Image Segmentation System Research Articles

MULTIRESOLUTION ANALYSIS USING WAVELET TRANSFORMS FOR MEDICAL IMAGE SEGMENTATION

The experimental study presented in this paper is aimed at the development of an automatic image segmentation system for classifying region of interest (ROI) in medical images which are obtained from medical scanners like MRI. Multiresolution analysis (MRA) using wavelet transforms has been used in the proposed segmentation system. It is particularly a challenging task to classify cancers in human organs in scanners output using shape or gray-level information; organs shape changes throw different slices in medical stack and the gray-level intensity overlap in soft tissues. This paper presents the application of wavelet transform to perform these task using the three dimensional waveletdecomposition, coefficients thresholding and object reconstruction. The proposed method is verified for simulated data at first and then applied for processing of brain parts to emphasize its selected components. The goal of the paper is in (i) the presentation of the three-dimensional wavelet transform, (ii) discussion of its use for volume data denoising, and (iii) proposal of the following data extraction to allow their classification. The paper compares numerical results achieved by the use of different wavelet functions and thresholding methods with the experience of an expert to propose the best algorithmic approach to this problem.

Novel coupled DP system for fuzzy C-means clustering and image segmentation

This study proposed a novel fuzzy c-means clustering method which calculates the density of the data points based on the weighted mean distance (WMFCM). A novel coupled DNA-GA and P system (DP system) is introduced to realize the clustering process. The evolutional rules in the coupled DP system can help the WMFCM algorithm jump out of the local optimum and get the initial clustering centers. The performance of the coupled DP system in dealing with fuzzy clustering problems is measured by conducting experimental analysis on UCI datasets and BSDS300 image datasets. And the experimental results are compared with several popular algorithms. Experimental results show that our algorithm can perform better than other algorithms.

Deep learning neural networks for medical image segmentation of brain tumours for diagnosis: a recent review and taxonomy

Brain tumour identification with traditional magnetic resonance imaging (MRI) tends to be time-consuming and in most cases, reading of the resulting images by human agents is prone to error, making it desirable to use automated image segmentation. This is a multi-step process involving: (a) collecting data in the form of raw processed or raw images, (b) removing bias by using pre-processing, (c) processing the image and locating the brain tumour, and (d) showing the tumour affected areas on a computer screen or projector. Several systems have been proposed for medical image segmentation but have not been evaluated in the field. This may be due to ongoing issues of image clarity, grey and white matter present in a scan image, lack of knowledge of the end user and constraints arising from MRI imaging systems. This makes it imperative to develop a comprehensive technique for the accurate diagnosis of brain tumors in MRI images. In this paper, we introduce a taxonomy consisting of ‘Data, Image segmentation processing, and View’ (DIV) which are the major components required to develop a high-end system for brain tumour diagnosis based on deep learning neural networks. The DIV taxonomy is evaluated based on system completeness and acceptance. The utility of the DIV taxonomy is demonstrated by classifying 30 state-of-the-art publications in the domain of medFical image segmentation systems based on deep neural networks. The results demonstrate that few components of medical image segmentation systems have been validated although several have been evaluated by identifying role and efficiency of the components in this domain.

An Improved Image Segmentation System

In this paper, we present a solution-based cooperation approach for strengthening the image segmentation.This paper proposes a cooperative method relying on Multi-Agent System. The main contribution of this work is to highlight the importance of cooperation between the contour and region growing based on Multi-Agent System (MAS). Consequently, agents’ interactions form the main part of the whole process for image segmentation. Similar works were proposed to evaluate the effectiveness of the proposed solution. The main difference is that our Multi-Agent System can perform the segmentation process ensuring efficiency. Our results show that the performance indices in the system were higher. Furthermore, the integration of the cooperation paradigm allows to speed up the segmentation process. Besides, the tests reveal the robustness of our method by proving competitive results. Our proposal achieved an accuracy of 93,51%± 0,8, a sensitivity of 93,53%± 5,08 and a specificity rate of 92,64%± 4,01.

