MACFNet: Detection of Alzheimer's disease via multiscale attention and cross-enhancement fusion network.

BACKGROUND AND OBJECTIVE: Alzheimer's disease (AD) is a dreaded degenerative disease that results in a profound decline in human cognition and memory. Due to its intricate pathogenesis and the lack of effective therapeutic interventions, early diagnosis plays a paramount role in AD. Recent research based on neuroimaging has shown that the application of deep learning methods by multimodal neural images can effectively detect AD. However, these methods only concatenate and fuse the high-level features extracted from different modalities, ignoring the fusion and interaction of low-level features across modalities. It consequently leads to unsatisfactory classification performance. METHOD: In this paper, we propose a novel multi-scale attention and cross-enhanced fusion network, MACFNet, which enables the interaction of multi-stage low-level features between inputs to learn shared feature representations. We first construct a novel Cross-Enhanced Fusion Module (CEFM), which fuses low-level features from different modalities through a multi-stage cross-structure. In addition, an Efficient Spatial Channel Attention (ECSA) module is proposed, which is able to focus on important AD-related features in images more efficiently and achieve feature enhancement from different modalities through two-stage residual concatenation. Finally, we also propose a multiscale attention guiding block (MSAG) based on dilated convolution, which can obtain rich receptive fields without increasing model parameters and computation, and effectively improve the efficiency of multiscale feature extraction. RESULTS: Experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that our MACFNet has better classification performance than existing multimodal methods, with classification accuracies of 99.59 %, 98.85 %, 99.61 %, and 98.23 % for AD vs. CN, AD vs. MCI, CN vs. MCI and AD vs. CN vs. MCI, respectively, and specificity of 98.92 %, 97.07 %, 99.58 % and 99.04 %, and sensitivity of 99.91 %, 99.89 %, 99.63 % and 97.75 %, respectively. CONCLUSIONS: The proposed MACFNet is a high-accuracy multimodal AD diagnostic framework. Through the cross mechanism and efficient attention, MACFNet can make full use of the low-level features of different modal medical images and effectively pay attention to the local and global information of the images. This work provides a valuable reference for multi-mode AD diagnosis.

UKSSL: Underlying Knowledge Based Semi-Supervised Learning for Medical Image Classification.

Goal: Deep learning techniques have made significant progress in medical image analysis. However, obtaining ground truth labels for unlabeled medical images is challenging as they often outnumber labeled images. Thus, training a high-performance model with limited labeled data has become a crucial challenge. Methods: This study introduces an underlying knowledge-based semi-supervised framework called UKSSL, consisting of two components: MedCLR extracts feature representations from the unlabeled dataset; UKMLP utilizes the representation and fine-tunes it with the limited labeled dataset to classify the medical images. Results: UKSSL evaluates on the LC25000 and BCCD datasets, using only 50% labeled data. It gets precision, recall, F1-score, and accuracy of 98.9% on LC25000 and 94.3%, 94.5%, 94.3%, and 94.1% on BCCD, respectively. These results outperform other supervised-learning methods using 100% labeled data. Conclusions: The UKSSL can efficiently extract underlying knowledge from the unlabeled dataset and perform better using limited labeled medical images.

Multimodal Emotion Recognition Based on Facial Expressions, Speech, and EEG.

Goal: As an essential human-machine interactive task, emotion recognition has become an emerging area over the decades. Although previous attempts to classify emotions have achieved high performance, several challenges remain open: 1) How to effectively recognize emotions using different modalities remains challenging. 2) Due to the increasing amount of computing power required for deep learning, how to provide real-time detection and improve the robustness of deep neural networks is important. Method: In this paper, we propose a deep learning-based multimodal emotion recognition (MER) called Deep-Emotion, which can adaptively integrate the most discriminating features from facial expressions, speech, and electroencephalogram (EEG) to improve the performance of the MER. Specifically, the proposed Deep-Emotion framework consists of three branches, i.e., the facial branch, speech branch, and EEG branch. Correspondingly, the facial branch uses the improved GhostNet neural network proposed in this paper for feature extraction, which effectively alleviates the overfitting phenomenon in the training process and improves the classification accuracy compared with the original GhostNet network. For work on the speech branch, this paper proposes a lightweight fully convolutional neural network (LFCNN) for the efficient extraction of speech emotion features. Regarding the study of EEG branches, we proposed a tree-like LSTM (tLSTM) model capable of fusing multi-stage features for EEG emotion feature extraction. Finally, we adopted the strategy of decision-level fusion to integrate the recognition results of the above three modes, resulting in more comprehensive and accurate performance. Result and Conclusions: Extensive experiments on the CK+, EMO-DB, and MAHNOB-HCI datasets have demonstrated the advanced nature of the Deep-Emotion method proposed in this paper, as well as the feasibility and superiority of the MER approach.

