Proposed Image Segmentation Method Research Articles

Cross-Modal Consistency for Single-Modal MR Image Segmentation.

Multi-modal magnetic resonance (MR) image segmentation is an important task in disease diagnosis and treatment, but it is usually difficult to obtain multiple modalities for a single patient in clinical applications. To address these issues, a cross-modal consistency framework is proposed for a single-modal MR image segmentation. To enable single-modal MR image segmentation in the inference stage, a weighted cross-entropy loss and a pixel-level feature consistency loss are proposed to train the target network with the guidance of the teacher network and the auxiliary network. To fuse dual-modal MR images in the training stage, the cross-modal consistency is measured according to Dice similarity entropy loss and Dice similarity contrastive loss, so as to maximize the prediction similarity of the teacher network and the auxiliary network. To reduce the difference in image contrast between different MR images for the same organs, a contrast alignment network is proposed to align input images with different contrasts to reference images with a good contrast. Comprehensive experiments have been performed on a publicly available prostate dataset and an in-house pancreas dataset to verify the effectiveness of the proposed method. Compared to state-of-the-art methods, the proposed method can achieve better segmentation. The proposed image segmentation method can fuse dual-modal MR images in the training stage and only need one-modal MR images in the inference stage. The proposed method can be used in routine clinical occasions when only single-modal MR image with variable contrast is available for a patient.

Fracture failure analysis of heavy-haul train couplers using convolutional neural network along with multilayer perceptron

Abstract Metal couplers are susceptible to unpredictable failure and fracture under long-term high-load conditions in heavy-haul railway transportation. The current mainstream manual inspection method has the disadvantages of high subjectivity and high a priori knowledge requirements, thus not meeting the rapid analysis requirements of production companies. Therefore, in this study, an automated failure analysis method is proposed for heavy-haul coupler fractures. First, a novel image segmentation method (PermuteNet) combining a visual multilayer perceptron and a convolutional neural network is designed to segment different failure patterns of fracture surfaces. The proposed method uses two newly proposed modules—permute attention module and context attention module—to improve the network’s ability to perceive weakly differentiated objects, thereby improving the recognition ability of the model for different failure patterns. In addition, a deep supervisory function is adopted to accelerate the convergence speed of the network. Finally, the proposed image segmentation method is deployed on a computer in conjunction with a developed client application to implement a single-click detection function for coupler fracture pattern analysis. Experiments are performed using the heavy-haul coupler fracture dataset established using on-site data; the proposed segmentation method achieves a mean intersection over union of 77.8%, which is considerably higher than that of other existing methods. By using the client software, the single-click detection function of the fracture area is realized. Thus, the proposed method provides a more convenient and accurate fracture identification solution for factory inspectors and has broad application prospects.

A Novel Fuzzy-Based Remote Sensing Image Segmentation Method.

Image segmentation is a well-known image processing task that consists of partitioning an image into homogeneous areas. It is applied to remotely sensed imagery for many problems such as land use classification and landscape changes. Recently, several hybrid remote sensing image segmentation techniques have been proposed that include metaheuristic approaches in order to increase the segmentation accuracy; however, the critical point of these approaches is the high computational complexity, which affects time and memory consumption. In order to overcome this criticality, we propose a fuzzy-based image segmentation framework implemented in a GIS-based platform for remotely sensed images; furthermore, the proposed model allows us to evaluate the reliability of the segmentation. The Fast Generalized Fuzzy c-means algorithm is implemented to segment images in order to detect local spatial relations between pixels and the Triple Center Relation validity index is used to find the optimal number of clusters. The framework elaborates the composite index to be analyzed starting by multiband remotely sensed images. For each cluster, a segmented image is obtained in which the pixel value represents, transformed into gray levels, the graph belonging to the cluster. A final thematic map is built in which the pixels are classified based on the assignment to the cluster to which they belong with the highest membership degree. In addition, the reliability of the classification is estimated by associating each class with the average of the membership degrees of the pixels assigned to it. The method was tested in the study area consisting of the south-western districts of the city of Naples (Italy) for the segmentation of composite indices maps determined by multiband remote sensing images. The segmentation results are consistent with the segmentations of the study area by morphological and urban characteristics, carried out by domain experts. The high computational speed of the proposed image segmentation method allows it to be applied to massive high-resolution remote sensing images.

