Analysis of Various Image Segmentation Techniques on Retinal Oct Images

Clustering-based segmentation algorithm is one of the common methods in image segmentation. However, how to avoid the influence of the initialization and the singular value is a problem we have to face. For overcoming this problem, we proposed a new image segmentation technology which is based on the AIC criterion and not affected by the singular values. The simulation results show that the method has good performance on stability and accuracy. Image segmentation is the key step in image analysis of computer vision and image processing field. It has been widely applied in various areas such as in the process of automating production, sensing images and biomedical images. The main goal of image segmentation is to simplify an image into segments that have a strong correlation with objects in the real world. The existing segmentation algorithm can be generally divided into three classes: edge detection, region- based segmentation and data clustering. Edge detection method relies on the edges of the object with background and the other objects. For the images with noise, it is difficult to separate the boundary and the target background (1). Region- based segmentation method segments an image into several meaningful sub-domains that are non-overlapping and same- nature. But it may lead to the over-segmentation, and has to combine with other methods to use (2). Data clustering method is based on the whole image and considers the distance between each data. Advantages of data clustering method are low complexity and easy to implement. Disadvantages are sensitive to the noise and selection of the initial centroids (3). Data clustering is one of the common techniques in image segmentation. Its purpose is to cluster pixels into several parts (regions) according to the feature of image. Based on the properties of clustering algorithm, researchers have proposed various image segmentation algorithm, such as based on hierarchical clustering, based on K-means clustering, based on fuzzy clustering, based on mean shift, and so on (3-5). Clustering analysis is an unsupervised process of partitioning a data set into subsets of similar data objects. The elementary principle is as far as possible to increase the difference between categories and reduce the difference within the category. In the process of image segmentation based on data clustering, thus the objective is that the similar pixels are divided into the same regions and the non-similar pixels are divided into different regions. However, Two difficulties we must face are that how to determine the cluster centers and avoid influence of noise. In this paper, a new image segmentation algorithm is proposed based on the AIC criterion. The new segmentation technology can achieve an ideal performance and not affected by the initialization of centroids and the singular values. The simulation results verify the efficiency of proposed algorithm.

Drusen is considered as the landmark for diagnosis of AMD and important risk factor for the development of AMD. Therefore, accurate segmentation of drusen in retinal OCT images is crucial for early diagnosis of AMD. However, drusen segmentation in retinal OCT images is still very challenging due to the large variations in size and shape of drusen, blurred boundaries, and speckle noise interference. Moreover, the lack of OCT dataset with pixel-level annotation is also a vital factor hindering the improvement of drusen segmentation accuracy. To solve these problems, a novel multi-scale transformer global attention network (MsTGANet) is proposed for drusen segmentation in retinal OCT images. In MsTGANet, which is based on U-Shape architecture, a novel multi-scale transformer non-local (MsTNL) module is designed and inserted into the top of encoder path, aiming at capturing multi-scale non-local features with long-range dependencies from different layers of encoder. Meanwhile, a novel multi-semantic global channel and spatial joint attention module (MsGCS) between encoder and decoder is proposed to guide the model to fuse different semantic features, thereby improving the model's ability to learn multi-semantic global contextual information. Furthermore, to alleviate the shortage of labeled data, we propose a novel semi-supervised version of MsTGANet (Semi-MsTGANet) based on pseudo-labeled data augmentation strategy, which can leverage a large amount of unlabeled data to further improve the segmentation performance. Finally, comprehensive experiments are conducted to evaluate the performance of the proposed MsTGANet and Semi-MsTGANet. The experimental results show that our proposed methods achieve better segmentation accuracy than other state-of-the-art CNN-based methods.

Optical pressure sensors based plantar image segmenting using an improved fully convolutional network

