3D Capsule Networks for Brain Image Segmentation.

Stroke is the death of brain cells due to lack of blood supply to the cells caused by a blood clot or a blood vessel rupture. It is a dominant cause of disability and death globally. Rehabilitation of post-stroke patients require an efficient treatment plan. Segmentation of stroke lesions from brain images is the first step towards treatment planning. Generally, stroke lesions are manually segmented from brain Magnetic Resonance (MR) images by neuroradiologists. Manual segmentation requires expertise, which is costly, time-consuming, error-prone and laborintensive. Automated stroke lesion segmentation overcomes drawbacks in manual segmentation. U-nets have given state-of-theart results even in small scale medical image datasets. Medical images like MRI are usually noisy even after pre-processing. As a result, the pooling layer used in U-nets, which reduces the number of parameters, tends to loose important information. Capsule networks has been proposed to overcome the drawbacks of pooling layer for classification tasks. Using this information as a motivation, a novel modified U-shaped 3D capsule network (MUDCap3) has been proposed. The 3D nature of the network is to learn temporal information from 3DMRI. The proposed MUDCap3 model has achieved a dice score of 0.67 on the ATLAS dataset. The obtained results outperformed over several state-of-the-art models in the literature.

Medical image segmentation is crucial for improving healthcare outcomes. Convolutional neural networks (CNNs) have been widely applied in medical image analysis; however, their inherent inductive biases limit their ability to capture global contextual information. Vision transformer (ViT) architectures address this limitation by leveraging attention mechanisms to model global relationships; however, they typically require large-scale datasets for effective training, which is challenging in the field of medical imaging due to limited data availability. This study aimed to integrate the advantages of CNN and ViT architectures to improve segmentation performance on small-scale medical image datasets. In this study, we established a U-shaped network architecture based on a Transformer-assisted convolutional neural network (TAC-UNet). The TAC-UNet is primarily composed of a hybrid structure integrating CNN and Transformer components. Specifically, the hybrid architecture follows a dual-path design in which the Transformer branch continuously conveys global contextual information to the CNN backbone. This allows the CNN backbone to enhance its global perception while building on the local features it extracts, thereby improving its ability to comprehend complex image structures. A channel cross-attention (CCA) module is also incorporated as a bridge between the encoder and decoder to better reconcile the semantic discrepancies between them. Detailed experiments on three public datasets were conducted. Specifically, our model was trained on 30 images from the Multi-organ Nucleus Segmentation (MoNuSeg) training dataset, 85 images from the Gland Segmentation (GlaS) training dataset, and 551 images from the Computer Vision Center Colorectal Cancer-Clinic Database (CVC-ClinicDB) dataset. We evaluated the performance of our model on the corresponding test sets. Our TAC-UNet achieved the best Dice scores (80.36%, 90.70%, and 91.81% on the MoNuSeg, GlaS, and CVC-ClinicDB datasets, respectively) of all the models. Compared to other CNN-based, Transformer-based, and hybrid methods, the TAC-UNet demonstrated significantly superior segmentation performance. Our TAC-UNet model showed advanced segmentation performance on small-scale medical image datasets. The detailed experimental results showed the effectiveness of the method. Our model's code is available at: https://github.com/hejlhello/TAC-UNet.

Recently, the Capsule Network is an emerging neural network structure that is characterized by the ability to maintain high classification accuracy. By analyzing the difference between Capsule Network and traditional convolutional neural network, it is found that the model compression method applied to the traditional neural network cannot be directly used in the Capsule Network. To address the problem, an IPC-CapsNet compression algorithm is proposed based on the structural characteristics of the Capsule Networks. The algorithm can reduce the computational complexity and compress the scale of model computation on the basis of retaining the accuracy of model classification. Considering the deficiency of Capsule Network processing serialized text data separately, we combined with IPC-CapsNet and then come up with a sentiment classification algorithm SPT-CapsNet. It has conducted a sentiment analysis experiment of MicroBlog dataset. Compared to other methods, our SPT-CapsNet obtained the best performance among the metrics. The SPT-CapsNet improves the running speed and maintains the balance between classification accuracy and computational efficiency.

