MAMA Net: Multi-Scale Attention Memory Autoencoder Network for Anomaly Detection

LMTTM-VMI: Linked Memory Token Turing Machine for 3D volumetric medical image classification

Biomedical imaging is vital for the diagnosis and treatment of various medical conditions, yet the effective integration of deep learning technologies into this field presents challenges. Traditional methods often struggle to efficiently capture the spatial characteristics and intricate structural features of 3D volumetric medical images, limiting memory utilization and model adaptability. To address this, we introduce a Linked Memory Token Turing Machine (LMTTM), which utilizes external linked memory to efficiently process spatial dependencies and structural complexities within 3D volumetric medical images, aiding in accurate diagnoses. LMTTM can efficiently record the features of 3D volumetric medical images in an external linked memory module, enhancing complex image classification through improved feature accumulation and reasoning capabilities. Our experiments on six 3D volumetric medical image datasets from the MedMNIST v2 demonstrate that our proposed LMTTM model achieves average ACC of 82.4%, attaining state-of-the-art (SOTA) performance. Moreover, ablation studies confirmed that the Linked Memory outperforms its predecessor, TTM's original Memory, by up to 5.7%, highlighting LMTTM's effectiveness in 3D volumetric medical image classification and its potential to assist healthcare professionals in diagnosis and treatment planning. The code is released at https://github.com/hongkai-wei/LMTTM-VMI.

A GRU-CNN model for auditory attention detection using microstate and recurrence quantification analysis

Attention as a cognition ability plays a crucial role in perception which helps humans to concentrate on specific objects of the environment while discarding others. In this paper, auditory attention detection (AAD) is investigated using different dynamic features extracted from multichannel electroencephalography (EEG) signals when listeners attend to a target speaker in the presence of a competing talker. To this aim, microstate and recurrence quantification analysis are utilized to extract different types of features that reflect changes in the brain state during cognitive tasks. Then, an optimized feature set is determined by employing the processes of significant feature selection based on classification performance. The classifier model is developed by hybrid sequential learning that employs Gated Recurrent Units (GRU) and Convolutional Neural Network (CNN) into a unified framework for accurate attention detection. The proposed AAD method shows that the selected feature set achieves the most discriminative features for the classification process. Also, it yields the best performance as compared with state-of-the-art AAD approaches from the literature in terms of various measures. The current study is the first to validate the use of microstate and recurrence quantification parameters to differentiate auditory attention using reinforcement learning without access to stimuli.

Self-Supervised Multi-Scale Cropping and Simple Masked Attentive Predicting for Lung CT-Scan Anomaly Detection

Anomaly detection has been widely explored by training an out-of-distribution detector with only normal data for medical images. However, detecting local and subtle irregularities without prior knowledge of anomaly types brings challenges for lung CT-scan image anomaly detection. In this paper, we propose a self-supervised framework for learning representations of lung CT-scan images via both multi-scale cropping and simple masked attentive predicting, which is capable of constructing a powerful out-of-distribution detector. Firstly, we propose CropMixPaste, a self-supervised augmentation task for generating density shadow-like anomalies that encourage the model to detect local irregularities of lung CT-scan images. Then, we propose a self-supervised reconstruction block, named simple masked attentive predicting block (SMAPB), to better refine local features by predicting masked context information. Finally, the learned representations by self-supervised tasks are used to build an out-of-distribution detector. The results on real lung CT-scan datasets demonstrate the effectiveness and superiority of our proposed method compared with state-of-the-art methods.

Deep Cascade-Learning Model via Recurrent Attention for Immunofixation Electrophoresis Image Analysis

Immunofixation Electrophoresis (IFE) analysis has been an indispensable prerequisite for the diagnosis of M-protein, which is an important criterion to recognize diversified plasma cell diseases. Existing intelligent methods of IFE diagnosis commonly employ a single unified classifier to directly classify whether M-protein exists and which isotype of M-protein is. However, this unified classification is not optimal because the two tasks have different characteristics and require different feature extraction techniques. Classifying the M-protein existence depends on the presence or absence of dense bands in IFE data, while classifying the M-protein isotype depends on the location of dense bands. Consequently, a cascading two-classifier framework suitable to the two tasks respectively may achieve better performance. In this paper, we propose a novel deep cascade-learning model, which sequentially integrates a positive-negative classifier based on deep collocative learning and an isotype classifier based on recurrent attention model to address these two tasks respectively. Specifically, the attention mechanism can mimic the visual perception of clinicians, where only the most informative local regions are extracted through sequential partial observations. This not only avoids the interference of redundant regions but also saves computational power. Further, domain knowledge about SP lane and heavy-light-chain lanes is also introduced to assist our attention location. Extensive numerical experiments show that our deep cascade-learning outperforms state-of-the-art methods on recognized evaluation metrics and can effectively capture the co-location of dense bands in different lanes.