An image segmentation method of pulverized coal for particle size analysis

An important index to evaluate the process efficiency of coal preparation is the mineral liberation degree of pulverized coal, which is greatly influenced by the particle size and shape distribution acquired by image segmentation. However, the agglomeration effect of fine powders and the edge effect of granular images caused by scanning electron microscopy greatly affect the precision of particle image segmentation. In this study, we propose a novel image segmentation method derived from mask regional convolutional neural network based on deep learning for recognizing fine coal powders. Firstly, an atrous convolution is introduced into our network to learn the image feature of multi-sized powders, which can reduce the missing segmentation of small-sized agglomerated particles. Then, a new mask loss function combing focal loss and dice coefficient is used to overcome the false segmentation caused by the edge effect. The final comparative experimental results show that our method achieves the best results of 94.43% and 91.44% on AP50 and AP75 respectively among the comparison algorithms. In addition, in order to provide an effective method for particle size analysis of coal particles, we study the particle size distribution of coal powders based on the proposed image segmentation method and obtain a good curve relationship between cumulative mass fraction and particle size.

Renal Pathology Images Segmentation Based on Improved Cuckoo Search with Diffusion Mechanism and Adaptive Beta-Hill Climbing.

Lupus Nephritis (LN) is a significant risk factor for morbidity and mortality in systemic lupus erythematosus, and nephropathology is still the gold standard for diagnosing LN. To assist pathologists in evaluating histopathological images of LN, a 2D Rényi entropy multi-threshold image segmentation method is proposed in this research to apply to LN images. This method is based on an improved Cuckoo Search (CS) algorithm that introduces a Diffusion Mechanism (DM) and an Adaptive β-Hill Climbing (AβHC) strategy called the DMCS algorithm. The DMCS algorithm is tested on 30 benchmark functions of the IEEE CEC2017 dataset. In addition, the DMCS-based multi-threshold image segmentation method is also used to segment renal pathological images. Experimental results show that adding these two strategies improves the DMCS algorithm's ability to find the optimal solution. According to the three image quality evaluation metrics: PSNR, FSIM, and SSIM, the proposed image segmentation method performs well in image segmentation experiments. Our research shows that the DMCS algorithm is a helpful image segmentation method for renal pathological images.

Multi-threshold image segmentation based on an improved differential evolution: Case study of thyroid papillary carcinoma

The scholarly world has demonstrated an immense enthusiasm for medical image segmentation due to its intricate nature and critical role in medical diagnosis and treatment systems. Multi-threshold image segmentation (MTIS) is a popular technique for this purpose, due to its simplicity and straightforwardness. This paper presents an improved Differential Evolution (DE) algorithm called AGDE, which is based on MTIS and was used to evaluate its high capability at IEEE CEC 2017. Comparisons with classical and advanced algorithms were conducted as part of the experiments. An AGDE-based multi-threshold image segmentation method utilizing a non-local mean 2D histogram in combination with Rényi's entropy was applied to segment images from the Berkeley Segmentation Datasets 500 (BSDS500) and microscopic images of thyroid papillary carcinoma (TPC). The experimental results showed that the proposed image segmentation method outperformed its competitors, making it a promising approach for medical image segmentation.

Feasibility of Automated Black Ice Segmentation in Various Climate Conditions Using Deep Learning

Black ice has recently been identified as a major cause of transportation accidents due to detecting difficulties on the road surface. It is crucial to provide traffic users with black ice warnings beforehand to sustain commuting safety. The identification of black ice, however, is a difficult initiative, since it necessitates the installation of sophisticated monitoring stations and demands frequently manual inspection. In order to build an economical automatic black ice detection technique, the datasets are built upon a variety of weather conditions, including clear, snowy, rainy, and foggy conditions, as well as two distinct forms of pavement: asphalt and concrete pavement. The Mask R-CNN model was performed to construct the black ice detection via image segmentation. The deep learning architecture was constructed based on pre-trained convolutional neural network models (ResNetV2) for black ice detection purposes. Different pretrained models and architecture (Yolov4) were then compared to determine which is superior for image segmentation of black ice. Afterward, through the retrieved bounding box data, the degree of danger area is determined based on the number of segmentation pixels. In general, the training results confirm the feasibility of the black ice detection method via the deep learning technique. Within “Clear” weather conditions, the detecting precision can be achieved up to 92.5%. The results also show that the increase in the number of weather types leads to a noticeable reduction in the training precision. Overall, the proposed image segmentation method is capable of real-time detection and can caution commuters of black ice in advance.

