Research on the magnetic resonance imaging brain tumor segmentation algorithm based on DO-UNet

With the social and economic development and the improvement of people's living standards, smart medical care is booming, and medical image processing is becoming more and more popular in research, of which brain tumor segmentation is an important branch of medical image processing. However, the manual segmentation method of brain tumors requires a lot of time and effort from the doctor and has a great impact on the treatment of patients. In order to solve this problem, we propose a DO-UNet model for magnetic resonance imaging brain tumor image segmentation based on attention mechanism and multi-scale feature fusion to realize fully automatic segmentation of brain tumors. Firstly, we replace the convolution blocks in the original U-Net model with the residual modules to prevent the gradient disappearing. Secondly, the multi-scale feature fusion is added to the skip connection of U-Net to fuse the low-level features and high-level features more effectively. In addition, in the decoding stage, we add an attention mechanism to increase the weight of effective information and avoid information redundancy. Finally, we replace the traditional convolution in the model with DO-Conv to speed up the network training and improve the segmentation accuracy. In order to evaluate the model, we used the BraTS2018, BraTS2019, and BraTS2020 datasets to train the improved model and validate it online, respectively. Experimental results show that the DO-UNet model can effectively improve the accuracy of brain tumor segmentation and has good segmentation performance.     

Robust shape and topology optimization considering geometric uncertainties with stochastic level set perturbation

When geometric uncertainties arising from manufacturing errors are comparable with the characteristic length or the product responses are sensitive to such uncertainties, the products of deterministic design cannot perform robustly. This paper presents a new level set‐based framework for robust shape and topology optimization against geometric uncertainties. We first propose a stochastic level set perturbation model of uncertain topology/shape to characterize manufacturing errors in conjunction with Karhunen–Loève (K–L) expansion. We then utilize polynomial chaos expansion to implement the stochastic response analysis. In this context, the mathematical formulation of the considered robust shape and topology optimization problem is developed, and the adjoint‐variable shape sensitivity scheme is derived. An advantage of this method is that relatively large shape variations and even topological changes can be accounted for with desired accuracy and efficiency. Numerical examples are given to demonstrate the validity of the present formulation and numerical techniques. In particular, this method is justified by the observations in minimum compliance problems, where slender bars vanish when the manufacturing errors become comparable with the characteristic length of the structures. Copyright © 2016 John Wiley & Sons, Ltd.     

Automatic liver tumor segmentation on multiphase computed tomography volume using SegNet deep neural network and K-means clustering

Liver and liver tumor segmentations are essential in computer-aided systems for diagnosing liver tumors. These systems must operate on multiphase computed tomography (CT) images instead of a single phase for accurate diagnosis for clinical applications. We have proposed a framework that can perform segmentation from quadriphasic CT data. The liver was segmented using a fine-tuned SegNet model and the liver tumor was segmented using the K-means clustering method coupled with a power-law transformation-based image enhancement technique. The best values for liver segmentation achieved were: Dice Coefficient = 96.46 ± 0.48%, Jaccard Index = 93.16 ± 0.89%, volumetric overlap error = 6.84 ± 0.89% and average symmetric surface distance = 0.59 ± 0.3 mm and the results for liver tumor delineation were Dice Coefficient = 85.07 ± 4.5%, Jaccard Index = 74.29 ± 6.8%, volumetric overlap error = 25.71 ± 6.8% and average symmetric surface distance = 1.14 ± 1.3 mm. The proposed liver segmentation method based on deep learning is fully automatic, robust, and effective for all phases. The image enhancement technique has shown promising results and aided in better liver tumor segmentation. The liver tumors were segmented satisfactorily; however, improvements concerning false positive reduction can further increase the accuracy.     

A variational level set segmentation formulation based on signal model for images in the presence of intensity inhomogeneity

Biological images with significant intensity inhomogeneity are considerably difficult for the tissue segmentation. To overcome the difficulties caused by the intensity inhomogeneity, this study presents a variational level set method to simultaneous bias field estimation and tissue segmentation for images in the presence of intensity inhomogeneity. An energy function is defined in terms of two data fitting terms which incorporate the local clustering properties into the global region information. First, depended on the observed image mode, the local cluster property based on the observed signal is simplified to a criterion function which is similar to the Mumford‐Shah model. The local criterion energy is then integrated with a global region measure, which is based on intensity difference of the true signal. The energy is minimized in a variational level set formulation with a regularity term, thus avoiding the expensive computation of the level set reinitialization and keeping the curve close to the signal distance function. Experiment results on biological images show desirable performance and demonstrate the effectiveness of the proposed algorithm.     