NF-GAT: A Node Feature-Based Graph Attention Network for ASD Classification.

Goal: The purpose of this paper is to recognize autism spectrum disorders (ASD) using graph attention network. Methods: we propose a node features graph attention network (NF-GAT) for learning functional connectivity (FC) features to achieve ASD diagnosis. Firstly, node features are modelled based on functional magnetic resonance imaging (fMRI) data, with each subject modelled as a graph. Next, we use the graph attention layer to learn the node features and gets the node information of different nodes for ASD classification. Results: Compared with other models, the NF-GAT has significant advantages in terms of classification results. Conclusions: NF-GAT can be effectively used for ASD classification.

Comparing Business, Innovation, and Platform Ecosystems: A Systematic Review of the Literature.

In recent decades, the term "ecosystem" has garnered substantial attention in scholarly and managerial discourse, featuring prominently in academic and applied contexts. While individual scholars have made significant contributions to the study of various types of ecosystem, there appears to be a research gap marked by a lack of comprehensive synthesis and refinement of findings across diverse ecosystems. This paper systematically addresses this gap through a hybrid methodology, employing bibliometric and content analyses to systematically review the literature from 1993 to 2023. The primary research aim is to critically examine theoretical studies on different ecosystem types, specifically focusing on business, innovation, and platform ecosystems. The methodology of this study involves a content review of the identified literature, combining quantitative bibliometric analyses to differentiate patterns and content analysis for in-depth exploration. The core findings center on refining and summarizing the definitions of business, innovation, and platform ecosystems, shedding light on both commonalities and distinctions. Notably, the research unveils shared characteristics such as openness and diversity across these ecosystems while highlighting significant differences in terms of participants and objectives. Furthermore, the paper delves into the interconnections within these three ecosystem types, offering insights into their dynamics and paving the way for discussions on future research directions. This comprehensive examination not only advances our understanding of business, innovation, and platform ecosystems but also lays the groundwork for future scholarly inquiries in this dynamic and evolving field.

Exploring simple triplet representation learning.

Fully supervised learning methods necessitate a substantial volume of labelled training instances, a process that is typically both labour-intensive and costly. In the realm of medical image analysis, this issue is further amplified, as annotated medical images are considerably more scarce than their unlabelled counterparts. Consequently, leveraging unlabelled images to extract meaningful underlying knowledge presents a formidable challenge in medical image analysis. This paper introduces a simple triple-view unsupervised representation learning model (SimTrip) combined with a triple-view architecture and loss function, aiming to learn meaningful inherent knowledge efficiently from unlabelled data with small batch size. With the meaningful representation extracted from unlabelled data, our model demonstrates exemplary performance across two medical image datasets. It achieves this using only partial labels and outperforms other state-of-the-art methods. The method we present herein offers a novel paradigm for unsupervised representation learning, establishing a baseline that is poised to inspire the development of more intricate SimTrip-based methods across a spectrum of computer vision applications. Code and user guide are released at https://github.com/JerryRollingUp/SimTripSystem, the system also runs at http://43.131.9.159:5000/.

An Enhanced RIME Optimizer with Horizontal and Vertical Crossover for Discriminating Microseismic and Blasting Signals in Deep Mines.