An Energy-Efficient Convolutional Neural Network Processor Architecture Based on a Systolic Array

Deep convolutional neural networks (CNNs) have shown strong abilities in the application of artificial intelligence. However, due to their extensive amount of computation, traditional processors have low energy efficiency when executing CNN algorithms, which is unacceptable for portable devices with limited hardware cost and battery capacity, so designing a CNN-specific processor is necessary. In this paper, we propose an energy-efficient CNN processor architecture for lightweight devices with a processing elements (PEs) array consisting of 384 PEs. Using the systolic array-based PE array, it realizes parallel operations between filter rows and between channels of output feature maps, supporting the acceleration of 3D convolution and fully connected computation with various parameters by configuring internal instruction registers. The computing strategy based on the proposed systolic dataflow achieves less hardware overhead compared with other strategies, and the reuse of image values and weight values, which effectively reduce the power of memory access. A memory system with a multi-level storage structure combined with register file (RF) and SRAM is used in the proposed CNN processor, which further reduces the energy overhead of computing. The proposed CNN processor architecture has been verified on a ZC706 FPGA platform using VGG-16 based on the proposed image segmentation method, the evaluation results indicate that the peak throughput achieves 115.2 GOP/s consuming 3.801 W at 150 MHz, energy efficiency and DSP efficiency reaches 30.32 GOP/s/W and 0.26 GOP/s/DSP, respectively.

Grayscale medical image segmentation method based on 2D&3D object detection with deep learning

BackgroundGrayscale medical image segmentation is the key step in clinical computer-aided diagnosis. Model-driven and data-driven image segmentation methods are widely used for their less computational complexity and more accurate feature extraction. However, model-driven methods like thresholding usually suffer from wrong segmentation and noises regions because different grayscale images have distinct intensity distribution property thus pre-processing is always demanded. While data-driven methods with deep learning like encoder-decoder networks always are always accompanied by complex architectures which require amounts of training data.MethodsCombining thresholding method and deep learning, this paper presents a novel method by using 2D&3D object detection technologies. First, interest regions contain segmented object are determined with fine-tuning 2D object detection network. Then, pixels in cropped images are turned as point cloud according to their positions and grayscale values. Finally, 3D object detection network is applied to obtain bounding boxes with target points and boxes’ bottoms and tops represent thresholding values for segmentation. After projecting to 2D images, these target points could composite the segmented object.ResultsThree groups of grayscale medical images are used to evaluate the proposed image segmentation method. We obtain the IoU (DSC) scores of 0.92 (0.96), 0.88 (0.94) and 0.94 (0.94) for segmentation accuracy on different datasets respectively. Also, compared with five state of the arts and clinically performed well models, our method achieves higher scores and better performance.ConclusionsThe prominent segmentation results demonstrate that the built method based on 2D&3D object detection with deep learning is workable and promising for segmentation task of grayscale medical images.

Interactive image segmentation based on the appearance model and orientation energy

Tang et al. (2013) proposed a graph-based image segmentation model by minimizing the distance between the object and background appearance overlap models. This model is very effective for interactive image segmentation. However, it is prone to isolated nodes when the colors or other appearances characteristic of the object and background are very similar. To improve the performance of this algorithm and related algorithms, we add new spatial distance and contour orientation energy terms to the energy function. Accordingly, we modify the construction of the energy graph. We add terminal nodes S and T and add prior constraints. Finally, we use the pseudoflow algorithm proposed by Hochbaum to calculate the maximum flow of the new energy graph. A large number of experiments on the MSRA dataset, BSD dataset and GrabCut dataset show that the results of the proposed method are better than those of many recently proposed image segmentation methods. The code is available at https://github.com/powerhope/AMOE.

Automatic clustering method to segment COVID-19 CT images.