Prior research studies have shown that the peak signal to noise ratio (PSNR) is the most frequent watermarked image quality metric that is used for determining the levels of strength and weakness of watermarking algorithms. Conversely, normalised cross correlation (NCC) is the most common metric used after attacks were applied to a watermarked image to verify the strength of the algorithm used. Many researchers have used these approaches to evaluate their algorithms. These strategies have been used for a long time, however, which unfortunately limits the value of PSNR and NCC in reflecting the strength and weakness of the watermarking algorithms. This paper considers this issue to determine the threshold values of these two parameters in reflecting the amount of strength and weakness of the watermarking algorithms. We used our novel watermarking technique for embedding four watermarks in intermediate significant bits (ISB) of six image files one-by-one through replacing the image pixels with new pixels and, at the same time, keeping the new pixels very close to the original pixels. This approach gains an improved robustness based on the PSNR and NCC values that were gathered. A neural network model was built that uses the image quality metrics (PSNR and NCC) values obtained from the watermarking of six grey-scale images that use ISB as the desired output and that are trained for each watermarked image’s PSNR and NCC. The neural network predicts the watermarked image’s PSNR together with NCC after the attacks when a portion of the output of the same or different types of image quality metrics (PSNR and NCC) are obtained. The results indicate that the NCC metric fluctuates before the PSNR values deteriorate.

In day-to-day life, new technologies are emerging in the field of Image processing, especially in the domain of segmentation. Image segmentation is the most important part in digital image processing. Segmentation is nothing but a portion of any image and object. In image segmentation, the digital image is divided into multiple set of pixels. Image segmentation is generally required to cut out region of interest (ROI) from an image. Currently there are many different algorithms available for image segmentation. This chapter presents a brief outline of some of the most common segmentation techniques (e.g. Segmentation based on thresholding, Model based segmentation, Segmentation based on edge detection, Segmentation based on clustering, etc.,) mentioning its advantages as well as the drawbacks. The Matlab simulated results of different available image segmentation techniques are also given for better understanding of image segmentation. Simply, different image segmentation algorithms with their prospects are reviewed in this chapter to reduce the time of literature survey of the future researchers.

Image recognition and image processing usually contain the technique of image segmentation. Excellent segmentation results can directly affect the accuracy of image recognition and processing. The essence of image segmentation is to segment each frame of a certain image or a video into multiple specific objects or regions and represent them with different labels. This paper focuses on the segmentation results obtained in image segmentation of images used for intelligent monitoring of Mandarin exams are usually visualized for image analysis. In this paper, we first investigate the performance improvement techniques for semantic segmentation in the image segmentation task for intelligent monitoring of Mandarin exams, improve the pixel classification capability by performing semantic migration, and, for the first time, extend the dataset substantially by style transformation to improve the model’s recognition of advanced features. In addition, to further address the shortcomings of the dataset, this paper improves the performance of image segmentation using synthetic datasets by investigating synthetic dataset image segmentation improvement techniques that reduce the reliance on manually annotated datasets. Image segmentation techniques continue to advance, and there are even thousands of commonly used segmentation methods for image segmentation development to date. Among them, they can be broadly classified as region-based segmentation methods, threshold-based segmentation methods, edge-based segmentation methods, specific theory-based segmentation methods, and deep learning-based segmentation methods. However, the methods used in this paper have all been experimentally demonstrated to improve the effectiveness of the techniques and proved to outperform other existing methods in the same field in the publicly available datasets LSUN, Cityscapes, and GTA5 datasets, respectively.

The research that used digital image processing to detect glaucoma has been known as one of the popular methods. The beginning step of the research is to choose the best channel among red, green, or blue (RGB) so it can ease the glaucoma segmentation. In choosing the channel, it is important to analyze deeply the used retinal images. Choosing of best component can affect the accuracy of glaucoma diagnosis results. In this research, the most suitable component will be analyzed to detect glaucoma based on the visual, MSE (Mean Square Error) value, and PSNR (Peak Signal to Noise Ratio). In this research, we used 85 images of glaucoma from the DRISTHI-GS database and 101 normal images from the RIM-ONE database. From the visualization, it showed that the red component had high brightness level so it can differ the optic disc and other parts of retinal eyes. The green component still has vessel blood so it will make it more difficult to segment the images. Blue component results in very dark of retinal image. From MSE and PNSR values, it showed that the green component had the smallest MSE value while the blue component has the biggest MSE value. PSNR value was obtained from the green component. Both red and blue components had PSNR value which had a small difference. From these results, it can be concluded that the MSE and PSNR values do not guarantee visual results. So that for further research, it is expected that the MSE and PSNR values will be obtained from the part that we want to observe