Integrated segmentation of brain tumor images for radiotherapy and neurosurgery

Segmentation of brain tumor images is an important task in diagnosis and treatment planning for cancer patients. To achieve this goal with standard clinical acquisition protocols, conventionally, either classification algorithms are applied on multimodal MR images or atlas‐based segmentation is used on a high‐resolution monomodal MR image. These two approaches have been commonly regarded separately. We propose to integrate all the available imaging information into one framework to be able to use the information gained from the tissue classification of the multimodal images to perform a more precise segmentation on the high‐resolution monomodal image by atlas‐based segmentation. For this, we combine a state of the art regularized classification method with an enhanced version of an atlas‐registration approach including multiscale tumor‐growth modeling. This contribution offers the possibility to simultaneously segment subcortical structures in the patient by warping the respective atlas labels, which is important for neurosurgical planning and radiotherapy planning. © 2013 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 23, 59–63, 2013     

Development of automatic glioma brain tumor detection system using deep convolutional neural networks

We have developed six convolutional neural network (CNN) models for finding optimal brain tumor detection system on high-grade glioma and low-grade glioma lesions from voluminous magnetic resonance imaging human brain scans. Glioma is the most common form of brain tumor. The models are constructed based on the different combinations and settings of hyperparameters with conventional CNN architecture. The six models are two layers with five epochs, five layers with dropout, five layers with stopping criteria (FLSC), FLSC and dropout (FLSCD), FLSC and batch normalization (FLSCBN), and FLSCBN and dropout. The models were trained and tested with BraTS2013 and whole brain atlas data sets. Among them, FLSCBN model yielded the best classification results for brain tumor detection. Experimental results revealed that our deep learning approach was better than the conventional state-of-art methods.     

Structural shape and topology optimization using a meshless Galerkin level set method

This paper aims to propose a meshless Galerkin level set method for shape and topology optimization of continuum structures. To take advantage of the implicit free boundary representation scheme, the design boundary is represented as the zero level set of a scalar level set function, to flexibly handle complex shape fidelity and topology changes by maintaining concise and smooth interface. Compactly supported radial basis functions (CSRBFs) are used to parameterize the level set function and construct the shape functions for meshfree approximations based on a set of unstructured field nodes. The meshless Galerkin method with global weak form is used to implement the discretization of the state equations. This provides a pathway to unify the two different numerical stages in most conventional level set methods: (1) the propagation of discrete level set function on a set of Eulerian grid and (2) the approximation of discrete equations on a set of Lagrangian mesh. The original more difficult shape and topology optimization based on the level set equation is transformed into a relatively easier size optimization, to which many efficient optimization algorithms can be applied. The proposed level set method can describe the moving boundaries without remeshing for discontinuities. The motion of the free boundary is just a question of advancing the discrete level set function in time by solving the size optimization. Several benchmark examples are used to demonstrate the effectiveness of the proposed method. The numerical results show that the proposed method can simplify numerical process and avoid numerical difficulties involved in most conventional level set methods. It is straightforward to apply the proposed method to more advanced shape and topology optimization problems. Copyright © 2011 John Wiley & Sons, Ltd.     

Image registration-based brain tumor detection and segmentation using ANFIS classification approach

Abnormal cells in human brain lead to the development of tumors. Manual detection of this tumor region is a time-consuming process. Hence, this paper proposes an efficient and automated computer-aided methodology for brain tumor detection and segmentation using image registration technique and classification approaches. This proposed work consists of the following modules: image registration, contourlet transform, and feature extraction with feature normalization, classification, and segmentation. The extracted features are optimized using genetic algorithm, and then an adaptive neuro-fuzzy inference system classification approach is used to classify the features for the detection and segmentation of tumor regions in brain magnetic resonance imaging. A quantitative analysis is performed to evaluate the proposed methodology for brain tumor detection using sensitivity, specificity, segmentation accuracy, precision, and Dice similarity coefficient.