Real-time monitoring of rock stability during the mining process is critical. This paper first proposed a RIME algorithm (CCRIME) based on vertical and horizontal crossover search strategies to improve the quality of the solutions obtained by the RIME algorithm and further enhance its search capabilities. Then, by constructing a binary version of CCRIME, the key parameters of FKNN were optimized using a binary conversion method. Finally, a discrete CCRIME-based BCCRIME was developed, which uses an S-shaped function transformation approach to address the feature selection issue by converting the search result into a real number that can only be zero or one. The performance of CCRIME was examined in this study from various perspectives, utilizing 30 benchmark functions from IEEE CEC2017. Basic algorithm comparison tests and sophisticated variant algorithm comparison experiments were also carried out. In addition, this paper also used collected microseismic and blasting data for classification prediction to verify the ability of the BCCRIME-FKNN model to process real data. This paper provides new ideas and methods for real-time monitoring of rock mass stability during deep well mineral resource mining.

Face Image Segmentation Using Boosted Grey Wolf Optimizer.

Image segmentation methods have received widespread attention in face image recognition, which can divide each pixel in the image into different regions and effectively distinguish the face region from the background for further recognition. Threshold segmentation, a common image segmentation method, suffers from the problem that the computational complexity shows exponential growth with the increase in the segmentation threshold level. Therefore, in order to improve the segmentation quality and obtain the segmentation thresholds more efficiently, a multi-threshold image segmentation framework based on a meta-heuristic optimization technique combined with Kapur's entropy is proposed in this study. A meta-heuristic optimization method based on an improved grey wolf optimizer variant is proposed to optimize the 2D Kapur's entropy of the greyscale and nonlocal mean 2D histograms generated by image computation. In order to verify the advancement of the method, experiments compared with the state-of-the-art method on IEEE CEC2020 and face image segmentation public dataset were conducted in this paper. The proposed method has achieved better results than other methods in various tests at 18 thresholds with an average feature similarity of 0.8792, an average structural similarity of 0.8532, and an average peak signal-to-noise ratio of 24.9 dB. It can be used as an effective tool for face segmentation.

Multiple-instance ensemble for construction of deep heterogeneous committees for high-dimensional low-sample-size data.

Deep ensemble learning, where we combine knowledge learned from multiple individual neural networks, has been widely adopted to improve the performance of neural networks in deep learning. This field can be encompassed by committee learning, which includes the construction of neural network cascades. This study focuses on the high-dimensional low-sample-size (HDLS) domain and introduces multiple instance ensemble (MIE) as a novel stacking method for ensembles and cascades. In this study, our proposed approach reformulates the ensemble learning process as a multiple-instance learning problem. We utilise the multiple-instance learning solution of pooling operations to associate feature representations of base neural networks into joint representations as a method of stacking. This study explores various attention mechanisms and proposes two novel committee learning strategies with MIE. In addition, we utilise the capability of MIE to generate pseudo-base neural networks to provide a proof-of-concept for a "growing" neural network cascade that is unbounded by the number of base neural networks. We have shown that our approach provides (1) a class of alternative ensemble methods that performs comparably with various stacking ensemble methods and (2) a novel method for the generation of high-performing "growing" cascades. The approach has also been verified across multiple HDLS datasets, achieving high performance for binary classification tasks in the low-sample size regime.

An Enhanced Hunger Games Search Optimization with Application to Constrained Engineering Optimization Problems.