A Method for Image Anomaly Detection Based on Distillation and Reconstruction

Image anomaly detection is a trending research topic in computer vision. The objective is to build models using available normal samples to detect various abnormal images without depending on real abnormal samples. It has high research significance and value for applications in the detection of defects in product appearance, medical image analysis, hyperspectral image processing, and other fields. This paper proposes an image anomaly detection algorithm based on feature distillation and an autoencoder structure, which uses the feature distillation structure of a dual-teacher network to train the encoder, thus suppressing the reconstruction of abnormal regions. This system also introduces an attention mechanism to highlight the detection objects, achieving effective detection of different defects in product appearance. In addition, this paper proposes a method for anomaly evaluation based on patch similarity that calculates the difference between the reconstructed image and the input image according to different regions of the image, thus improving the sensitivity and accuracy of the anomaly score. This paper conducts experiments on several datasets, and the results show that the proposed algorithm has superior performance in image anomaly detection. It achieves 98.8% average AUC on the SMDC-DET dataset and 98.9% average AUC on the MVTec-AD dataset.

Self-supervised anomaly detection, staging and segmentation for retinal images

Unsupervised anomaly detection (UAD) is to detect anomalies through learning the distribution of normal data without labels and therefore has a wide application in medical images by alleviating the burden of collecting annotated medical data. Current UAD methods mostly learn the normal data by the reconstruction of the original input, but often lack the consideration of any prior information that has semantic meanings. In this paper, we first propose a universal unsupervised anomaly detection framework SSL-AnoVAE, which utilizes a self-supervised learning (SSL) module for providing more fine-grained semantics depending on the to-be detected anomalies in the retinal images. We also explore the relationship between the data transformation adopted in the SSL module and the quality of anomaly detection for retinal images. Moreover, to take full advantage of the proposed SSL-AnoVAE and apply towards clinical usages for computer-aided diagnosis of retinal-related diseases, we further propose to stage and segment the anomalies in retinal images detected by SSL-AnoVAE in an unsupervised manner. Experimental results demonstrate the effectiveness of our proposed method for unsupervised anomaly detection, staging and segmentation on both retinal optical coherence tomography images and color fundus photograph images.

D-BIN: A Generalized Disentangling Batch Instance Normalization for Domain Adaptation

Pattern recognition is significantly challenging in real-world scenarios by the variability of visual statistics. Therefore, most existing algorithms relying on the independent identically distributed assumption of training and test data suffer from the poor generalization capability of inference on unseen testing datasets. Although numerous studies, including domain discriminator or domain-invariant feature learning, are proposed to alleviate this problem, the data-driven property and lack of interpretation of their principle throw researchers and developers off. Consequently, this dilemma incurs us to rethink the essence of networks' generalization. An observation that visual patterns cannot be discriminative after style transfer inspires us to take careful consideration of the importance of style features and content features. Does the style information related to the domain bias? How to effectively disentangle content and style features across domains? In this article, we first investigate the effect of feature normalization on domain adaptation. Based on it, we propose a novel normalization module to adaptively leverage the propagated information through each channel and batch of features called disentangling batch instance normalization (D-BIN). In this module, we explicitly explore domain-specific and domaininvariant feature disentanglement. We maneuver contrastive learning to encourage images with the same semantics from different domains to have similar content representations while having dissimilar style representations. Furthermore, we construct both self-form and dual-form regularizers for preserving the mutual information (MI) between feature representations of the normalization layer in order to compensate for the loss of discriminative information and effectively match the distributions across domains. D-BIN and the constrained term can be simply plugged into state-of-the-art (SOTA) networks to improve their performance. In the end, experiments, including domain adaptation and generalization, conducted on different datasets have proven their effectiveness.

Unsupervised anomaly detection in brain MRI: Learning abstract distribution from massive healthy brains

PURPOSE

To develop a general unsupervised anomaly detection method based only on MR images of normal brains to automatically detect various brain abnormalities.