Coronavirus pandemic (COVID-19) has infected more than ten million persons worldwide. Therefore, researchers are trying to address various aspects that may help in diagnosis this pneumonia. Image segmentation is a necessary pr-processing step that implemented in image analysis and classification applications. Therefore, in this study, our goal is to present an efficient image segmentation method for COVID-19 Computed Tomography (CT) images. The proposed image segmentation method depends on improving the density peaks clustering (DPC) using generalized extreme value (GEV) distribution. The DPC is faster than other clustering methods, and it provides more stable results. However, it is difficult to determine the optimal number of clustering centers automatically without visualization. So, GEV is used to determine the suitable threshold value to find the optimal number of clustering centers that lead to improving the segmentation process. The proposed model is applied for a set of twelve COVID-19 CT images. Also, it was compared with traditional k-means and DPC algorithms, and it has better performance using several measures, such as PSNR, SSIM, and Entropy.

Automatic Segmentation of Epidermis and Hair Follicles in Optical Coherence Tomography Images of Normal Skin by Convolutional Neural Networks.

Optical coherence tomography (OCT) is a well-established bedside imaging modality that allows analysis of skin structures in a non-invasive way. Automated OCT analysis of skin layers is of great relevance to study dermatological diseases. In this paper, an approach to detect the epidermal layer along with the follicular structures in healthy human OCT images is presented. To the best of the authors' knowledge, the approach presented in this paper is the only epidermis detection algorithm that segments the pilosebaceous unit, which is of importance in the progression of several skin disorders such as folliculitis, acne, lupus erythematosus, and basal cell carcinoma. The proposed approach is composed of two main stages. The first stage is a Convolutional Neural Network based on U-Net architecture. The second stage is a robust post-processing composed by a Savitzky-Golay filter and Fourier Domain Filtering to fully define the borders belonging to the hair follicles. After validation, an average Dice of 0.83 ± 0.06 and a thickness error of 10.25 μm is obtained on 270 human skin OCT images. Based on these results, the proposed method outperforms other state-of-the-art methods for epidermis segmentation. It demonstrates that the proposed image segmentation method successfully detects the epidermal region in a fully automatic way in addition to defining the follicular skin structures as main novelty.

Automatic Human Dendritic Cells Segmentation Using K-Means Clustering and Chan-Vese Active Contour Model

Background and objectiveNowadays, the number of pathologies related to food are multiplied. Mycotoxins are one of the most severe food contaminants that cause serious effects on the human health. Therefore, it is necessary to develop an assessment tool for evaluating their impact on the immune response. Recently, a new investigational method using human dendritic cells was endorsed by biologists. Nevertheless, analysis of the morphological features and the behavior of these cells remains merely visual. In addition, this manual analysis is difficult and time-consuming. Here, we focus mainly on automating the evaluation process by using advanced image processing technology. MethodsAn automatic segmentation approach of microscopic dendritic cell images is developed to provide a fast and objective evaluation. First, a combination of K-means clustering and mathematical morphology is used to detect dendritic cells. Second, a region-based Chan-Vese active contour model is used to segment the detected cells more precisely. Finally, dendritic cells are extracted by a filtering based on eccentricity measure. ResultsThe proposed scheme is tested on an actual dataset containing 421 microscopic dendritic cell images. The experimental results show high conformity between the results of the proposed scheme and ground-truth elaborated by biological expert. Moreover, a comparative study with other state-of-art segmentation schemes demonstrates the efficiency of the proposed method. It gives the highest average accuracy rate (99.42 %) compared to recent studied approaches. ConclusionsThe proposed image segmentation method for morphological analysis of dendrite inhibition can consistently be used as an assessment tool for biologists to facilitate the evaluation of serious health impacts of mycotoxins.