Simplifying TugGraph using zipping algorithms

Graphs are an invaluable modelling tool in many domains, but visualising large graphs in their entirety can be difficult. Hierarchical graph visualisation – recursively clustering a graph’s nodes to view it at a higher level of abstraction – has thus become popular. However, this can hide important information that a user needs to understand a graph’s topology, e.g. nodes’ neighbourhoods. TugGraph addressed this by ‘separating out’ a given node’s neighbours from their hierarchy ancestors to visualise them independently. Its original implementation was straightforward, but copied parts of the hierarchy, making it slow and memory-hungry. An optimised later version, which we refer to as FastTug, avoided this, but at a cost in clarity. Optimising TugGraph without sacrificing clarity is difficult because of the need to keep every hierarchy node connected, a common challenge for graph hierarchy editing algorithms. Recently, this problem has been addressed by ‘zipping’ algorithms, multi-level split/merge algorithms that preserve hierarchy node connectedness and can be built upon for higher-level editing. In this paper, we generalise the original unzipping algorithms to implement SimpleTug, a simple, modular version of TugGraph that is easy to understand and implement, and even faster and more memory-efficient than FastTug. We formally prove its equivalence to FastTug, and show how both can be parallelised. Using our millipede hierarchical image segmentation system, we show experimentally that both the serial and parallel versions of SimpleTug are around 25% faster than their FastTug counterparts, whilst using considerably less memory. Finally, we discuss the interesting theoretical connections between TugGraph and zipping, and suggest ideas for further work.

A Video Image Segmentation System for the Fruit-trees in Multi-stage Outdoors Orchard under Natural Conditions

Segmentation is an important part of each machine vision system that has a direct relationship with the final system accuracy and performance. Outdoors segmentation is often complex and difficult due to both changes in sunlight intensity and the different nature of background objects. However, in fruit-tree orchards, an automatic segmentation algorithm with high accuracy and speed is very desirable. For this reason, a multi-stage segmentation algorithm is applied for the segmentation of apple fruits with Red Delicious cultivar in orchard under natural light and background conditions. This algorithm comprises a combination of five segmentation stages, based on: 1- L*u*v* color space, 2- local range texture feature, 3- intensity transformation, 4- morphological operations, and 5- RGB color space. To properly train a segmentation algorithm, several videos were recorded under nine different light intensities in Iran- Kermanshah (longitude: 7.03E; latitude: 4.22N) with natural (real) conditions in terms of both light and background. The order of segmentation stage methods in multi-stage algorithm is very important since has a direct relationship with final segmentation accuracy. The best order of segmentation methods resulted to be: 1- color, 2- texture and 3- intensity transformation methods. Results show that the values of sensitivity, accuracy and specificity, in both classes, were higher than 97.5%, over the test set. We believe that those promising numbers imply that the proposed algorithm has a remarkable performance and could potentially be applied in real-world industrial case.

Sunflower leaf diseases detection using image segmentation based on particle swarm optimization

Sun flower (Helianthus annuus L.) is one of the important oil seed crops and potentially fit in agricultural system and oil production sector of India. Sunflower crop gets damaged by the impact of various diseases, insects and nematodes resulting in wide range of loss in production. Disease detection is possible through naked eye observation, but this method is unsuccessful when one has to monitor the large farms. As a solution to this problem, we developed and present a system for segmentation and classification of Sunflower leaf images. This research paper presents surveys conducted on different diseases classification techniques that can be used for sunflower leaf disease detection. Segmentation of Sunflower leaf images, which is an important aspect for disease classification, is done by using Particle swarm optimization algorithm. Satisfactory results have been given by the experiments done on leaf images. The average accuracy of classification of proposed algorithm is 98.0% compared to 97.6 and 92.7% reported in state-of-the-art methods.