Heart disease is one of the leading causes of mortality worldwide, emphasizing the need for early and accurate diagnosis. Traditional machine learning (ML) models such as Random Forest (RF) and Support Vector Machines (SVM) have been widely used for heart disease classification. However, these models often lack the ability to extract hierarchical patterns and long-range dependencies present in complex medical data. To address this limitation, we propose a hybrid deep learning framework that integrates XGBoost with Capsule Networks (XGBoost-CapsNet) and Convolutional Neural Networks (CNN) with Transformer Encoders (CNN-TE) to enhance classification performance.The study utilizes a structured dataset containing essential heart disease indicators. Feature selection is performed using XGBoost, which ranks attributes based on importance. The Capsule Network (CapsNet) is then used to preserve spatial relationships and hierarchical dependencies among features. Meanwhile, the CNN-TE model extracts spatial features through convolutional layers and captures long-range dependencies using a Transformer Encoder with multi-head self-attention mechanisms. The models are trained using optimized hyperparameters and evaluated against baseline ML models (Random Forest, SVM, and standalone CNN). Performance metrics such as accuracy, precision, recall, F1-score, and AUC-ROC are used for comparison.Experimental evaluations demonstrate that the proposed hybrid models significantly outperform traditional approaches. The XGBoost-CapsNet model achieves an accuracy of 98.2%, while CNN-TE reaches 97.4%, both surpassing standalone CNN (95.1%), Random Forest (94.2%), and SVM (91.8%). The AUC-ROC scores further validate the robustness of the models, with XGBoost-CapsNet scoring 0.99 and CNN-TE achieving 0.98. The use of feature selection with XGBoost improves interpretability and computational efficiency, while the hybrid deep learning models enable better feature extraction and classification accuracy.

Facing the challenge of small open labeled data sets in remote sensing change detection, this letter proposes a novel supervised change detection method by taking advantages of capsule network which can reach the same performance as traditional convolutional neural networks (CNNs) but with less training data. To achieve this aim, we propose a pseudo-Siamese capsule network which takes both rotational invariance and spatial hierarchies between features into account for aerial images change detection. First, the features of image pairs are extracted by two identical nonshared weights convolutional capsule networks. Second, the extracted features are directly concatenated and sent to another convolutional capsule layer. The change probability map is obtained by calculating the length of the capsule vectors in the final layer. Additionally, to reduce the influence of imbalance samples when we optimize our network, we design a margin-focal loss function to pay more attention to the misclassified samples. Finally, binary change map can be produced by a simple threshold. Experimental results carried out on the SZTAKI AirChange Benchmark Set show that the proposed method achieves comparable and even better results with existing state-of-the-art methods in terms of F-measure.

(1) Background: The effectiveness of deep learning artificial intelligence depends on data availability, often requiring large volumes of data to effectively train an algorithm. However, few studies have explored the minimum number of images needed for optimal algorithmic performance. (2) Methods: This institutional review board (IRB)-approved retrospective review included patients who received prostate magnetic resonance imaging (MRI) between September 2014 and August 2018 and a magnetic resonance imaging (MRI) fusion transrectal biopsy. T2-weighted images were manually segmented by a board-certified abdominal radiologist. Segmented images were trained on a deep learning network with the following case numbers: 8, 16, 24, 32, 40, 80, 120, 160, 200, 240, 280, and 320. (3) Results: Our deep learning network’s performance was assessed with a Dice score, which measures overlap between the radiologist’s segmentations and deep learning-generated segmentations and ranges from 0 (no overlap) to 1 (perfect overlap). Our algorithm’s Dice score started at 0.424 with 8 cases and improved to 0.858 with 160 cases. After 160 cases, the Dice increased to 0.867 with 320 cases. (4) Conclusions: Our deep learning network for prostate segmentation produced the highest overall Dice score with 320 training cases. Performance improved notably from training sizes of 8 to 120, then plateaued with minimal improvement at training case size above 160. Other studies utilizing comparable network architectures may have similar plateaus, suggesting suitable results may be obtainable with small datasets.

Combining neural networks and image synthesis to enable automatic thoracic cavity segmentation of hyperpolarized 129Xe MRI without proton scans

Capsule networks have gained a lot of popularity in short time due to its unique approach to model equivariant class specific properties as capsules from images. However the dynamic routing algorithm comes with a steep computational complexity. In the proposed approach we aim to create scalable versions of the capsule networks that are much faster and provide better accuracy in problems with higher number of classes. By using dynamic routing to extract intermediate features instead of generating output class specific capsules, a large increase in the computational speed has been observed. Moreover, by extracting equivariant feature capsules instead of class specific capsules, the generalization capability of the network has also increased as a result of which there is a boost in accuracy.

As a significant global health threat, breast cancer needs accurate ultrasound images segmentation for early intelligent diagnosis. Medical image segmentation has made extensive use of the well-known CNNs, transformers, and their variations. However, because of the intrinsic restrictions resulting from the intense complexity of transformers and breast ultrasound pictures, high performance and fast speed cannot be accomplished simultaneously. The research proposes a unique BS-Mamba architecture for rapid and reliable tumor segmentation of breast ultrasound images. It incorporates three new modules to extract multi-level feature for improving the breast image segmentation performance and speed. On the one hand, the BreastSegMamba block effectively captures both global and local high-resolution information, and processes complex features fast. On the other hand, the hybrid attention block is designed to strengthen the extraction of positional and channel features for accurate segmentation. Additionally, the data-sensitive fuzzy logic function focuses on the edges of the ultrasound images to enhance features in critical areas for higher segmentation performance. Through comprehensive experiments and ablation studies on the BUSI and Dataset B breast ultrasound datasets, BS-Mamba significantly outperforms the current state-of-the-art methods in terms of segmentation accuracy. With a Dice coefficient of 92.13% and an IoU of 86.42% on the BUSI dataset and a Dice coefficient of 92.62% and an IoU of 86.67% on Dataset B, respectively, BS-Mamba demonstrated exceptional segmentation performance. Furthermore, in comparison to other established models, BS-Mamba achieves a training time acceleration of up to 2.88×, further substantiating its computational efficiency.

