Image Segmentation Applications Research Articles

Interval type-2 outlier-robust picture fuzzy clustering and its application in medical image segmentation

Based on picture fuzzy set theory, picture fuzzy clustering has achieved good results on some data as more information is involved in the clustering process. However, current picture fuzzy clustering methods still suffer from two common weaknesses, i.e., the sensitivity to outliers and the neglect of the uncertainty caused by different fuzzy degrees, which influence their performance in practical applications like medical image segmentation. To solve these issues, we present two new picture fuzzy clustering methods in this paper. First, to improve immunity to outliers, we propose an outlier-robust picture fuzzy clustering method named ORPFC by using a robust distance measurement, which treats the data objects far away from cluster prototypes as outliers and limits their effects on the prototype update. Second, to handle the uncertainty caused by fuzzy degrees, we further present an interval type-2 enhanced method called IT2ORPFC by incorporating the interval type-2 fuzzy set theory into ORPFC. In each iteration, IT2ORPFC estimates positive memberships, neutral memberships, and refusal memberships according to different fuzzification coefficients and then conducts type reduction for reliable type-1 clustering results. In the experiments, the proposed methods obtain robust and reliable results on eleven datasets. Specifically, ORPFC and IT2ORPFC achieve rewarding performance on segmenting medical images with noise.

A coarse-to-fine full attention guided capsule network for medical image segmentation

As an important material in clinical diagnoses, medical images are widely used by the doctors to discover the diseases and make therapeutic schedules. Accurately locating the lesions and correctly delineating their severities based on the medical images can significantly help to improve the detection rate and diagnosis accuracy of the diseases. In this paper, we design an effective attention guided capsule network, named HR-CapsSegNet, for segmenting medical targets from medical images. First, by forming a capsule-based high-resolution network architecture assisted by cross-branch multiscale feature augmentation, the HR-CapsSegNet performs advantageously in providing multiscale feature representations with high-level strong semantics. Second, by designing a capsule-based full attention mechanism, the feature encoding quality at each scale can be significantly promoted by sticking up the informative feature semantics from a cross-channel global perspective. In addition, by employing a hierarchical coarse-to-fine segmentation strategy, the feature distractions causing false recognitions can be progressively removed to provide an accurate segmentation map. Intensive quantitative assessments, visual examinations, and comparative analyses on four challenging datasets prove the promising applicability and competitive superiority of the HR-CapsSegNet for medical image segmentation applications.

ADC textural features in patients with single brain metastases improve clinical risk models

AimsIn this retrospective study we performed a quantitative textural analysis of apparant diffusion coefficient (ADC) images derived from diffusion weighted MRI (DW-MRI) of single brain metastases (BM) patients from different primary tumors and tested whether these imaging parameters may improve established clinical risk models.MethodsWe identified 87 patients with single BM who had a DW-MRI at initial diagnosis. Applying image segmentation, volumes of contrast-enhanced lesions in T1 sequences, hyperintense T2 lesions (peritumoral border zone (T2PZ)) and tumor-free gray and white matter compartment (GMWMC) were generated and registered to corresponding ADC maps. ADC textural parameters were generated and a linear backward regression model was applied selecting imaging features in association with survival. A cox proportional hazard model with backward regression was fitted for the clinical prognostic models (diagnosis-specific graded prognostic assessment score (DS-GPA) and the recursive partitioning analysis (RPA)) including these imaging features.ResultsThirty ADC textural parameters were generated and linear backward regression identified eight independent imaging parameters which in combination predicted survival. Five ADC texture features derived from T2PZ, the volume of the T2PZ, the normalized mean ADC of the GMWMC as well as the mean ADC slope of T2PZ. A cox backward regression including the DS-GPA, RPA and these eight parameters identified two MRI features which improved the two risk scores (HR = 1.14 [1.05;1.24] for normalized mean ADC GMWMC and HR = 0.87 [0.77;0.97]) for ADC 3D kurtosis of the T2PZ.)ConclusionsTextural analysis of ADC maps in patients with single brain metastases improved established clinical risk models. These findings may aid to better understand the pathogenesis of BM and may allow selection of patients for new treatment options.

