Medical Image Clustering Algorithm Based on Graph Model

Medical images owing to blurriness, unsharp edges, unclear boundaries make the detection and diagnosis of abnormalities a cumbersome task. Crisp set theory sometimes fails in processing medical images owing to uncertainty in computer vision system and human understanding along with imprecise grey pixel values. It is imperative to get accurate results for a wrong decision in analyzing images may cost a person’s life. Fuzzy techniques are exploited to deal with this vagueness as it follows fuzzification, membership modification, and defuzzification to get accurate results. In some cases where uncertainty increases or dissimilar kind of uncertainties are required, fuzzy techniques are not capable to give good results. So, advanced fuzzy sets like intuitionistic fuzzy sets and type II fuzzy sets are used to get better results with increased accuracy. Intuitionistic fuzzy sets use hesitation function while type II fuzzy sets utilize fuzzy membership function to deal with more uncertainties. This paper reviews the current applications of advanced fuzzy set in pre-processing, segmentation, and clustering and edge detection of medical images.

This paper presents a new technique for incorporating local membership information into the standard fuzzy C-means (FCM) clustering algorithm. In this technique, the objective consists of minimizing the classical FCM function with a unity fuzzifier exponent plus the Kullback-Leibler (KL) information distance acting as a fuzzification and regularization term. The KL distance is proposed to measure the proximity between cluster membership function of a pixel and an average of the cluster membership functions of immediate neighborhood pixels. Therefore, minimizing this KL distance biases the cluster membership of the pixel toward this smoothed membership function of the local neighborhoods. This can provide immunity against noise and results in clustered images with piecewise homogeneous regions. Results of clustering and segmentation of synthetic and real-world medical images are presented to compare the performance of the proposed local membership KL information based FCM (LMKLFCM) and the standard FCM, a local data information based FCM (LDFCM) and a type of local membership information based FCM (LMFCM) algorithms.

We propose a soft-constrained clustering method for group-based labeling of medical images. Since the idea of group-based labeling is to attach the label to a group of samples at once, we need to have groups (i.e., clusters) with high purity. The proposed method is formulated to achieve high purity even for difficult clustering tasks such as medical image clustering, where image samples of the same class are often very distant in their feature space. In fact, those images degrade the performance of conventional constrained clustering methods. Experiments with an endoscopy image dataset demonstrated that our method outperformed various state-of-the-art methods.

Many environmental and genetic conditions may modify jaws growth. In orthodontics, the right treatment timing is crucial. This timing is a function of the Cervical Vertebra Maturation (CVM) degree. Thus, determining the CVM is important. In orthodontics, the lateral X-ray radiography is used to determine it. Many classical methods need knowledge and time to look and identify some features to do it. Nowadays, Machine Learning (ML) and Artificial Intelligent (AI) tools are used for many medical and biological image processing, clustering and classification. This paper reports on the development of a Deep Learning (DL) method to determine directly from the images the degree of maturation of CVM classified in six degrees. Using 300 such images for training and 200 for evaluating and 100 for testing, we could obtain a 90% accuracy. The proposed model and method are validated by cross validation. The implemented software is ready for use by orthodontists.

Deep learning has achieved great success in the field of computer vision, and the precision in image classification and image detection has surpassed humans. Therefore, this paper combines deep learning and medical image segmentation, focusing on how to improve the accuracy and speed of segmentation algorithm of medical exercise rehabilitation image. Aiming at the shortcomings of traditional medical image recognition methods, a medical exercise rehabilitation image segmentation algorithm based on hierarchical features of convolutional neural networks is proposed, this paper calls it as hierarchical features of convolutional neural networks (HFCNN). The algorithm firstly samples the convolution output of multiple layers in the convolutional neural network to a unified scale and combines them to construct a hierarchical feature. This hierarchical feature combines the structural information of objects contained in the shallow layer of the network with the semantic information of objects contained in the deep layers of the network, so it has a strong ability to express. Secondly, the image can be segmented into multiple super pixels by the super pixel segmentation algorithm. The classifier is trained using the hierarchical features of the super pixel, and then the classification result is mapped back to the pixel. Finally, a fully connected conditional random field algorithm including one-potential potential energy and paired potential energy is constructed. The corresponding energy function is used to smooth the classification result of the pixel, and the regional consistency and continuity of the pixel mark are improved. Compared with many classical convolutional neural network algorithms, this algorithm not only accelerates the network convergence speed, shortens the training time, but also significantly improves the accuracy of segmentation algorithm of medical exercise rehabilitation image, showing good practical value.

