Medical Image Clustering Research Articles

K-Mean Based Hyper-Metaheuristic Grey Wolf and Cuckoo Search Optimizers for Automatic MRI Medical Image Clustering

In this paper a new clustering algorithm is proposed for optimal clustering of MRI medical image. In our proposed algorithm, the clustering process implemented by K-means clustering algorithm, due to its simplicity and speed. The optimization process was done by a well-known metaheuristic algorithms Grey Wolf Optimizer (GWO) and Cuckoo Search Optimizer. GWO is a metaheuristic algorithm inspired by the social hierarchy and hunting behavior of grey wolves. It mimics the leadership hierarchy and hunting strategies of wolves to explore the search space efficiently. GWO has shown promising performance in finding high-quality solutions compared to other well-established optimizers. It explores the solution space to find better cluster assignments that minimize the overall intra-cluster variance. By leveraging the exploration potential of GWO, the proposed algorithm aims to improve the quality of the clustering results. Furthermore, the Cuckoo Search Optimizer (CS) is combined with GWO to enhance the algorithm's ability to find a global solution. Cuckoo Search is a metaheuristic algorithm inspired by the breeding behavior of cuckoo birds. It employs random search and Levy flights to diversify the search process and avoid getting trapped in local optima. By combining CS with GWO, the proposed algorithm aims to increase the likelihood of finding the optimal clustering solution.

Structure-aware preserving projections with applications to medical image clustering

The application of dimensionality reduction (DR) in effectively handling high-dimensional data is becoming increasingly prominent. However, mainstream methods in projection learning exhibit a reliance on either global or local structures, resulting in the inability to effectively learn the discriminative projection. To address this issue, we propose a novel unsupervised DR algorithm, called Structure-Aware Preserving Projections (SAPP). Specifically, SAPP exploits a powerful combination of subspace clustering and graph construction to effectively capture the intrinsic structure of the data. It is able to find discriminative projections, which is mainly attributed to two key factors: (1) can capture the local structure of the data by constructing the nearest neighbor graph and introducing the grouping effect of the representation into projection learning; and (2) preserves the global structure and respects the complex relationship between data points by integrating least squares regression into the dimension reduction process. Moreover, SAPP proves to be a versatile framework that is easily extended to semi-supervised scenarios. Extensive experiments on medical image datasets confirm the effectiveness of our proposed method, showcasing superior clustering accuracy compared to state-of-the-art approaches.

MedTransCluster: Transfer learning for deep medical image clustering

This work introduces the “MedTransCluster” framework, a novel approach to medical image clustering in chest radiography through the application of transfer learning, leveraging the capabilities of pre-trained deep learning models. Our evaluation encompassed a variety of neural networks, considering their adaptability to the nuances of medical imaging data. The study incorporated four renowned clustering algorithms and an expanded set of evaluation metrics, offering a comprehensive comparison and a refined analysis of these models’ ability to cluster complex diagnostic features. Notably, EfficientNetB0 coupled with DBSCAN clustering algorithm achieved a silhouette score of 0.924131, and ResNet152 with KMeans displayed a Calinski Harabasz score of 9655.213964, indicating their superior proficiency in capturing the intricacies of medical features. These results emphasize the critical importance of model refinement within the healthcare imaging sphere and underscore the potential of methodologies like MedTransCluster in enhancing diagnostic accuracy and patient outcomes.

Contrastive learning for unsupervised medical image clustering and reconstruction

The lack of large labeled medical imaging datasets, along with significant inter-individual variability compared to clinically established disease classes, poses significant challenges in exploiting medical imaging information in a precision medicine paradigm, where in principle dense patient-specific data can be employed to formulate individual predictions and/or stratify patients into finer-grained groups which may follow more homogeneous trajectories and therefore empower clinical trials. In order to efficiently explore the effective degrees of freedom underlying variability in medical images in an unsupervised manner, in this work we propose an unsupervised autoencoder framework which is augmented with a contrastive loss to encourage high separability in the latent space. The model is validated on (medical) benchmark datasets. As cluster labels are assigned to each example according to cluster assignments, we compare performance with a supervised transfer learning baseline. Our methods achieves similar performance to the supervised architecture, indicating that separation in the latent space reproduces expert medical observer-assigned labels. The proposed method could be beneficial for patient stratification, exploring new subdivision of larger classes or pathological continua or, due to its sampling abilities in a variation setting, data augmentation in medical image processing.