FourEyes

Crowdsourcing is a common means of collecting image segmentation training data for use in a variety of computer vision applications. However, designing accurate crowd-powered image segmentation systems is challenging, because defining object boundaries in an image requires significant fine motor skills and hand-eye coordination, which makes these tasks error-prone. Typically, special segmentation tools are created and then answers from multiple workers are aggregated to generate more accurate results. However, individual tool designs can bias how and where people make mistakes, resulting in shared errors that remain even after aggregation. In this article, we introduce a novel crowdsourcing approach that leverages tool diversity as a means of improving aggregate crowd performance. Our idea is that given a diverse set of tools, answer aggregation done across tools can help improve the collective performance by offsetting systematic biases induced by the individual tools themselves. To demonstrate the effectiveness of the proposed approach, we design four different tools and present FourEyes, a crowd-powered image segmentation system that uses aggregation across different tools. We then conduct a series of studies that evaluate different aggregation conditions and show that using multiple tools can significantly improve aggregate accuracy. Furthermore, we investigate the idea of applying post-processing for multi-tool aggregation in terms of correction mechanism. We introduce a novel region-based method for synthesizing more accurate bounds for image segmentation tasks through averaging surrounding annotations. In addition, we explore the effect of adjusting the threshold parameter of an EM-based aggregation method. Our results suggest that not only the individual tool’s design, but also the correction mechanism, can affect the performance of multi-tool aggregation. This article extends a work presented at ACM IUI 2018 [46] by providing a novel region-based error-correction method and additional in-depth evaluation of the proposed approach.

Development of an acousto-optic system for hyperspectral image segmentation

Development of an acousto-optic system for hyperspectral image segmentation

Deep Learning-based Image Segmentation on Multimodal Medical Imaging.

Multi-modality medical imaging techniques have been increasingly applied in clinical practice and research studies. Corresponding multi-modal image analysis and ensemble learning schemes have seen rapid growth and bring unique value to medical applications. Motivated by the recent success of applying deep learning methods to medical image processing, we first propose an algorithmic architecture for supervised multi-modal image analysis with cross-modality fusion at the feature learning level, classifier level, and decision-making level. We then design and implement an image segmentation system based on deep Convolutional Neural Networks (CNN) to contour the lesions of soft tissue sarcomas using multi-modal images, including those from Magnetic Resonance Imaging (MRI), Computed Tomography (CT) and Positron Emission Tomography (PET). The network trained with multi-modal images shows superior performance compared to networks trained with single-modal images. For the task of tumor segmentation, performing image fusion within the network (i.e. fusing at convolutional or fully connected layers) is generally better than fusing images at the network output (i.e. voting). This study provides empirical guidance for the design and application of multi-modal image analysis.

Cloud-Based Brain Magnetic Resonance Image Segmentation and Parcellation System for Individualized Prediction of Cognitive Worsening.

For patients with cognitive disorders and dementia, accurate prognosis of cognitive worsening is critical to their ability to prepare for the future, in collaboration with health-care providers. Despite multiple efforts to apply computational brain magnetic resonance image (MRI) analysis in predicting cognitive worsening, with several successes, brain MRI is not routinely quantified in clinical settings to guide prognosis and clinical decision-making. To encourage the clinical use of a cutting-edge image segmentation method, we developed a prediction model as part of an established web-based cloud platform, MRICloud. The model was built in a training dataset from Alzheimer's Disease Neuroimaging Initiative (ADNI) where baseline MRI scans were combined with clinical data over time. Each MRI was parcellated into 265 anatomical units based on the MRICloud fully automated image segmentation function, to measure the volume of each parcel. The Mini Mental State Examination (MMSE) was used as a measure of cognitive function. The normalized volume of 265 parcels, combined with baseline MMSE score, age, and sex were input variables for a Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis, with MMSE change in the subsequent two years as the target for prediction. A leave-one-out analysis performed on the training dataset estimated a correlation coefficient of 0.64 between true and predicted MMSE change. A receiver operating characteristic (ROC) analysis estimated a sensitivity of 0.88 and a specificity of 0.76 in predicting substantial cognitive worsening after two years, defined as MMSE decline of ≥4 points. This MRICloud prediction model was then applied to a test dataset of clinically acquired MRIs from the Johns Hopkins Memory and Alzheimer's Treatment Center (MATC), a clinical care setting. In the latter setting, the model had both sensitivity and specificity of 1.0 in predicting substantial cognitive worsening. While the MRICloud prediction model demonstrated promise as a platform on which computational MRI findings can easily be extended to clinical use, further study with a larger number of patients is needed for validation.

基于PSO-KMeans算法的MATLAB(GUI)图像分割系统平台开发应用

基于PSO-KMeans算法的MATLAB(GUI)图像分割系统平台开发应用

Atlas pre-selection strategies to enhance the efficiency and accuracy of multi-atlas brain segmentation tools.