We consider the problem of image representation and clustering. Traditionally, an n1 x n2 image is represented by a vector in the Euclidean space R n1 x n2. Some learning algorithms are then applied to these vectors in such a high dimensional space for dimensionality reduction, classification, and clustering. However, an image is intrinsically a matrix, or the second order tensor. The vector representation of the images ignores the spatial relationships between the pixels in an image. In this paper, we introduce a tensor framework for image analysis. We represent the images as points in the tensor space Rn1 mathcal Rn2 which is a tensor product of two vector spaces. Based on the tensor representation, we propose a novel image representation and clustering algorithm which explicitly considers the manifold structure of the tensor space. By preserving the local structure of the data manifold, we can obtain a tensor subspace which is optimal for data representation in the sense of local isometry. We call it TensorImage approach. Traditional clustering algorithm such as k-means is then applied in the tensor subspace. Our algorithm shares many of the data representation and clustering properties of other techniques such as Locality Preserving Projections, Laplacian Eigenmaps, and spectral clustering, yet our algorithm is much more computationally efficient. Experimental results show the efficiency and effectiveness of our algorithm.

TWave: High-order analysis of functional MRI

Recently, diagnosing diseases using medical images became crucial. As these images are transmitted through the network, they need a high level of protection. If the data in these images are liable for unauthorized usage, this may lead to severe problems. There are different methods for securing images. One of the most efficient techniques for securing medical images is encryption. Confusion and diffusion are the two main steps used in encryption algorithms. This paper presents a new encryption algorithm for encrypting both grey and color medical images. A new image splitting technique based on image blocks introduced. Then, the image blocks scrambled using a zigzag pattern, rotation, and random permutation. Then, a chaotic logistic map generates a key to diffuse the scrambled image. The efficiency of our proposed method in encrypting medical images is evaluated using security analysis and time complexity. The security is tested in entropy, histogram differential attacks, correlation coefficient, PSNR, keyspace, and sensitivity. The achieved results show a high-performance security level reached by successful encryption of both grey and color medical images. A comparison with various encryption methods is performed. The proposed encryption algorithm outperformed the recent existing encryption methods in encrypting medical images.

Medical image copyright protection is becoming increasingly relevant as medical images are used more frequently in medical networks and institutions. The traditional embedded watermarking system is inappropriate for medical images since it degrades the original images’ quality. Furthermore, medical-colored image watermarking options are constrained since most medical watermarking systems are built for gray-scale images. This paper proposes a zero-watermarking scheme for medical color image copyright protection based on a chaotic system and Resnet50, which is a convolutional neural network method. The network Resnet50 is used to extract features from the color medical image, and then a logistic Gaussian map is used to scramble these features and scramble the binary image. Finally, an exclusive OR operation is performed (scrambled binary image, scrambled features for the medical color image) to form a zero watermarking. The experimental result proves that our scheme is effective and robust to geometric and common image processing attacks. The BER values of the extracted watermarks are below 0.0039, and the NCC values are above 0.9942, while the average PSNR values of the attacked images are 29.0056 dB. Also, it is superior to other zero-watermark schemes for medical images in terms of robustness to conventional image processing and geometric attacks. Furthermore, the experimental results show that the Resnet50 model outperforms other models in terms of reducing the mean squared errors of the features between the attacked and original image.

In the information age, network security has gradually become a potentially huge problem, especially in the medical field, it is essential to ensure the accuracy and safety of images, and patient information needs to be included with minimal change. Combined log-polar transform (LPT) and discrete cosine transform (DCT), a novel robust watermarking algorithm for medical images, is proposed. It realized the lossless embedding of patient information into medical images. In the process of feature extraction and watermark embedding, the proposed algorithm reflects the characteristics of LPT, scale invariance and rotation invariance, and retains the advantages of DCT's ability to resist conventional attacks and robustness. As it adopts zero-watermarking embedding technology, it solves the defects caused by the traditional watermark embedding technology to modify the original image data and guaranteed the quality of medical images. The good experimental results show the effectiveness of this algorithm.