The Hunger Games Search (HGS) is an innovative optimizer that operates without relying on gradients and utilizes a population-based approach. It draws inspiration from the collaborative foraging activities observed in social animals in their natural habitats. However, despite its notable strengths, HGS is subject to limitations, including inadequate diversity, premature convergence, and susceptibility to local optima. To overcome these challenges, this study introduces two adjusted strategies to enhance the original HGS algorithm. The first adaptive strategy combines the Logarithmic Spiral (LS) technique with Opposition-based Learning (OBL), resulting in the LS-OBL approach. This strategy plays a pivotal role in reducing the search space and maintaining population diversity within HGS, effectively augmenting the algorithm's exploration capabilities. The second adaptive strategy, the dynamic Rosenbrock Method (RM), contributes to HGS by adjusting the search direction and step size. This adjustment enables HGS to escape from suboptimal solutions and enhances its convergence accuracy. Combined, these two strategies form the improved algorithm proposed in this study, referred to as RLHGS. To assess the efficacy of the introduced strategies, specific experiments are designed to evaluate the impact of LS-OBL and RM on enhancing HGS performance. The experimental results unequivocally demonstrate that integrating these two strategies significantly enhances the capabilities of HGS. Furthermore, RLHGS is compared against eight state-of-the-art algorithms using 23 well-established benchmark functions and the CEC2020 test suite. The experimental results consistently indicate that RLHGS outperforms the other algorithms, securing the top rank in both test suites. This compelling evidence substantiates the superior functionality and performance of RLHGS compared to its counterparts. Moreover, RLHGS is applied to address four constrained real-world engineering optimization problems. The final results underscore the effectiveness of RLHGS in tackling such problems, further supporting its value as an efficient optimization method.

Deep Learning for Medical Image-Based Cancer Diagnosis.

(1) Background: The application of deep learning technology to realize cancer diagnosis based on medical images is one of the research hotspots in the field of artificial intelligence and computer vision. Due to the rapid development of deep learning methods, cancer diagnosis requires very high accuracy and timeliness as well as the inherent particularity and complexity of medical imaging. A comprehensive review of relevant studies is necessary to help readers better understand the current research status and ideas. (2) Methods: Five radiological images, including X-ray, ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission computed tomography (PET), and histopathological images, are reviewed in this paper. The basic architecture of deep learning and classical pretrained models are comprehensively reviewed. In particular, advanced neural networks emerging in recent years, including transfer learning, ensemble learning (EL), graph neural network, and vision transformer (ViT), are introduced. Five overfitting prevention methods are summarized: batch normalization, dropout, weight initialization, and data augmentation. The application of deep learning technology in medical image-based cancer analysis is sorted out. (3) Results: Deep learning has achieved great success in medical image-based cancer diagnosis, showing good results in image classification, image reconstruction, image detection, image segmentation, image registration, and image synthesis. However, the lack of high-quality labeled datasets limits the role of deep learning and faces challenges in rare cancer diagnosis, multi-modal image fusion, model explainability, and generalization. (4) Conclusions: There is a need for more public standard databases for cancer. The pre-training model based on deep neural networks has the potential to be improved, and special attention should be paid to the research of multimodal data fusion and supervised paradigm. Technologies such as ViT, ensemble learning, and few-shot learning will bring surprises to cancer diagnosis based on medical images.

Synergistic Integration of Skeletal Kinematic Features for Vision-Based Fall Detection.

According to the World Health Organisation, falling is a major health problem with potentially fatal implications. Each year, thousands of people die as a result of falls, with seniors making up 80% of these fatalities. The automatic detection of falls may reduce the severity of the consequences. Our study focuses on developing a vision-based fall detection system. Our work proposes a new feature descriptor that results in a new fall detection framework. The body geometry of the subject is analyzed and patterns that help to distinguish falls from non-fall activities are identified in our proposed method. An AlphaPose network is employed to identify 17 keypoints on the human skeleton. Thirteen keypoints are used in our study, and we compute two additional keypoints. These 15 keypoints are divided into five segments, each of which consists of a group of three non-collinear points. These five segments represent the left hand, right hand, left leg, right leg and craniocaudal section. A novel feature descriptor is generated by extracting the distances from the segmented parts, angles within the segmented parts and the angle of inclination for every segmented part. As a result, we may extract three features from each segment, giving us 15 features per frame that preserve spatial information. To capture temporal dynamics, the extracted spatial features are arranged in the temporal sequence. As a result, the feature descriptor in the proposed approach preserves the spatio-temporal dynamics. Thus, a feature descriptor of size [m×15] is formed where m is the number of frames. To recognize fall patterns, machine learning approaches such as decision trees, random forests, and gradient boost are applied to the feature descriptor. Our system was evaluated on the UPfall dataset, which is a benchmark dataset. It has shown very good performance compared to the state-of-the-art approaches.