Otsu Method for Chicken Egg Embryo Detection based-on Increase Image Quality

Detection of chicken egg embryos using image processing has limitations and needs some processes for improvement. By human vision, the previous process used binoculars and candling using light/beams directed at the chicken eggs in the incubator. In this study, we propose the application of image segmentation using the Otsu method in detecting chicken egg embryos. This method uses image segmentation with increased image quality (preprocessing) by several methods such as resizing, grayscaling, image adjustment, and image enhancement. These processes produce a better image and can be used for input in the segmentation process. In addition, this study compares several segmentation methods in detecting chicken egg embryos, such as thresholding, Otsu basic, and k-means clustering. The results show that our proposed method produced segmentation images to detect chicken egg embryos of 200 datasets images. This method has a faster process and can create a uniform segmentation than other methods. However, other methods can also detect chicken egg embryos. The method’s accuracy proposed in this study increased by 1.5% compared to other methods. In addition, the resulting SSIM value has a percentage close to and more than 90%, which means that the segmentation of the results obtained can be used to detect chicken egg embryos.

A memristive RBF neural network and its application in unsupervised medical image segmentation

A memristive RBF neural network and its application in unsupervised medical image segmentation

AnalyZr: A Python application for zircon grain image segmentation and shape analysis

Zircon grain shape is traditionally interpreted as a product of the physico-chemical conditions during crystal growth and may be modified during grain transport processes. The analysis of magmatic zircon grain shape has been proposed to inform on crystallization conditions, whereas detrital zircon grain shape has been proposed to complement traditional sediment provenance analysis. Shape parameters can be automatically measured from digital images of zircon mounts; however, this requires extraction of individual grain boundaries for measurement. Existing image segmentation software may require the use of proprietary languages, or knowledge of scripting to develop automated image segmentation routines, and is typically not tailored towards the geosciences. Furthermore, the separation of touching zircon grains in images remains a challenge for existing algorithms. To facilitate zircon grain shape analysis, we present AnalyZr, an open-source graphical Python application designed to segment reflected and transmitted light images of zircons mounted in resin. A new segmentation algorithm is implemented to improve the separation of touching zircon grains. Shape parameters are automatically measured from the segmented images and may be output to a .csv or .mdb file. Two case studies demonstrate the use of the application in resolving geologically relevant information in zircon grains sourced from: i) compositionally and age-distinct granite, diorite, and gabbro samples from across Western Australia, and ii) age-distinct detrital zircons from the Canning Basin, Western Australia.

An end-to-end approach to segmentation in medical images with CNN and posterior-CRF.

Conditional Random Fields (CRFs) are often used to improve the output of an initial segmentation model, such as a convolutional neural network (CNN). Conventional CRF approaches in medical imaging use manually defined features, such as intensity to improve appearance similarity or location to improve spatial coherence. These features work well for some tasks, but can fail for others. For example, in medical image segmentation applications where different anatomical structures can have similar intensity values, an intensity-based CRF may produce incorrect results. As an alternative, we propose Posterior-CRF, an end-to-end segmentation method that uses CNN-learned features in a CRF and optimizes the CRF and CNN parameters concurrently. We validate our method on three medical image segmentation tasks: aorta and pulmonary artery segmentation in non-contrast CT, white matter hyperintensities segmentation in multi-modal MRI, and ischemic stroke lesion segmentation in multi-modal MRI. We compare this with the state-of-the-art CNN-CRF methods. In all applications, our proposed method outperforms the existing methods in terms of Dice coefficient, average volume difference, and lesion-wise F1 score.

Improving an inkjet printer: Removing stray-dots by constraining error diffusion in highlight regions

In our previous paper presented in the last year, we mostly focused on the color saturation problem in our inkjet printer. However, our partner reported that there are some boundary noise pixels on the background, which are quite visible when the background is white. By checking the pipeline of our printing procedure, we realized that the noise stray dots are generated during the halftoning procedure. This paper is dedicated to separate the white background from the foreground, which enables us to constrain the error diffusion process inside the white background. The main idea is to apply image segmentation, which could help us to precisely extract the background.