Multi-atlas brain segmentation of human brain MR images allows quantification research in structural neuroimaging. To achieve high accuracy and computational efficiency of segmentation relies on a custom subset of atlases for each target subject. However, the criterion for atlas pre-selection remains an open question. In this study, two atlas pre-selection approaches based on location-based feature matching were proposed and compared to random and mutual information-based methods using a database of 47 atlases. A varying number of atlases ranked top with hierarchical structural granularity were compared using Dice overlap. The results indicated that the proposed 4L approach consistently led to the highest level of accuracy at a given number of employed atlases in both adult and geriatric populations. In addition, the proposed two methods (4L and LV) can reduce 20 times computational time compared with the stereotypical mutual information-based method. Our pre-selection strategy would provide better segmentation performance in terms of both accuracy and efficiency. The proposed atlas pre-selection will be further implemented into our online automatic brain image segmentation system (www.mricloud.org).

Study on Multi-Scale Window Determination for GLCM Texture Description in High-Resolution Remote Sensing Image Geo-Analysis Supported by GIS and Domain Knowledge

Texture features based on the gray-level co-occurrence matrix (GLCM) can effectively improve classification accuracy in geographical analyses of optical remote sensing (RS) images, with the parameters of scale of the GLCM texture window greatly affecting the validity. By analyzing human visual attention characteristics for geo-texture cognition, it was found that there is a strong correlation between the texture scale parameters and the domain shape knowledge in a specified geo-scene. Therefore, a new approach for quickly determining the multi-scale parameters of the texture with the assistance of a geographic information system (GIS) and domain knowledge is proposed in this paper. First, the validity of domain knowledge from an existing GIS database is measured by spatial data mining algorithms, including spatial partitioning, image segmentation, and space-time system evaluation. Second, the general domain shape knowledge of each category is described by the GIS minimum enclosing rectangle indices and rectangular-degree indices. Then, the corresponding multi-scale texture windows can be quickly determined for each category by a correlation analysis with the shape indices. Finally, the Fisher function is used to evaluate the validity of the scale parameters. The experimental results show that the multi-scale value keeps a one-to-one relationship with the classified objects, and their value ranges are from a few to tens, instead of the smaller values of a traditional analysis; thus, effective texture features at such a scale can be built to identify categories in a geo-scene. In this way, the proposed method can increase the total number of categories for a certain geo-scene and reduce the classification uncertainty, as well as better meet the requirements of large-scale image geo-analysis. It also has as high a calculation efficiency and as good a performance as the traditional enumeration method.

Improved particle swarm optimisation to estimate bone age

This paper automatizes the process of bone age maturity assessment by applying three versions of particle swarm optimization (PSO) along with image processing methods to the left hand X-ray images. PSO versions were adopted to enhance the segmentation accuracy. The proposed method was compared to the conventional visual inspection method in terms of three segmentation criteria, classification accuracy, robustness against noise and computational complexity. Herein, PSO, worst behavior-based PSO (WB-PSO) and adaptive inertia weight (AIW-PSO) along with Otsu and an iteratively statistical method were implemented to segment the hand radiographs. A dataset containing left hand-wrist radiographs from 65 referred children was collected. Their results provided 82.49, 83.08, 84.27, 81.76 and 69.04% classification accuracy using the PSO, WB-PSO, AIW-PSO, Otsu and the iteratively statistical methods, respectively. To assess the robustness of the implemented methods, white Gaussian noise with different intensities was added to the images and the results indicated that as the noise level increased the robustness against noise for the PSO variants became more highlighted compared to the Otsu and statistical methods. Due to the convincing results, the AIW-PSO image segmentation system is suggested as an auxiliary diagnostic tool to help specialists for more accurate age bone estimation.

A novel fuzzy clustering based system for medical image segmentation

Segmenting region of interest in medical images is challenging because medical image suffers from noise, degradation due to environment influence and low resolution due to devices, etc. In this paper, we have developed a novel idea based on weighted spatial kernel FCM clustering for segmenting region of interest in the medical images. Unlike traditional methods which ignore spatial information, we propose a new robust system that explores spatial information to remove uncertainty in identifying accurate region in the medical images. Furthermore, the proposed method estimates the weights for spatial information to derive precise membership function to segment the region based on Gaussian kernel as distance metric. We conducted experiments on standard datasets, namely MRI Brian image dataset and evaluated performance of the proposed method using recall, precision and f-measure. Experimental results reveal that, the proposed method performs better compared to existing methods.