CLUSTERING OF MEDICAL IMAGES USING MULTIWAVELET TRANSFORM AND K-MEANS ALGORITHMS

Imaging data and biological records are both included in the field of medical informatics. Medical image clustering is an important area of research that is getting increased interest in both academia and the health professions. It addresses the issues of medical diagnosis, analysis, and education. Several medical imaging methods and applications based on data mining have been made and tested to deal with these problems. This paper looks at how image classification techniques diagnose diseases in the human body. It concerns the imaging modalities, dataset, and the pros and cons of each method. An optimal clustering technique of medical images using multiwavelet transforms proposed that combines the multiwavelet transform filterbanks with the k-means clustering algorithm to improve the performance and get a clinically meaningful clustering shape. In comparison with other methods of clustering, it was shown that this method has a much higher cluster classification than those published before. A user-friendly Matlab program has been constructed to test and get the results of the proposed algorithms

Soft and self constrained clustering for group-based labeling.

When using deep neural networks in medical image classification tasks, it is mandatory to prepare a large-scale labeled image set, and this often requires significant effort by medical experts. One strategy to reduce the labeling cost is group-based labeling, where image samples are clustered and then a label is attached to each cluster. The efficiency of this strategy depends on the purity of the clusters. Constrained clustering is an effective way to improve the purity of the clusters if we can give appropriate must-links and cannot-links as constraints. However, for medical image clustering, the conventional constrained clustering methods encounter two issues. The first issue is that constraints are not always appropriate due to the gap between semantic and visual similarities. The second issue is that attaching constraints requires extra effort from medical experts. To deal with the first issue, we propose a novel soft-constrained clustering method, which has the ability to ignore inappropriate constraints. To deal with the second issue, we propose a self-constrained clustering method that utilizes prior knowledge about the target images to set the constraints automatically. Experiments with the endoscopic image datasets demonstrated that the proposed methods give clustering results with higher purity.

Graph entropy-based clustering algorithm in medical brain image database

The high incidence of brain tumor has increased significantly in recent years. It is becoming more and more concernful to discover knowledge through mining medical brain image to aid doctors’ diagnosis. Clustering medical images for Intelligent Decision Support is an important part in the field of medical image mining because there are several technical aspects which make this problem challenging. In this paper, we propose a medical brain image clustering method to find similar pathology images that can assist doctors to analyze the specific disease, discover its potential cause and make more accurate treatment. Firstly, this method represents medical brain image dataset as a weighted, undirected and complete graph. Secondly, this graph is sparsified so as to describe the similarity of medical images very well. Last but not the least, a graph entropy based clustering method for this sparsified graph is proposed to cluster these medical images. The experimental results show that this method can cluster medical images efficiently and run well in time complexity. The clustering results can better describe the similarity of medical images.

Decision tree based medical image clustering algorithm in computer-aided diagnoses

With the rapid development of intelligent diagnostic medical imaging, artificial intelligent methods have become a research hotspot in this field with the rapid development of medical imaging intelligent diagnosis. The new research progress of artificial intelligence in medical image processing in recent five years is discussed. This paper discussed the function of medical image mining in computer-aided diagnoses. The idea of using luminance grade as the features of CT image and the method of extracting and storing the luminance grade are proposed. The results of classification based on decision tree and clustering based on density to some brain and breast CT images and the analysis to them are introduced. Moreover, the conclusion and future work are given.

Robust fuzzy RBF network based image segmentation and intelligent decision making system for carotid artery ultrasound images

