Search

The classification of medical images enables physicians to perform expeditious and accurate data analysis, increasing the chances of timely disease diagnosis and early intervention to the patient. However, classification is a time‐consuming and labour intensive process when done manually. The Capsule Network (CapsNet) architecture has advantages in accurately and quickly classifying medical images due to its ability to evaluate images within part‐whole relationships, robustness to data rotations and affine transformations, and good performance on small datasets. However, CapsNet may demonstrate low performance on complex datasets. In this study, a new CapsNet model named MResCaps is proposed to overcome this disadvantage and enhance its performance on complex images. MResCaps utilizes an increasing number of residual blocks in each layer in parallel lane to obtain rich feature maps at different levels, aiming to achieve high success in the classification of various medical images. To evaluate the model's performance, the CIFAR10 dataset and the DermaMNIST, PneumoniaMNIST, and OrganMNIST‐S datasets from the MedMNIST dataset collection are used. MResCaps outperformed CapsNet by 20% in terms of accuracy on the CIFAR10 dataset. In addition, AUC values of 96.25%, 96.30%, and 97.12% were achieved in DermaMNIST, PneumoniaMNIST, and OrganMNIST‐S datasets, respectively. The results show that the proposed new model MResCaps improves the performance of CapsNet in the classification of complex and medical images. Furthermore, the model has demonstrated a better performance in comparison with extant studies in the literature. This study aims to contribute significantly to the literature by introducing a novel perspective on CapsNet‐based architectures for the classification of medical images through a parallel‐laned architecture and a rich feature capsule‐focused approach. [ABSTRACT FROM AUTHOR]

Intracranial aneurysms (IAs) manifest as atypical dilatation within the intracranial arterial structures, the rupture of which accounts for high mortality and morbidity rates. Current clinical protocols require radiologists to manually annotate IAs on Magnetic Resonance Angiography (MRA) images, which is inherently subjective and time‐consuming. Given these limitations, there is an urgent need to explore methods for automated and accurate segmentation of IAs from MRA images. In particular, recent years have witnessed the proliferation of sophisticated computational techniques, with deep learning algorithms—especially the 3D U‐Net and its derivatives—gaining prominence in segmentation works. Nevertheless, convolutional neural network (CNN)‐based models have an inherent limitation in capturing long‐range spatial dependencies, which inadvertently compromises the retention of global features critical for segmentation. In response to this challenge, we introduce an avant‐garde architectural design, dubbed staged cluster transformers (SCTR), which incorporates cluster mechanism into vision transformers to perform volumetric MRA image segmentation. In addition to the MRA clustering branch, the spatially aligned brain Magnetic Resonance Imaging (MRI) representation branch is also combined to extract the structural features and assist the network in learning richer contextual and boundary information for accurate voxel prediction. For validation, we utilized both a publicly available challenge dataset and an internal clinical dataset in this study. Our proposed model achieves dice similarity coefficients (DSC) of 0.5587 and 0.8110 on these two datasets, respectively, outperforming other state‐of‐the‐art approaches. The results suggest that SCTR is a promising method for automatic segmentation of IAs. Our code is available at https://github.com/guolilin/SCTR. [ABSTRACT FROM AUTHOR]

Early diagnosis of multiple sclerosis (MS) through the delineation of lesions in the brain magnetic resonance imaging is important in preventing the deteriorating condition of MS. This study aims to develop a modified U‐Net model for automating lesions segmentation in MS more accurately. The proposed modified U‐Net uses residual dense blocks to replace the standard convolutional stacks and incorporates three axes (axial, sagittal, and coronal) of 2D slice images as input. Furthermore, a custom fusion method is also introduced for merging the predicted lesions from different axes. The model was implemented on ISBI2015 and OpenMS data sets. On ISBI2015, the proposed model achieves the best overall score of 93.090% and DSC of 0.857 on the OpenMS data set. [ABSTRACT FROM AUTHOR]