Magnetic Resonance Imaging (MRI) provides a non-invasive manner to aid clinical diagnosis, while its limitation is the slow scanning speed. Recently, due to the high costs of health care and taking account of patient comfort, some methods such as Parallel MRI (pMRI) and compressed sensing MRI have been developed to reduce the MR scanning duration under the sampling process. It is almost unavoidable to accept some doses of X-rays in computed tomography (CT scans). If one could find a more efficient way to represent the required visual information, the tasks of image processing and medical imaging would become easier and less troublesome. In this paper, first, we used pMRI on complex double data of brain magnetic resonance image. pMRI significantly reduces the number of measurements in the Fourier domain because each coil only acquires a small fraction of the whole measurements. It is important to reconstruct the original MR image efficiently and precisely for better diagnosis. In this research, we proposed a new super resolution and deblurring algorithm with dictionary learning, based on assuming a local Sparse-Land model on image patches, serving as regularization, then we validated the proposed method by using another one called the adaptive selection of sub dictionaries- adaptive reweighted sparsity regularization. Visual comparison and significant difference in psnr calculation (0.8111db) and time complexity showed that the proposed method had much better results.

We propose a novel approach to investigate and implement unsupervised image content understanding and segmentation of color industrial images like medical imaging, forensic imaging, security and surveillance imaging, biotechnical imaging, biometrics, mineral and mining imaging, material science imaging, and many more. In this particular work, our focus will be on medical images only. The aim is to develop a computer aided diagnosis (CAD) system based on a newly developed Multidimensional Spatially Variant Finite Mixture Model (MSVFMM) using Markov Random Fields (MRF) Model. Unsupervised means automatic discovery of classes or clusters in images rather than generating the class or cluster descriptions from training image sets. The aim of this work is to produce precise segmentation of color medical images on the basis of subtle color and texture variation. Finer segmentation of images has tremendous potential in medical imaging where subtle information related to color and texture is required to analyze the image accurately. In this particular work, we have used CIE-Luv and Daubechies wavelet transforms as color and texture descriptors respectively. Using the combined effect of a CIE-Luv color model and Daubechies transforms, we can segment color medical images precisely in a meaningful manner. The evaluation of the results is done through comparison of the segmentation quality with another similar alternative approach and it is found that the proposed approach is capable of producing more faithful segmentation.

Traditional image clustering algorithms deal with single-task clustering (STC) problem on a single domain. However, with the increasing number of related images on the Web, it is challenging for STCs to perform related image clustering tasks independently without considering the between-task relationship, which mainly consists of similar visual features and image patterns among tasks. Therefore, it is intuitive to resort to multi-task clustering (MTC) algorithms. However, most existing MTCs learn a shared feature subspace, which may lead to negative transfer when facing the image clustering tasks that are not strongly related. In this paper, we propose a novel multi-task image clustering algorithm, which performs multiple image clustering tasks simultaneously and propagates the task correlation to improve clustering performance. Specifically, we first extend the information bottleneck method to cluster tasks independently. The related and unrelated images between the pairwise clusters of different tasks are then discovered. Meanwhile, two corresponding types of correlations are propagated among the tasks, where only the positive correlation benefits the clustering of each task. A sequential and collaborative method is further designed to ensure an optimal solution. Moreover, we perform a theoretical analysis of the properties on correlation propagation and the convergence of our algorithm. The experimental results demonstrate that the proposed algorithm outperforms the state-of-the-art clustering methods.

Clustering of Medical Images for Analysis: A Fuzzy Approach

Automated methods for image segmentation, image registration, clustering of images and probabilistic atlas construction are of great interest in medical image analysis. In this work, we propose a model where these different aspects are combined in one comprehensive probabilistic framework. The framework is formulated as an EM optimization algorithm. Validation is performed on simulated and real images in terms of segmentation, clustering and atlas construction. Accurate segmentations are obtained and the different modes in a population of normal controls and Huntington disease patients are discovered. Furthermore, our method reveals the localization of cluster specific morphological differences for each image in the population.