A Collaborative Dragonfly Algorithm with Novel Communication Strategy and Application for Multi-Thresholding Color Image Segmentation

<p>The Dragonfly Algorithm (DA) is a novel swarm intelligence algorithm with some positive applications in recent years. The algorithm simulates the basic survival ability of dragonflies to evade predators and capture prey in natural environment. The original DA algorithm converges too fast, and it is easy to fall into the local optimum, which causes the search to stagnate and the algorithm effect is not ideal. Based on above, a collaborative evolutionary dragonfly algorithm (CDA) with multi-group strategy is proposed in this paper. It uses multi-group strategy and Cauchy mutation to jointly improve the convergence speed and accuracy of the original algorithm. Image segmentation is an essential aspect of computer graphics and image processing. It has become increasingly important. This paper uses threshold technology based on the CDA algorithm to find the optimal index value under different threshold conditions. The experimental results have demonstrated that the CDA is highly competitive in terms of convergence speed and convergence accuracy DA algorithm, and CDA also performs excellent advantages in graphic segmentation experiments.</p> <p> </p>

The Application of Image Segmentation to Determine the Ratio of Peritumoral Edema Area to Tumor Area on Primary Malignant Brain Tumor and Metastases through Conventional Magnetic Resonance Imaging


 BACKGROUND: Primary malignant brain tumor and metastases on the brain have a similar pattern in conventional Magnetic Resonance Imaging (MRI), even though both require entirely different treatment and management. The pathophysiological difference of peritumoral edema can help to distinguish the case of primary malignant brain tumor and brain metastases. 
 
 
 AIM: This study aimed to analyze the ratio of the area of peritumoral edema to the tumor using Otsu’s method of image segmentation technique with a user-friendly Graphical User Interface (GUI). 
 
 
 METODS: Data was prepared by obtaining the examination results of Anatomical Pathology and MRI imaging. The area of peritumoral edema was identified from MRI image segmentation with T2/FLAIR sequence. While the area of tumor was identified using MRI image segmentation with T1 sequence. 
 
 
 RESULTS: The Mann-Whitney test was employed to analyze the ratio of the area of peritumoral edema to tumor on both groups. Data testing produced a significance level of 0.013 (p < 0.05) with a median value (Nmax-Nmin) of 1.14 (3.31-0.08) for the primary malignant brain tumor group and a median value (Nmax-Nmin) of 1.17 (10.30-0.90) for the brain metastases group. 
 
 
 CONCLUSIONS: There was a significant difference in the ratio of the area of peritumoral edema to the area of tumor from both groups, in which brain metastases have a greater value than the primary malignant brain tumor.

Application of Image Segmentation to Identify In-flight Particles in Thermal Spraying.

In thermal spray process, the characteristics of in-flight particles (velocity and temperature) play an important role regarding the microstructure of the deposit and thus the coating performances. The implementation of diagnostic devices is necessary to measure such characteristics. Many imaging systems and algorithms have been developed for identifying and tracking in-flight particles. However, these current image systems have significant limitations in terms of accuracy for example. One key to solving the tracking problem is to get an algorithm that can effectively distinguish different particles in the same image frame at the same time. This study aims to develop an algorithm capable of identifying a large number of in-flight particles sprayed by thermal process. The results show that the noise and vignettes could be successfully treated, particles are clearly recognized in the background, leading to properly measuring the sizes and positions of the particle versus time. The proposed algorithm has a higher recognition rate and recognition range than other algorithms, which will provide a reasonable basis for subsequent calculation and processing.