Deep Learning and Vision Transformer for Medical Image Analysis.

Artificial intelligence (AI) refers to the field of computer science theory and technology [...].

A Survey of Convolutional Neural Network in Breast Cancer.

Problems: For people all over the world, cancer is one of the most feared diseases. Cancer is one of the major obstacles to improving life expectancy in countries around the world and one of the biggest causes of death before the age of 70 in 112 countries. Among all kinds of cancers, breast cancer is the most common cancer for women. The data showed that female breast cancer had become one of the most common cancers. Aims: A large number of clinical trials have proved that if breast cancer is diagnosed at an early stage, it could give patients more treatment options and improve the treatment effect and survival ability. Based on this situation, there are many diagnostic methods for breast cancer, such as computer-aided diagnosis (CAD). Methods: We complete a comprehensive review of the diagnosis of breast cancer based on the convolutional neural network (CNN) after reviewing a sea of recent papers. Firstly, we introduce several different imaging modalities. The structure of CNN is given in the second part. After that, we introduce some public breast cancer data sets. Then, we divide the diagnosis of breast cancer into three different tasks: 1. classification; 2. detection; 3. segmentation. Conclusion: Although this diagnosis with CNN has achieved great success, there are still some limitations. (i) There are too few good data sets. A good public breast cancer dataset needs to involve many aspects, such as professional medical knowledge, privacy issues, financial issues, dataset size, and so on. (ii) When the data set is too large, the CNN-based model needs a sea of computation and time to complete the diagnosis. (iii) It is easy to cause overfitting when using small data sets.

A Survey on Artificial Intelligence in Posture Recognition.

Over the years, the continuous development of new technology has promoted research in the field of posture recognition and also made the application field of posture recognition have been greatly expanded. The purpose of this paper is to introduce the latest methods of posture recognition and review the various techniques and algorithms of posture recognition in recent years, such as scale-invariant feature transform, histogram of oriented gradients, support vector machine (SVM), Gaussian mixture model, dynamic time warping, hidden Markov model (HMM), lightweight network, convolutional neural network (CNN). We also investigate improved methods of CNN, such as stacked hourglass networks, multi-stage pose estimation networks, convolutional pose machines, and high-resolution nets. The general process and datasets of posture recognition are analyzed and summarized, and several improved CNN methods and three main recognition techniques are compared. In addition, the applications of advanced neural networks in posture recognition, such as transfer learning, ensemble learning, graph neural networks, and explainable deep neural networks, are introduced. It was found that CNN has achieved great success in posture recognition and is favored by researchers. Still, a more in-depth research is needed in feature extraction, information fusion, and other aspects. Among classification methods, HMM and SVM are the most widely used, and lightweight network gradually attracts the attention of researchers. In addition, due to the lack of 3D benchmark data sets, data generation is a critical research direction.

Automated diagnosis of cardiovascular diseases from cardiac magnetic resonance imaging using deep learning models: A review.

In recent years, cardiovascular diseases (CVDs) have become one of the leading causes of mortality globally. At early stages, CVDs appear with minor symptoms and progressively get worse. The majority of people experience symptoms such as exhaustion, shortness of breath, ankle swelling, fluid retention, and other symptoms when starting CVD. Coronary artery disease (CAD), arrhythmia, cardiomyopathy, congenital heart defect (CHD), mitral regurgitation, and angina are the most common CVDs. Clinical methods such as blood tests, electrocardiography (ECG) signals, and medical imaging are the most effective methods used for the detection of CVDs. Among the diagnostic methods, cardiac magnetic resonance imaging (CMRI) is increasingly used to diagnose, monitor the disease, plan treatment and predict CVDs. Coupled with all the advantages of CMR data, CVDs diagnosis is challenging for physicians as each scan has many slices of data, and the contrast of it might be low. To address these issues, deep learning (DL) techniques have been employed in the diagnosis of CVDs using CMR data, and much research is currently being conducted in this field. This review provides an overview of the studies performed in CVDs detection using CMR images and DL techniques. The introduction section examined CVDs types, diagnostic methods, and the most important medical imaging techniques. The following presents research to detect CVDs using CMR images and the most significant DL methods. Another section discussed the challenges in diagnosing CVDs from CMRI data. Next, the discussion section discusses the results of this review, and future work in CVDs diagnosis from CMR images and DL techniques are outlined. Finally, the most important findings of this study are presented in the conclusion section.