Image segmentation requires large amounts of annotated data. However, collecting massive datasets with annotations is difficult since they are expensive and labor‐intensive. The unsupervised domain adaptation (UDA) for image segmentation is a promising approach to address the label‐scare problem on the target domain, which enables the trained model on the source labeled domain to be adaptive to the target domain. The adversarial‐based methods encourage extracting the domain‐invariant features by training a domain discriminator to mitigate the domain gap. Existing UDA segmentation methods fail to obtain satisfied segmentation results as they only consider the global knowledge of output space while neglecting the local information of feature space. In this paper, a fusing feature and output (FFO) space method is proposed for UDA, which in the context of medical image segmentation. The proposed model is learned by training a more powerful domain discriminator, which considers features extracted from both feature space and output space. Extensive experiments carried out on several medical image datasets show the adaptation effectiveness of our approach in improving the segmentation performance. [ABSTRACT FROM AUTHOR]

The statistical properties in various medical images demonstrate uncorrelated noise fluctuations. The signal noise fluctuations are generally due to physical imaging processes and have nothing to do with the tissue textures. Adding the noise types (e.g., quantization, electronics, photon) usually degrade medical images. The noise variation is usually assumed to be additive with zero‐mean, constant variance Gaussian distribution. However, close consideration of different medical images indicates the need for better model representation to minimise the noise that can be vital in decision‐making. This research proposed a probabilistic method to represent all real‐type noise in general medical images. The method aims to cover most classical statistical models such as Gaussian, lognormal, Rayleigh, Weibull, and Nakagami without a prior examination to test for fitness. The proposed model was applied to actual clinical images to test the performance of the noise originating from the physical processes. The noise is assumed to be additive white Gaussian type with a zero mean and constant variance. The theoretical literature indicates that a nonlinear function can better represent noise. This research helps to form a relationship between the image intensity and the noise variance that yields the fitting parameters in the introduced nonlinear function. The validity of the proposed method was proved mathematically and tested using the well know Kolmogorov–Smirnov (K‐S) and Akaike Information Criteria (AIC) tests. The method was successfully applied to various clinical images such as magnetic resonance, x‐ray, and panoramic images. The model's performance is compared with the classical models using root mean squared error (RMSE), relative error (RE), and R2 as the evaluation matrices. The presented model has outperformed all classic models. [ABSTRACT FROM AUTHOR]

Medical images have become omnipresent in diagnosis and therapy. However, they can be affected by various types of noise that reduce image quality and make the final diagnostic decision difficult. The main objective of this research is to effectively remove the noise while preserving the important image characteristics. This paper proposes a novel approach for image denoising based on discrete wavelet transform (DWT) with the selection of the best decomposition level and mother wavelet. Then, the thresholding function is carried out in the detail coefficients. Optimal thresholding is done using new optimization techniques such as the crow search algorithm and social spider optimization techniques. Finally, the inverse of DWT is applied to reconstruct the denoised image. The proposed method is evaluated using peak signal to noise ratio, mean square error, and the structural similarity index measure. The experimental results show the efficiency of the optimization‐based denoising method over standard methods. Interesting results are obtained with all kinds of noise, and improvements about 30 dB can be reached with the Rician noise. [ABSTRACT FROM AUTHOR]

Many types of medical images must be fused, as single‐modality medical images can only provide limited information due to the imaging principles and the complexity of human organ structures. In this paper, a multimodal medical image fusion method that combines the advantages of nonsubsampling contourlet transform (NSCT) and fuzzy entropy is proposed to provide a basis for clinical diagnosis and improve the accuracy of target recognition and the quality of fused images. An image is initially decomposed into low‐ and high‐frequency subbands through NSCT. The corresponding fusion rules are adopted in accordance with the different characteristics of the low‐ and high‐frequency components. The membership degree of low‐frequency coefficients is calculated. The fuzzy entropy is also computed and subsequently used to guide the fusion of coefficients to preserve image details. High‐frequency components are fused by maximizing the regional energy. The final fused image is obtained by inverse transformation. Experimental results show that the proposed method achieves good fusion effect based on the subjective visual effect and objective evaluation criteria. This method can also obtain high average gradient, SD, and edge preservation and effectively retain the details of the fused image. The results of the proposed algorithm can provide effective reference for doctors to assess patient condition. [ABSTRACT FROM AUTHOR]