Characteristics of Computed Tomography Images for Patients with Acute Liver Injury Caused by Sepsis under Deep Learning Algorithm

This study was aimed at exploring the application of image segmentation based on full convolutional neural network (FCN) in liver computed tomography (CT) image segmentation and analyzing the clinical features of acute liver injury caused by sepsis. The Sigmoid function, encoder-decoder, and weighted cross entropy loss function were introduced and optimized based on FCN. The Dice value, precision, recall rate, volume overlap error (VOE), relative volume difference (RVD), and root mean square error (RMSE) values of the optimized algorithms were compared and analyzed. 92 patients with sepsis were selected as the research objects, and they were divided into a nonacute liver injury group (50 cases) and acute liver injury group (42 cases) based on whether they had acute liver injury. The differences in the proportion of patients with different disease histories, the proportion of patients with different infection sites, the number of organ failure, and the time of admission to intensive care unit (ICU) were compared between the two groups. It was found that the optimized window CT image Dice value after preprocessing (0.704 ± 0.06) was significantly higher than the other two methods (P < 0.05). The Dice value, precision, and recall rate of the optimized-FCN algorithm were (0.826 ± 0.06), (0.91 ± 0.08), and (0.88 ± 0.09), respectively, which were significantly higher than other algorithms (P < 0.05). The VOE, RVD, and RMSE values were (21.19 ± 1.97), (10.45 ± 1.02), and (0.25 ± 0.02), respectively, which were significantly lower than other algorithms (P < 0.05). The proportion of patients with a history of drinking in the nonacute liver injury group was lower than that in the acute liver injury group (P < 0.05), and the proportion of patients with a history of hypotension was greatly higher than that in the nonacute liver injury group (P < 0.01). CT images of sepsis patients with acute liver injury showed that large areas of liver parenchyma mixed with high-density hematoma, the number of organ failures, and the length of stay in ICU were significantly higher than those in the nonacute liver injury group (P < 0.05). It showed that the optimization algorithm based on FCN greatly improved the performance of CT image segmentation. Long-term drinking, low blood pressure, number of organ failures, and length of stay in ICU were all related to sepsis and acute liver injury. Conclusion in this study could provide a reference basis for the diagnosis and prognosis of acute liver injury caused by sepsis.

Multi-Model Medical Image Segmentation Using Multi-Stage Generative Adversarial Networks

Image segmentation is a challenging problem in medical applications. Medical imaging has become an integral part of machine learning research, as it enables inspecting interior human body with no surgical intervention. Much research has been conducted to study brain segmentation. However, prior studies usually employ one-stage models to segment brain tissues, which could lead to a significant information loss. In this paper, we propose a multi-stage Generative Adversarial Network (<inline-formula> <tex-math notation="LaTeX">$GAN$ </tex-math></inline-formula>) model to resolve existing issues of one-stage models. To do this, we apply a <i>coarse-to-fine</i> method to improve brain segmentation using a multi-stage <inline-formula> <tex-math notation="LaTeX">$GAN$ </tex-math></inline-formula>. In the first stage, our model generates a <i>coarse</i> outline for both the background and brain tissues. Then, in the second stage, the model generates a <i>refine</i> outline for the white matter (<inline-formula> <tex-math notation="LaTeX">$WM$ </tex-math></inline-formula>), gray matter (<inline-formula> <tex-math notation="LaTeX">$GM$ </tex-math></inline-formula>), and cerebrospinal fluid (<inline-formula> <tex-math notation="LaTeX">$CSF$ </tex-math></inline-formula>). We perform a fusion of the <i>coarse</i> and <i>refine</i> outlines to achieve high results. Despite using very limited data, we obtain an improved Dice Coefficient (DC) accuracy of up to 5&#x0025; compared to one-stage models. We conclude that our model is more efficient and accurate in practice for brain segmentation of both infants and adults. In addition, we observe that our multi-stage model is 2.69&#x2013;13.93 minutes faster than prior models. Moreover, our multi-stage model achieves higher performance with only a few-shot learning, in which only limited labeled data is available. Therefore, for medical images, our solution is applicable to a wide range of image segmentation applications for which convolution neural networks and one-stage methods have failed. This helps to advance the process of analyzing brain images, thus providing many advantages to the healthcare system, especially in critical health situations where urgent intervention is needed.