Registration of longitudinal optical coherence tomography (OCT) images assists disease monitoring and is essential in image fusion applications. Mouse retinal OCT images are often collected for longitudinal study of eye disease models such as uveitis, but their quality is often poor compared with human imaging. This paper presents a novel but efficient framework involving an optimal transport based graph matching (OT-GM) method for 3D mouse OCT image registration. We first perform registration of fundus-like images obtained by projecting all b-scans of a volume on a plane orthogonal to them, hereafter referred to as the x-y plane. We introduce Adaptive Weighted Vessel Graph Descriptors (AWVGD) and 3D Cube Descriptors (CD) to identify the correspondence between nodes of graphs extracted from segmented vessels within the OCT projection images. The AWVGD comprises scaling, translation and rotation, which are computationally efficient, whereas CD exploits 3D spatial and frequency domain information. The OT-GM method subsequently performs the correct alignment in the x-y plane. Finally, registration along the direction orthogonal to the x-y plane (the z-direction) is guided by the segmentation of two important anatomical features peculiar to mouse b-scans, the Internal Limiting Membrane (ILM) and the hyaloid remnant (HR). Both subjective and objective evaluation results demonstrate that our framework outperforms other well-established methods on mouse OCT images within a reasonable execution time.

Recently, image thresholding methods based on various entropy functions have been found popularity. Nonetheless, entropic-based methods depend on the spatial distribution of the grey level values in an image. Hence, the accuracy of these methods is limited due to the non-uniform distribution of the grey values. Further, the analysis of the COVID-19 X-ray images is evolved as an important area of research. Therefore, it is needed to develop an efficient method for the segmentation of the COVID-19 X-ray images. To address these issues, an efficient non-entropy-based thresholding method is suggested. A novel fitness function in terms of the segmentation score (SS) is introduced, which is used to reduce the segmentation error. A soft computing approach is suggested. An efficient optimizer using the chance-based birds’ intelligence is introduced to maximize the fitness values. The new optimizer is validated utilizing the benchmark test functions. The statistical parameters reveal that the suggested optimizer is efficient. It shows a quite significant improvement over its counterparts—optimization based on seagull/cuckoo birds. Precisely, the paper includes three novel contributions—(i) fitness function, (ii) chance-based birds’ intelligence for optimization, (iii) multiclass segmentation. The COVID-19 X-ray images are taken from the Kaggle Radiography database, to the experiment. Its results are compared with three different state-of-the-art entropy-based techniques—Tsallis, Kapur’s, and Masi. For providing a statistical analysis, Friedman’s mean rank test is conducted and our method Ranked one. Its superiority is claimed in terms of Peak Signal to Noise Ratio (PSNR), Feature Similarity Index (FSIM) and Structure Similarity Index (SSIM). On the whole, an improvement of about 11% in PSNR values is achieved using the proposed method. This method would be helpful for medical image analysis.

Data compression is important to reduce the transmission delays and to ensure efficient utilization of bandwidth and storage space. As images constitute a major part of the data being stored and communicated, image compression is of great importance. However, compression should not degrade the quality of the image to an unacceptable level. This paper presents a high fidelity image compression algorithm which scans the image in the form of 3*3 overlapping blocks, and compresses the image by extracting the information about the centre pixel and the pixels surrounding the centre pixel within the blocks. Decompression uses an iterative approach to reconstruct the image from the centre pixels and their neighbors. The proposed algorithm offers high quality at lower Peak Signal to Noise Ratio (PSNR) values. Also, a new quality metric is proposed and is used to compare the results with JPEG lossy approach. Results reveal that the quality of the decompressed image obtained by the proposed algorithm is better than that of JPEG lossy algorithm at same PSNR values.

Images consume more space when stored and use a lot of bandwidth during transmission. Hence, an image compression reduces storage space required, and time to transmit an image by making effective usage of bandwidth. In this paper, a simple image compression method using an index-based approach is proposed. This approach makes use of simple indices of an array to compress images. The context of nearby fifteen pixels is used, and the index for the current pixel is found. The indices are found for every pixel of an image. These indices are transformed and written into a transformed file. This transformed file is further compressed with Huffman compression to achieve a compressed file. Decompression uses a simple methodology to reconstruct the image. The pixel value is reconstructed using the index, and from previously reconstructed pixels of the image. The proposed algorithm provides high fidelity images at lower Peak Signal to Noise Ratio (PSNR). The results obtained from the proposed algorithm are compared with JPEG algorithm. At the same PSNR values, the quality of the reconstructed images by the proposed algorithm is comparable to that of the JPEG algorithm.