Brain image segmentation is one of the most important parts of clinical diagnostic tools. Brain images mostly contain noise, inhomogeneity and sometimes deviation. Therefore, accurate segmentation of brain images is a very difficult task. However, the process of accurate segmentation of these images is very important and crucial for a correct diagnosis by clinical tools. We presented a review of the methods used in brain segmentation. The review covers imaging modalities, magnetic resonance imaging and methods for noise reduction, inhomogeneity correction and segmentation. We conclude with a discussion on the trend of future research in brain segmentation.

Medical imaging is a technique to get images of the human body for medical science or clinical purposes. Segmentation of a medical image is a challenging task to isolate the suspicious region from the complex medical images. Genetic algorithms (GAs) are an effective tool to handle the problem of medical image segmentation. In this chapter, an application of color magnetic resonance (MR) brain image segmentation is presented by the parallel optimized multilevel sigmoidal (ParaOptiMUSIG) activation function with the parallel self-organizing neural network (PSONN) architecture. Not only confined within this approach, color MR brain image is also segmented by the NSGA-II-based ParaOptiMUSIG activation function to incorporate the multiple objective function-based scenario. These methods are compared with the process of color MR brain image segmentation by the MUSIG activation function with the PSONN architecture. All the methods are applied on a real-life color MR brain image and the quality of the segmented images are accessed by four standard objective functions. The comparison shows that the ParaOptiMUSIG activation function-based method and the NSGA-II-based ParaOptiMUSIG activation function-based method perform better than the MUSIG activation function-based method to segment the color MR brain image.

Problems like image recognition, object detection, image segmentation need efficacious solution for computer vision. Traditionally, these problems are being solved by Deep Learning. Convolutional Neural Network(CNN) and Recurrent Neural Network models are used for computer vision tasks. However, CNNs have some drawbacks. They cannot recognize objects if same object is viewed from different viewpoints and deformed objects. Besides, CNNs require an immense amount of training data. Capsule networks are viewed as a new solution for computer vision problems. They are capable of solving the above-mentioned problems better than CNNs. Capsule networks have shown better accuracy in many computer vision applications. In this paper, we review the methodologies and architectures of existing implementations of capsule networks.KeywordsDeep learningCNNDynamic routingCapsule networkExpectation maximization

Power distribution grids (PDGs) are one of the main parts of electrical logistic chains with the task of transferring electricity to the consumers continually. Adverse weather conditions, equipment failure, and human disruption can bring about the PDGs to faulty situations leading to the inevitable interrupting power consumption which results in financial losses. Therefore, it is vital to locate the faulty spot accurately and quickly. In this paper, an automatic deep learning framework is implemented to locate faults in the PDGs with limited measurement requirements i. e. only the voltage at the substations. The Spectrogram time-frequency analysis is performed on the voltage signal to obtain more informative training data. A convolutional neural network (CNN) model is utilized and trained to identify the location of the fault in the distribution grid. To provide a more precise outcome, the capsule network is used. This approach determines the location of the faulty section using an offline databank and then estimates the exact faulty point using an online databank of multiple fault scenarios in that section. To evaluate the powerfulness of the proposed method, several simulations are performed on the IEEE 34-node feeder in MATLAB (2020b). For further verification of the proposed method's effectiveness, several laboratory tests are done as well. The results demonstrate that the proposed technique performs exceptionally well in terms of accuracy compared to other state-of-art counterparts, even when merely using the recorded voltage at the substations.

Voice controlled applications can be a great aid to society, especially for physically challenged people. However this requires robustness to all kinds of variations in speech. A spoken language understanding system that learns from interaction with and demonstrations from the user, allows the use of such a system in different settings and for different types of speech, even for deviant or impaired speech, while also allowing the user to choose a phrasing. The user gives a command and enters its intent through an interface, after which the model learns to map the speech directly to the right action. Since the effort of the user should be as low as possible, capsule networks have drawn interest due to potentially needing little training data compared to deeper neural networks. In this paper, we show how capsules can incorporate multitask learning, which often can improve the performance of a model when the task is difficult. The basic capsule network will be expanded with a regularisation to create more structure in its output: it learns to identify the speaker of the utterance by forcing the required information into the capsule vectors. To this end we move from a speaker dependent to a speaker independent setting.

GMetaNet: Multi-scale ghost convolutional neural network with auxiliary MetaFormer decoding path for brain tumor segmentation