Towards collaborative appearance and semantic adaptation for medical image segmentation

This paper proposes a new unsupervised domain adaptation framework, named as Collaborative Appearance and Semantic Adaptation (CASA), for addressing the medical domain mismatch problem. Domain adaptation techniques have become one of the hot topics, especially when applying the established deep neural network into new domains in the medical analysis, i.e., semantic segmentation of medical lesions. To achieve unsupervised domain adaptation, our designed CASA framework could preserve synergistic fusion of adaptation knowledge from the perspectives of appearance and semantic. To be specific, we transform the appearance of medical lesions across domains via a Characterization Transfer Module (CTM), which can mitigate the appearance divergence of medical lesions across domains. Meanwhile, a Representation Transfer Module (RTM) is proposed via incorporating with a conditional generative adversarial network, which could transform features of source lesions to target-like feature, and further narrow the domain-wise distribution gap of underlying semantic knowledge. To the end, a challenging application of medical image segmentation is used to extensively validate the effectiveness of our proposed CASA framework. Various experiment results show its superior performance by a significant margin when comparing to the state-of-the-art domain adaptation methods.

Image Sketch Based Criminal Face Recognition Using Content Based Image Retrieval

Purpose: Face recognition is a geometric space recording activity that allows it to be used to distinguish the features of a face. Therefore, facial recognition can be used to identify ID cards, ATM card PINs, search for one’s committed crimes, terrorists, and other criminals whose faces were not caught by Close-Circuit Television (CCTV). Based on the face image database and by applying the Content-Base Image Retrieval method (CBIR), committed crimes can be recognized on his face. Moreover, the image segmentation technique was carried out before CBIR was applied. This work tried to recognize an individual who committed crimes based on his or her face by using sketch facial images as a query. Methods: We used an image sketch as a querybecause CCTV could not have caught the face image. The research used no less than 1,000 facial images were carried out, both normal as well asabnormal faces (with obstacles). Findings:Experiments demonstrated good enough in terms of precision and recall, which are 0,8 and 0,3 respectively, which is better than at least two previous works.The work demonstrates a precision of 80% which means retrieval of effectiveness is good enough. The 75 queries were carried out in this work to compute the precision and recall of image retrieval. Novelty: Most face recognition researchers using CBIR employed an image as a query. Furthermore, previous work still rarely applied image segmentation as well as CBIR.

Fast and Efficient Numerical Finite Difference Method for Multiphase Image Segmentation

We present a simple numerical solution algorithm for a gradient flow for the Modica–Mortola functional and numerically investigate its dynamics. The proposed numerical algorithm involves both the operator splitting and the explicit Euler methods. A time step formula is derived from the stability analysis, and the goodness of fit of transition width is tested. We perform various numerical experiments to investigate the property of the gradient flow equation, to verify the characteristics of our method in the image segmentation application, and to analyze the effect of parameters. In particular, we propose an initialization process based on target objects. Furthermore, we conduct comparison tests in order to check the performance of our proposed method.

Multi-density peaks clustering superpixel

A superpixel segmentation algorithm called multi-density peaks clustering (MDPC) is proposed. By selecting a sufficient number of local density maximum pixels from the image as cluster centers to depict the image texture, the boundary of the object can be captured very accurately. The algorithm framework of MDPC is divided into three steps. First, the local density of pixel is defined, and the local density maximum pixels are calculated. Then, the local density maximum pixels are used as cluster centers, and the global optimal search, which is based on the path-to-point idea, is used to complete the clustering of the remaining non-cluster center pixels to realize the initial segmentation. Finally, superpixels are obtained by merging the initial segments according to the size of the segments and the distance between adjacent segments. In quantitative comparisons, MDPC is compared with 13 state-of-the-art superpixel segmentation algorithms in three image segmentation datasets. The experimental results show that MDPC achieves better performance in terms of boundary recall, boundary precision, achievable segmentation accuracy, undersegmentation error, and explained variation. And the qualitative comparisons show that the proposed algorithm has obvious advantages over other superpixel segmentation algorithms in image detail description and boundary adherence. Finally, the practicability and stability of MDPC are further demonstrated by the application of image segmentation. The source code of MDPC will be available at https://github.com/zhaojianaaa.