A novel fuzzy clustering based system for medical image segmentation

Segmenting region of interest in medical images is challenging because medical image suffers from noise, degradation due to environment influence and low resolution due to devices, etc. In this paper, we have developed a novel idea based on weighted spatial kernel FCM clustering for segmenting region of interest in the medical images. Unlike traditional methods which ignore spatial information, we propose a new robust system that explores spatial information to remove uncertainty in identifying accurate region in the medical images. Furthermore, the proposed method estimates the weights for spatial information to derive precise membership function to segment the region based on Gaussian kernel as distance metric. We conducted experiments on standard datasets, namely MRI Brian image dataset and evaluated performance of the proposed method using recall, precision and f-measure. Experimental results reveal that, the proposed method performs better compared to existing methods.

Plant Diseases Recognition Based on Image Processing Technology

A new image recognition system based on multiple linear regression is proposed. Particularly, there are a number of innovations in image segmentation and recognition system. In image segmentation, an improved histogram segmentation method which can calculate threshold automatically and accurately is proposed. Meanwhile, the regional growth method and true color image processing are combined with this system to improve the accuracy and intelligence. While creating the recognition system, multiple linear regression and image feature extraction are utilized. After evaluating the results of different image training libraries, the system is proved to have effective image recognition ability, high precision, and reliability.

A Multi-Anatomical Retinal Structure Segmentation System for Automatic Eye Screening Using Morphological Adaptive Fuzzy Thresholding

Eye exam can be as efficacious as physical one in determining health concerns. Retina screening can be the very first clue for detecting a variety of hidden health issues including pre-diabetes and diabetes. Through the process of clinical diagnosis and prognosis; ophthalmologists rely heavily on the binary segmented version of retina fundus image; where the accuracy of segmented vessels, optic disc, and abnormal lesions extremely affects the diagnosis accuracy which in turn affect the subsequent clinical treatment steps. This paper proposes an automated retinal fundus image segmentation system composed of three segmentation subsystems follow same core segmentation algorithm. Despite of broad difference in features and characteristics; retinal vessels, optic disc, and exudate lesions are extracted by each subsystem without the need for texture analysis or synthesis. For sake of compact diagnosis and complete clinical insight, our proposed system can detect these anatomical structures in one session with high accuracy even in pathological retina images. The proposed system uses a robust hybrid segmentation algorithm combines adaptive fuzzy thresholding and mathematical morphology. The proposed system is validated using four benchmark datasets: DRIVE and STARE (vessels), DRISHTI-GS (optic disc), and DIARETDB1 (exudates lesions). Competitive segmentation performance is achieved, outperforming a variety of up-to-date systems and demonstrating the capacity to deal with other heterogeneous anatomical structures.

Fractional gravitational search-radial basis neural network for bone marrow white blood cell classification

ABSTRACTAutomotive image segmentation systems are becoming an important tool in the medical field for disease diagnosis. The white blood cell (WBC) segmentation is crucial, because it plays an important role in the determination of the diseases and helps experts to diagnose the blood disease disorders. The precise segmentation of the WBCs is quite challenging because of the complex contents in the bone marrow smears. In this paper, a novel neural network (NN) classifier is proposed for the classification of the bone marrow WBCs. The proposed NN classifier integrates the fractional gravitation search (FGS) algorithm for updating the weight in the radial basis function mapping for the classification of the WBC based on the cell nucleus feature. The experimentation of the proposed FGS-RBNN classifier is carried on the images collected from the publically available dataset. The performance of the proposed methodology is evaluated over the existing classifier approaches using the measures accuracy, sensitivity, and specificity. The results show that the classification using the nucleus features alone can be utilized to achieve the classification with the better accuracy. Moreover, the classification performance of the proposed FGS-RBNN is better than the existing classifiers, and it is proved to be the efficacious classifier with a classification accuracy of 95%.