MATERIALS AND METHODS

In this study, a novel method based on three-dimensional deep autoencoder network is proposed to automatically detect and segment various brain abnormalities without being trained on any abnormal samples. A total of 578 normal T2w MR volumes without obvious abnormalities were used for model training and validation. The proposed 3D autoencoder was evaluated on two different datasets (BraTs dataset and in-house dataset) containing T2w volumes from patients with glioblastoma, multiple sclerosis and cerebral infarction. Lesions detection and segmentation performance were reported as AUC, precision-recall curve, sensitivity, and Dice score.

RESULTS

In anomaly detection, AUCs for three typical lesions were as follows: glioblastoma, 0.844; multiple sclerosis, 0.858; cerebral infarction, 0.807. In anomaly segmentation, the mean Dice for glioblastomas was 0.462. The proposed network also has the ability to generate an anomaly heatmap for visualization purpose.

CONCLUSION

Our proposed method was able to automatically detect various brain anomalies such as glioblastoma, multiple sclerosis, and cerebral infarction. This work suggests that unsupervised anomaly detection is a powerful approach to detect arbitrary brain abnormalities without labeled samples. It has the potential to support diagnostic workflow in radiology as an automated tool for computer-aided image analysis.

Spatial-contextual variational autoencoder with attention correction for anomaly detection in retinal OCT images

Anomaly detection refers to leveraging only normal data to train a model for identifying unseen abnormal cases, which is extensively studied in various fields. Most previous methods are based on reconstruction models, and use anomaly score calculated by the reconstruction error as the metric to tackle anomaly detection. However, these methods just employ single constraint on latent space to construct reconstruction model, resulting in limited performance in anomaly detection. To address this problem, we propose a Spatial-Contextual Variational Autoencoder with Attention Correction for anomaly detection in retinal OCT images. Specifically, we first propose a self-supervised segmentation network to extract retinal regions, which can effectively eliminate interference of background regions. Next, by introducing both multi-dimensional and one-dimensional latent space, our proposed framework can then learn the spatial and contextual manifolds of normal images, which is conducive to enlarging the difference between reconstruction errors of normal images and those of abnormal ones. Furthermore, an ablation-based method is proposed to localize anomalous regions by computing the importance of feature maps, which is used to correct anomaly score calculated by reconstruction error. Finally, a novel anomaly score is constructed to separate the abnormal images from the normal ones. Extensive experiments on two retinal OCT datasets are conducted to evaluate our proposed method, and the experimental results demonstrate the effectiveness of our approach.

A new classification network for diagnosing Alzheimer's disease in class-imbalance MRI datasets

Automatic identification of Alzheimer's Disease (AD) through magnetic resonance imaging (MRI) data can effectively assist to doctors diagnose and treat Alzheimer's. Current methods improve the accuracy of AD recognition, but they are insufficient to address the challenge of small interclass and large intraclass differences. Some studies attempt to embed patch-level structure in neural networks which enhance pathologic details, but the enormous size and time complexity render these methods unfavorable. Furthermore, several self-attention mechanisms fail to provide contextual information to represent discriminative regions, which limits the performance of these classifiers. In addition, the current loss function is adversely affected by outliers of class imbalance and may fall into local optimal values. Therefore, we propose a 3D Residual RepVGG Attention network (ResRepANet) stacked with several lightweight blocks to identify the MRI of brain disease, which can also trade off accuracy and flexibility. Specifically, we propose a Non-local Context Spatial Attention block (NCSA) and embed it in our proposed ResRepANet, which aggregates global contextual information in spatial features to improve semantic relevance in discriminative regions. In addition, in order to reduce the influence of outliers, we propose a Gradient Density Multiple-weighting Mechanism (GDMM) to automatically adjust the weights of each MRI image via a normalizing gradient norm. Experiments are conducted on datasets from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and Australian Imaging, Biomarker and Lifestyle Flagship Study of Aging (AIBL). Experiments on both datasets show that the accuracy, sensitivity, specificity, and Area Under the Curve are consistently better than for state-of-the-art methods.