RETRACTED ARTICLE: Localization and segmentation of metal cracks using deep learning

Detection and quantification of defects from metal and metal-coated surfaces is one of the main challenges in computer vision-based semantic segmentation. Manual inspection is not a practically feasible solution for identifying defects such as surface-level cracks, scratches, and manufacturing mistakes, especially when we have to deal with large number of test subjects. The metal defects can be of different size, shape, and texture and often show close resemblance to the possible artefacts due to normal wear and tear and brush markings of metal coating. Hence it will be quite challenging to come up with an efficient segmentation method for quantifying such defects. In this work, we propose an automatic segmentation and quantification approach for inspecting defects from digital images of titanium-coated metal surfaces with a customized Deep learning architecture: UNet. The scheme uses a supervised learning approach with convolutional neural network (CNN) and can learn the suitable representations and features from the training data without any handcrafted features or human intervention. The proposed image segmentation method also uses appropriate pre-processing and post-processing stages. The input images are filtered using median filter for eliminating possible impulse noises, and the output mask generated from the CNN model is post-processed using suitable morphological operations for eliminating false detections. The detection and segmentation performance is evaluated using standard benchmarks, and the overall Dice score of the proposed model is 91.67% with a precision of 93.46%.

MRI Image Segmentation, Prediction and Diagnostic Accuracy: Deep Learning Framework and Machine Learning Techniques Analysis for Reducing The impact of Cardiac Diseases

Background: Usage of tele - monitoring system of electronic patient record (EHR) and magnetic reasoning is expected to increase rapidly in near future, yet numerous studies have examined cardiovascular risk prediction and statistic adoptive approach could improve clinical risk prediction. Objectives: To assess the performance outcomes of various techniques for predicting the risk of cardiovascular diseases and MRI image segmentation method on the basis of systematic review. Research Design: Retrospective Cardiovascular study. We associate UCI dataset, AHA dataset, real time patient datasets, hospital dataset and sunny broken dataset from 2017 to 2019, and predicted risk using the logistic regression, stochastic gradient boosted, random forest, SVM, ROC Curve, KNN algorithm, MXNET UNET. Measures: The proposed methods have been developed in four categories to accurately diagnose cardiovascular diseases. We assessed to analyze and compared the accuracy of four different machine learning algorithms with the ROC for assessing and diagnosing cardiovascular disease from UCI cardiac datasets. The research will then focus on to predict heart diseases automatically by segmenting and classifying the patients’ heart data in real- time with the help of machine learning algorithms, big data, wireless heart monitor and smart phones. We further improve the prediction accuracy by using logistic regression and ROC Curve to improve the prediction performance. Consequently, K- Nearest-Neighbor (KNN) method, R programming language and big data where applied to easily find the nearest hospitals, monitor and provide on-time visualization to the medical professionals. Finally, we propose automatic myocardial segmentation method for cardiac MRI on the basis of Deep Convolutional neural network. Results: Logistic Regression methods outperformed the standard accuracy rate even with application of ROC curve (AUC increased from 87% to 91%). Ever better performance was achieved in Models using additional Real time dataset attributes (AUC increased to 93% and KNN achieved approximately 83%). Proposed image segmentation method results tended using following techniques, Jaccard (0.6 ± 0.1 mean accuracy Dice’s value) outplays the dices co efficient (0.58 ± 0.1 mean accuracy Dice’s value) CCN reaches the value of the 0.9 (Table 7) and for the dice’s co-efficient respectively that can be compared to manual segmentation. The accuracy tended to decline while PM (Papillary muscles) we got 0.89 for the dice’s coefficient and mean squared error 0.01. Conclusions: The tele - monitoring system plays the important role for cardiovascular patients and the healthcare industry. Moreover, cardiac image classification demands a high level of expertise and significant time consumption on the part of the operator. Multicenter sufficiently powered and randomized controlled trials are needed to assess the potential benefits and cost-effectiveness of this intervention. Subsequently, our findings of image classification method will facilitate more advanced discovery.

A Spectral Structural Approach for Building Extraction from Satellite Imageries

Automatic feature extraction from high resolution satellite imagery remains an open research area in the field of remote sensing, computer vision and machine learning. While many algorithms have been proposed for automatic building extraction, none of them solve the problem completely. This paper proposes a system for increasing the degree of automation in extraction of building features from high resolution multispectral satellite images. Image segmentation is a prerequisite for processing of very high spatial resolution imageries. Most image segmentation methods use spectral information of an image alone for generating image objects. A novel image segmentation method for very high spatial resolution multispectral images using combined spectral and structural information is proposed in this paper. The method involves computation of textural parameters from high resolution multispectral imagery and is combined with the spectral bands for extracting spectral-structural characteristics. Hence in addition to the spectral information, the tone, texture and shape information is evaluated for an object-oriented analysis. The support vector machines classification rules are applied on the generated object primitives. The proposed image segmentation method is well applicable to the segmentation of imagery over urban and suburban areas for large scale building extraction.