In this ascension era of technology, Magnetic resonance imaging (MRI) emerges as the utmost clinically acceptable imaging modality for detection and diagnosis of tumors. The Breast tumor is leading scrupulous diseases among women. In last two decades, image segmentation has got a high boost and attention from the researchers across the globe. To represent the image in such a way which is easy to analyze and more meaningful, the process of segmentation is used. It is the primal step in processing images of different types. Therefore, the image is sectioned into desirable building blocks. Basically, it provides the meaningful objects of the image. Literature provides a variety of image segmentation algorithms even though there is a requirement of an efficient segmentation technique which can work efficiently on all sorts of images. The key extract of an algorithm lies within the superiority of segmentation performed by a particular method. The availability of segmentation algorithms is quite large, so the analysis of these algorithms might be interesting to the researchers. This paper reviews segmentation techniques such as theory-based, region-based, thresholding, edge-based, Neural Network-based, Model-based, and Partial differential equation based on the basis of their functioning, utility, advantages, disadvantages, and applications.

In this study, a bias field correction workflow was proposed to improve the flexibility and generalizability of the generative adversarial network (GAN) model for abdominal cancer patients treated with a 0.35T magnetic resonance imaging linear accelerator (MR-LINAC) system. Model training was performed using brain MR images acquired on a 3T diagnostic scanner, while model testing was performed using abdominal MR images obtained using a 0.35T MR-LINAC system. The performance of the proposed workflow was first compared with the GAN model using root-mean-square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). To assess the impact of the workflow on image segmentation, it was also compared with the N4ITK algorithm. Segmentation was performed using the k-means clustering algorithm with three clusters corresponding to air, fat, and soft tissue. Segmentation accuracy was then evaluated using the Dice similarity coefficient (DSC). The RMSE values were 30.59, 12.06, 10.37 for the bias field-corrupted images (IIN), GAN-corrected images (IGAN), and images corrected with the proposed workflow (IOUT), respectively. Corresponding PSNR values were 42.34, 46.04, 47.04 dB, and SSIM values were 0.84, 0.96, 0.98. For segmentation accuracy, the mean DSC for air masks was 0.95, 0.97, and 0.97; for fat masks, 0.61, 0.71, and 0.74; and for soft tissue masks, 0.60, 0.68, and 0.69, corresponding to IIN, N4ITK-corrected images (IN4ITK), and IOUT, respectively CONCLUSION: By effectively mitigating bias field artifacts, the proposed workflow has the potential to strengthen the clinical utility of MRI-guided adaptive radiotherapy for abdominal cancers, ensuring safer and more accurate radiation delivery.

This research paper presents an efficient hybrid framework for the enhancement of X‐ray images using the DWT (discrete wavelet transform), Gaussian, and Wiener filters. Digital X‐ray images perform an important role in detecting explosives or illegal items. However, lately used X‐ray images have certain shortcomings like noise, blurriness, and low contrast. Noise affects the object’s edges and values of intensity of pixels which gives rise to ambiguity for the system to separate objects and also hampers the decision‐making process. To overcome these issues, a new hybrid framework is proposed here that consists of two layers. First, it reads high‐ and low‐energy X‐ray images and fuses them through various fusion rules in the wavelet realm using DWT and is reconstructed using iDWT (inverse discrete wavelet transform). Subsequently, the Gaussian filter is applied to the fused image to remove the Gaussian noise, and finally, the Wiener filter is used to reduce blurriness and improve image quality. The quality of the image is measured using PSNR (peak signal‐to‐noise ratio) and MSE (mean squared error) values, which exhibits that an average of the MSE values of fused images is 40% lower, and the PSNR values are 10% higher than the single images. Experimental results show that this hybrid framework successfully reduced noise and blurriness and enhanced contrast and accuracy.

Image segmentation is the fundamental step to analyze images and extract data from them. This paper concentrates on the idea behind the basic methods used. Image segmentation is the process of partitioning a digital image into multiple segments(i. e. sets of pixels). The goal of segmentation is to simplify or change the representation of an image into something that is more meaningful and easier to analyze. Segmentation is typically used to locate objects and boundaries(line, curve) in image. The Image segmentation is a set of segments that collectively cover the entire image. Each of pixels in a region are similar with respect to some characteristics colour, intensity or texture. The various segmentation techniques discussed in this paper.