Convolutional neural network with coarse-to-fine resolution fusion and residual learning structures for cross-modality image synthesis

Multi-modality MRI has been increasingly used for disease diagnosis and prognosis evaluation. However, the acquisitions of multi-modal images always face some practical difficulties such as the increased cost and patient discomfort. In this paper, we proposed an improved 3D UNet model for MRI modality synthesis and use the synthetic modalities to improve the performance of the following image analysis tasks such as tumor segmentation and tumor grading. We developed our model with three improvements on the basic 3D UNet model. First, we constructed a coarse-to-fine resolution fusion network to improve the ability of structural texture preservation. Second, we designed a convolutional fusion-based residual learning framework to learn mapping function, which leads to more detail preservation as well as less artifacts in the background. Third, for many-to-one synthesis, to combine the input multi-modalities more effectively, we introduced a new network module to fuse the UNet output feature maps of each modality. One private and two public datasets including a total of 493 cases were used for synthesis validation. Our proposed method surpasses the best existing method about 2.0 dB and 0.8 dB in PSNRs on the two datasets, respectively. Furthermore, two separate radiomics applications were used to demonstrate the value of our modality synthesis method. In the image segmentation application, integrating the modalities synthesized by our method has improved the segmentation Dice by 1.3%. In gliomas grading diagnosis application, integrating the synthesized modalities improved the diagnostic accuracy by 8.3%.

Mixup (Sample Pairing) Can Improve the Performance of Deep Segmentation Networks

Abstract Researchers address the generalization problem of deep image processing networks mainly through extensive use of data augmentation techniques such as random flips, rotations, and deformations. A data augmentation technique called mixup, which constructs virtual training samples from convex combinations of inputs, was recently proposed for deep classification networks. The algorithm contributed to increased performance on classification in a variety of datasets, but so far has not been evaluated for image segmentation tasks. In this paper, we tested whether the mixup algorithm can improve the generalization performance of deep segmentation networks for medical image data. We trained a standard U-net architecture to segment the prostate in 100 T2-weighted 3D magnetic resonance images from prostate cancer patients, and compared the results with and without mixup in terms of Dice similarity coefficient and mean surface distance from a reference segmentation made by an experienced radiologist. Our results suggest that mixup offers a statistically significant boost in performance compared to non-mixup training, leading to up to 1.9% increase in Dice and a 10.9% decrease in surface distance. The mixup algorithm may thus offer an important aid for medical image segmentation applications, which are typically limited by severe data scarcity.

Image Segmentation and the Projections of Graphic Centred Approaches in Medical Image Processing

Medical image segmentation is considered the most precarious element in the analysis and processing of real-life images in the clinical sector. Actually, segmentation effects affect the subsequent procedures of image evaluation, life object illustration and description, feature dimensions and the subsequent considerable task levels such as object categorization. In that case, medical image segmentation is the most essential and crucial aspect for aiding the visualization, delineation and depiction of regions of interest for any particular image. The aspect of physical segmentation of a picture is not just challenging and time-consuming task to do, but also problematic to assure accuracy considering the wide-range image modalities and unguided image quantities which have to be observed. In that case, it now becomes fundamental to evaluate the present approaches of image segmentation based on the application of computing algorithms which require the interaction of users with evaluating medical images. In the process of image segmentation, an anatomic classification requires to be extracted or defined to be projected effectively and independently. In that case, this contribution is focused on image segmentation to extract details for decision-making in the clinical sector. The paper presents generalized and relative techniques that have been categorized into three groups: pixel-centre, edge-centred and region-centred techniques. The paper also provides a highlight of the strengths and weaknesses of these techniques in reference to the appropriateness of a wide-range application in medical image segmentation.