Efficient paddy field mapping using Landsat-8 imagery and object-based image analysis based on advanced fractel net evolution approach

This paper proposes an efficient paddy field mapping method using object-based image analysis and a bitemporal data set acquired by Landsat-8 Operational Land Imager. In the proposed approach, image segmentation is the first step and its quality has a serious impact on the accuracy of paddy field classification. In order to improve segmentation quality, a new segmentation algorithm based on a frequently used method, fractal net evolution approach, is developed, with improvement mainly in merging criteria. In order to automate the process of scale parameter determination, an unsupervised scale selection method is utilized to determine the optimal scale parameter for the proposed image segmentation approach. After segmentation, four types of object-based features including geometric, spectral, textural, and contextual information are extracted and input into the subsequent classification procedure. By using a random forest classifier, paddy fields and nonpaddy fields are separated. The proposed image segmentation method and the final classification result are both quantitatively evaluated. Our segmentation method outperformed two popular algorithms according to three supervised evaluation criteria. The classification result with overall accuracy of 91.00% and kappa statistic of 0.82 validated the effectiveness of the proposed framework. Further analysis on feature importance indicated that spectral features made the most contribution as compared to the other three types of object-based features.

A new segmentation method for very high resolution imagery using spectral and morphological information

Image segmentation is a key and prerequisite step for object-based analysis of very high resolution (VHR) imagery. Most existing image segmentation methods use either spectral or spatial information of an image alone. A novel image segmentation method for VHR multispectral images using combined spectral and morphological information is proposed in this paper. The method can be summarized as follows. First, a morphological derivative profile is calculated from an original multispectral image and combined with the spectral bands to quantify spectral-morphological characteristics of a pixel, which are considered as a criterion of homogeneity of neighboring pixels. Image segmentation is then conducted using a seeded region-growing procedure, which is based on the seed points automatically generated from the gradient image and dynamically added and the similarity between a seed pixel and its neighboring pixels in terms of spectral-morphological characteristics. The obtained segmentation result is further refined by a region merging procedure to generate a final segmentation result. The proposed method is evaluated using three VHR images of urban and suburban areas and compared with two existing segmentation methods, in terms of visual inspection, quantitative evaluation and indirect evaluation. Experimental results demonstrate that the joint use of spectral and morphological information outperformed the use of morphological information alone. Furthermore, the proposed image segmentation method performed better than existing methods. The proposed image segmentation method is well applicable to the segmentation of VHR imagery over urban and suburban areas.

English

2 ABSTRACT: Fingerprint image segmentation is part of pre-processing in fingerprint image recognition system. It has a critical effect to the fingerprint image recognition system. Regardless of years of research in the area of general purpose image segmentation, it is still a very challenging task. A new image decomposition scheme, called the Adaptive and Orientation algorithm, is proposed to achieve effective segmentation for fingerprint images in this work. The proposed model is inspired by total variation models, but it differentiates itself by integrating two unique features of fingerprints; namely, scale and orientation. The proposed Adaptive and Orientation algorithm decomposes a fingerprint image into two layers: cartoon and texture. The cartoon layer contains unwanted components (e.g. structured noise) while the texture layer mainly consists of the latent fingerprint. Proposed segmentation algorithm is experimented and analyzed for two different fingerprint images. The PSNR for image segmentation has been used as a comparison parameter for proposed image segmentation methods.

A Region-based Image Segmentation Method Under P Systems

Due to the reason of iterative calculation, there are some drawbacks for existing image segmentation methods based on region growing, such as large computation cost and low real-timing. Membrane computing is a novel class of computing models inspired by the structure and function of living cells, also known as P systems, which have the advantage of distributed and parallel computing. In order to overcome the drawbacks of existing image segmentation methods based on region growing, a regionbased image segmentation method based on P systems is proposed in this paper. A tissue-like P system designed specially applies evolution rules and communication rules to achieve an adaptive region growing for image segmentation. The proposed image segmentation method based on tissue-like P systems is evaluated in several standard gray-scale images and compared with the traditional image segmentation method based on region growing.