In this paper, a robust image segmentation and intelligent decision making system for carotid artery ultrasound images is proposed. Medical images may have various types of inherent degradations due to imaging equipments, operating environment, etc. For instance, carotid artery ultrasound images are affected by low resolution, speckle noise, and wave interferences. Hence, robust medical image clustering technique is inevitable for obtaining accurate results in the subsequent stages. In this context, a robust fuzzy radial basis function network (RFRBFN) technique is proposed. The proposed technique modified fuzzy RBF algorithm by incorporating spatial information and a smoothing parameter into its objective function, consequently, the proposed technique is able to cope with noise related variations. To assess the effectiveness, the RFRBFN technique is applied to segment carotid artery ultrasound images and its performance has been evaluated against impulse, and Gaussian noises of various intensities. Performance comparison with existing methods shows that the proposed RFRBFN outperforms the existing fuzzy based c-means and RBF techniques in case of both noisy and noise-free images. Experiments on 200 real carotid artery ultrasound images reveal the proposed technique offers effective segmentation results. Finally, intima-media thickness is measured from the obtained segmented images and multi-layer backpropagation neural network is employed to classify the segmented images into normal or diseased subjects. The proposed intelligent decision making system can thus be used as a secondary observer for identification of plaque in the carotid artery.

Intuitionistic fuzzy color clustering of human cell images on different color models

This paper provides a color cell image clustering algorithm using intuitionistic fuzzy set theory using different color models. The clustering algorithm clusters the blood cells very clearly that helps in detecting various types of human diseases. Clustering of medical images is a challenging task as medical images are vague in nature due to poor illumination. So the boundaries or regions are not clear. Clustering using fuzzy set theory is very robust but still there is some uncertainty present while defining the membership function in fuzzy set theory. This uncertainty is due the lack of knowledge or personal error while defining the membership function. Intuitionistic fuzzy set takes into account this uncertainty and thus it may be useful in medical or real time image processing. The two uncertainty parameters in intuitionistic fuzzy set thus help in converging the cluster center to a desirable location than the cluster centers obtained by fuzzy C means algorithm. Different color models e.g., RGB, HSV, and CIELab are used in this algorithm and it is found that RGB and CIELab give almost similar result. The algorithm is also tested on conventional fuzzy C means algorithm to show the efficacy of the new algorithm.

TWave: High-order analysis of functional MRI

The traditional approach to functional image analysis models images as matrices of raw voxel intensity values. Although such a representation is widely utilized and heavily entrenched both within neuroimaging and in the wider data mining community, the strong interactions among space, time, and categorical modes such as subject and experimental task inherent in functional imaging yield a dataset with "high-order" structure, which matrix models are incapable of exploiting. Reasoning across all of these modes of data concurrently requires a high-order model capable of representing relationships between all modes of the data in tandem. We thus propose to model functional MRI data using tensors, which are high-order generalizations of matrices equivalent to multidimensional arrays or data cubes. However, several unique challenges exist in the high-order analysis of functional medical data: naïve tensor models are incapable of exploiting spatiotemporal locality patterns, standard tensor analysis techniques exhibit poor efficiency, and mixtures of numeric and categorical modes of data are very often present in neuroimaging experiments. Formulating the problem of image clustering as a form of Latent Semantic Analysis and using the WaveCluster algorithm as a baseline, we propose a comprehensive hybrid tensor and wavelet framework for clustering, concept discovery, and compression of functional medical images which successfully addresses these challenges. Our approach reduced runtime and dataset size on a 9.3GB finger opposition motor task fMRI dataset by up to 98% while exhibiting improved spatiotemporal coherence relative to standard tensor, wavelet, and voxel-based approaches. Our clustering technique was capable of automatically differentiating between the frontal areas of the brain responsible for task-related habituation and the motor regions responsible for executing the motor task, in contrast to a widely used fMRI analysis program, SPM, which only detected the latter region. Furthermore, our approach discovered latent concepts suggestive of subject handedness nearly 100× faster than standard approaches. These results suggest that a high-order model is an integral component to accurate scalable functional neuroimaging.

Incorporating domain knowledge into medical image clustering

Image mining is more than just an extension of data mining to image domain but an interdisciplinary endeavor. Very few people have systematically investigated this field. Clustering medical images is an important part in domain-specific application image mining because there are several technical aspects which make this problem challenging. In this paper, we firstly quantify the domain knowledge about brain image (especially the brain symmetry), and then incorporate this quantified measurement into the clustering algorithm. Our algorithm contains two parts: (1) clustering regions of interest (ROI) detected from brain image; (2) clustering images based on the similarity of ROI. We apply the method to cluster brain images and present results to demonstrate its usefulness and effectiveness.

Research on Medical Image Clustering Based on Approximate Density Function

Research on Medical Image Clustering Based on Approximate Density Function