Multiple-level thresholding for breast mass detection.

Detection of breast mass plays a very important role in making the diagnosis of breast cancer. For faster detection of breast cancer caused by breast mass, we developed a novel and efficient patch-based breast mass detection system for mammography images. The proposed framework is comprised of three modules, including pre-processing, multiple-level breast tissue segmentation, and final breast mass detection. An improved Deeplabv3+ model for pectoral muscle removal is deployed in pre-processing. We then proposed a multiple-level thresholding segmentation method to segment breast mass and obtained the connected components (ConCs), where the corresponding image patch to each ConC is extracted for mass detection. In the final detection stage, each image patch is classified into breast mass and breast tissue background by trained deep learning models. The patches that are classified as breast mass are then taken as the candidates for breast mass. To reduce the false positive rate in the detection results, we applied the non-maximum suppression algorithm to combine the overlapped detection results. Once an image patch is considered a breast mass, the accurate detection result can then be retrieved from the corresponding ConC in the segmented images. Moreover, a coarse segmentation result can be simultaneously retrieved after detection. Compared to the state-of-the-art methods, the proposed method achieved comparable performance. On CBIS-DDSM, the proposed method achieved a detection sensitivity of 0.87 at 2.86 FPI (False Positive rate per Image), while the sensitivity reached 0.96 on INbreast with an FPI of only 1.29.

Diagnosis of cerebral microbleed via VGG and extreme learning machine trained by Gaussian map bat algorithm.

Cerebral microbleed (CMB) is a serious public health concern. It is associated with dementia, which can be detected with brain magnetic resonance image (MRI). CMBs often appear as tiny round dots on MRIs, and they can be spotted anywhere over brain. Therefore, manual inspection is tedious and lengthy, and the results are often short in reproducible. In this paper, a novel automatic CMB diagnosis method was proposed based on deep learning and optimization algorithms, which used the brain MRI as the input and output the diagnosis results as CMB and non-CMB. Firstly, sliding window processing was employed to generate the dataset from brain MRIs. Then, a pre-trained VGG was employed to obtain the image features from the dataset. Finally, an ELM was trained by Gaussian-map bat algorithm (GBA) for identification. Results showed that the proposed method VGG-ELM-GBA provided better generalization performance than several state-of-the-art approaches.

A Multi-Directional Pixel-Swapping Approach (MPSA) for Entropy-Retained Reversible Data Hiding in Encrypted Images.

Reversible data hiding (RDH), a promising data-hiding technique, is widely examined in domains such as medical image transmission, satellite image transmission, crime investigation, cloud computing, etc. None of the existing RDH schemes addresses a solution from a real-time aspect. A good compromise between the information embedding rate and computational time makes the scheme suitable for real-time applications. As a solution, we propose a novel RDH scheme that recovers the original image by retaining its quality and extracting the hidden data. Here, the cover image gets encrypted using a stream cipher and is partitioned into non-overlapping blocks. Secret information is inserted into the encrypted blocks of the cover image via a controlled local pixel-swapping approach to achieve a comparatively good payload. The new scheme MPSA allows the data hider to hide two bits in every encrypted block. The existing reversible data-hiding schemes modify the encrypted image pixels leading to a compromise in image security. However, the proposed work complements the support of encrypted image security by maintaining the same entropy of the encrypted image in spite of hiding the data. Experimental results illustrate the competency of the proposed work accounting for various parameters, including embedding rate and computational time.

Bionic Artificial Neural Networks in Medical Image Analysis.

Bionic artificial neural networks (BANNs) are a type of artificial neural network (ANN) [...].