A Review of Pharmaceutical Robot based on Hyperspectral Technology

The quality and safety of medicinal products are related to patients’ lives and health. Therefore, quality inspection takes a key role in the pharmaceutical industry. Most of the previous solutions are based on machine vision, however, their performance is limited by the RGB sensor. The pharmaceutical visual inspection robot combined with hyperspectral imaging technology is becoming a new trend in the high-end medical quality inspection process since the hyperspectral data can provide spectral information with spatial knowledge. Yet, there is no comprehensive review about hyperspectral imaging-based medicinal products inspection. This paper focuses on the pivotal pharmaceutical applications, including counterfeit drugs detection, active component analysis of tables, and quality testing of herbal medicines and other medical materials. We discuss the technology and hardware of Raman spectroscopy and hyperspectral imaging, firstly. Furthermore, we review these technologies in pharmaceutical scenarios. Finally, the development tendency and prospect of hyperspectral imaging technology-based robots in the field of pharmaceutical quality inspection is summarized.

FCF: Feature complement fusion network for detecting COVID-19 through CT scan images

COVID-19 spreads and contracts people rapidly, to diagnose this disease accurately and timely is essential for quarantine and medical treatment. RT-PCR plays a crucial role in diagnosing the COVID-19, whereas computed tomography (CT) delivers a faster result when combining artificial assistance. Developing a Deep Learning classification model for detecting the COVID-19 through CT images is conducive to assisting doctors in consultation. We proposed a feature complement fusion network (FCF) for detecting COVID-19 through lung CT scan images. This framework can extract both local features and global features by CNN extractor and ViT extractor severally, which successfully complement the deficiency problem of the receptive field of the other. Due to the attention mechanism in our designed feature complement Transformer (FCT), extracted local and global feature embeddings achieve a better representation. We combined a supervised with a weakly supervised strategy to train our model, which can promote CNN to guide the VIT to converge faster. Finally, we got a 99.34% accuracy on our test set, which surpasses the current state-of-art popular classification model. Moreover, this proposed structure can easily extend to other classification tasks when changing other proper extractors.

Attention Autoencoder for Generative Latent Representational Learning in Anomaly Detection

Today, accurate and automated abnormality diagnosis and identification have become of paramount importance as they are involved in many critical and life-saving scenarios. To accomplish such frontiers, we propose three artificial intelligence models through the application of deep learning algorithms to analyze and detect anomalies in human heartbeat signals. The three proposed models include an attention autoencoder that maps input data to a lower-dimensional latent representation with maximum feature retention, and a reconstruction decoder with minimum remodeling loss. The autoencoder has an embedded attention module at the bottleneck to learn the salient activations of the encoded distribution. Additionally, a variational autoencoder (VAE) and a long short-term memory (LSTM) network is designed to learn the Gaussian distribution of the generative reconstruction and time-series sequential data analysis. The three proposed models displayed outstanding ability to detect anomalies on the evaluated five thousand electrocardiogram (ECG5000) signals with 99% accuracy and 99.3% precision score in detecting healthy heartbeats from patients with severe congestive heart failure.

The COVID-19 epidemic analysis and diagnosis using deep learning: A systematic literature review and future directions

Since December 2019, the COVID-19 outbreak has resulted in countless deaths and has harmed all facets of human existence. COVID-19 has been designated an epidemic by the World Health Organization (WHO), which has placed a tremendous burden on nearly all countries, especially those with weak health systems. However, Deep Learning (DL) has been applied in several applications and many types of detection applications in the medical field, including thyroid diagnosis, lung nodule recognition, fetal localization, and detection of diabetic retinopathy. Furthermore, various clinical imaging sources, like Magnetic Resonance Imaging (MRI), X-ray, and Computed Tomography (CT), make DL a perfect technique to tackle the epidemic of COVID-19. Inspired by this fact, a considerable amount of research has been done. A Systematic Literature Review (SLR) has been used in this study to discover, assess, and integrate findings from relevant studies. DL techniques used in COVID-19 have also been categorized into seven main distinct categories as Long Short Term Memory Networks (LSTM), Self-Organizing Maps (SOMs), Conventional Neural Networks (CNNs), Generative Adversarial Networks (GANs), Recurrent Neural Networks (RNNs), Autoencoders, and hybrid approaches. Then, the state-of-the-art studies connected to DL techniques and applications for health problems with COVID-19 have been highlighted. Moreover, many issues and problems associated with DL implementation for COVID-19 have been addressed, which are anticipated to stimulate more investigations to control the prevalence and disaster control in the future. According to the findings, most papers are assessed using characteristics such as accuracy, delay, robustness, and scalability. Meanwhile, other features are underutilized, such as security and convergence time. Python is also the most commonly used language in papers, accounting for 75% of the time. According to the investigation, 37.83% of applications have identified chest CT/chest X-ray images for patients.