Aiming at the process of medical diagnosis, many problems such as unclear images and low contrast are often caused by noise and interference in the process of medical image acquisition and transmission. This article proposes a new image enhancement method that combines the wavelet domain with the spatial domain. First, we input two identical images (Both of the identical images are original images.) in which the first image is enhanced by histogram equalization. Then, the two images are divided into four sub‐images by a two‐dimensional wavelet transform. The average of the low‐frequency coefficients of the low‐frequency sub‐images of the two images is taken as the low‐frequency coefficients of the final reconstruction. Second, aiming at the problem that the contrast may be too low, the fourth high‐frequency sub‐image is blurred (sharpened) twice. The fourth high‐frequency sub‐image after blurring is denoised by median filtering. Finally, the four sub‐images are fused to obtain the enhanced image. The experimental results show that the peak signal‐to‐noise ratio, structural similarity, and processing time of the proposed algorithm are better than those of other contrast algorithms, especially the processing time. These objective indicators show that the proposed algorithm can not only effectively suppress noise but also significantly enhance the contrast. Subjectively, compared with other algorithms, the proposed algorithm achieves a better visual effect and greatly reduces the processing time. [ABSTRACT FROM AUTHOR]

Noises and artifacts are introduced in medical images during the process of imaging and transmission, resulting in reduced definition and lack of detail. Therefore, a contrast enhancement method, based on fuzzy set theory and nonsubsampled shearlet transform (NSST), is proposed. First, the original image is decomposed into several high‐frequency components and a low‐frequency component by NSST. Then, the threshold method is used to remove noises in the high‐frequency components. In addition, a linear stretch is used to improve the overall contrast in the low‐frequency component. Then, the reconstruct image is reconstructed by applying the inverse NSST to the processed high‐frequency and low‐frequency components. Finally, the fuzzy contrast is used to improve the detail information and global contrast in the reconstruct image. Experimental results indicate that, relative to contrast algorithms, the peak signal‐to‐noise ratio of the proposed method is improved by approximately 18%, and the root mean square error (RMSE) is optimized to approximately 48%. The proposed method also improves the image definition and texture information. Moreover, when compared with the Improved Fuzzy Contrast Combined Adaptive Threshold in NSCT for Medical Image Enhancement, the processing time (time) of this proposed method optimizes about 86%, which can obviously improve the computational efficiency of this method. [ABSTRACT FROM AUTHOR]

In order to enhance the pathological features of medical images and aid the medical diagnosis, the image enhancement is a necessary process. This study presented the Gaussian probability model combining with bi‐histogram equalization to enhance the contrast of pathological features in medical images. There are five different bi‐histogram equalizations, namely, bi‐histogram equalization (BBHE), dualistic sub‐image histogram equalization (DSIHE), bi‐histogram equalization with a plateau limit (BHEPL), bi‐histogram equalization median plateau limit (BHEPL‐D), and bi‐histogram equalization with modified histogram bins (BHEMHB). The entropy, contrast, absolute mean brightness error (AMBE), and skewness difference are used to quantize the enhancement results. From the experimental result, it is observed that the entropy and contrast of the images can be effectively enhanced by using Gaussian probability bi‐histogram equalizations, and the Gaussian probability bi‐histogram equalization median plateau limit (GPBHEPL‐D) has the best enhanced result. The proposed GPBHEPL‐D method is effective in strengthening the pathological features in medical images, so as to increase the efficiency of doctors' diagnoses and computer‐aided detection. [ABSTRACT FROM AUTHOR]