4S-DT: Self-Supervised Super Sample Decomposition for Transfer Learning With Application to COVID-19 Detection

Evaluating Neural Network Performance in Predicting Disease Status and Tissue Source of JC Polyomavirus from Patient Isolates Based on the Hypervariable Region of the Viral Genome

JC polyomavirus (JCPyV) establishes a persistent, asymptomatic kidney infection in most of the population. However, JCPyV can reactivate in immunocompromised individuals and cause progressive multifocal leukoencephalopathy (PML), a fatal demyelinating disease with no approved treatment. Mutations in the hypervariable non-coding control region (NCCR) of the JCPyV genome have been linked to disease outcomes and neuropathogenesis, yet few metanalyses document these associations. Many online sequence entries, including those on NCBI databases, lack sufficient sample information, limiting large-scale analyses of NCCR sequences. Machine learning techniques, however, can augment available data for analysis. This study employs a previously compiled dataset of 989 JCPyV NCCR sequences from GenBank with associated patient PML status and viral tissue source to train multilayer perceptrons for predicting missing information within the dataset. The PML status and tissue source models were 100% and 87.8% accurate, respectively. Within the dataset, 348 samples had an unconfirmed PML status, where 259 were predicted as No PML and 89 as PML sequences. Of the 63 sequences with unconfirmed tissue sources, eight samples were predicted as urine, 13 as blood, and 42 as cerebrospinal fluid. These models can improve viral sequence identification and provide insights into viral mutations and pathogenesis.

MiniSeg: An Extremely Minimum Network Based on Lightweight Multiscale Learning for Efficient COVID-19 Segmentation

The rapid spread of the new pandemic, i.e., coronavirus disease 2019 (COVID-19), has severely threatened global health. Deep-learning-based computer-aided screening, e.g., COVID-19 infected area segmentation from computed tomography (CT) image, has attracted much attention by serving as an adjunct to increase the accuracy of COVID-19 screening and clinical diagnosis. Although lesion segmentation is a hot topic, traditional deep learning methods are usually data-hungry with millions of parameters, easy to overfit under limited available COVID-19 training data. On the other hand, fast training/testing and low computational cost are also necessary for quick deployment and development of COVID-19 screening systems, but traditional methods are usually computationally intensive. To address the above two problems, we propose MiniSeg, a lightweight model for efficient COVID-19 segmentation from CT images. Our efforts start with the design of an attentive hierarchical spatial pyramid (AHSP) module for lightweight, efficient, effective multiscale learning that is essential for image segmentation. Then, we build a two-path (TP) encoder for deep feature extraction, where one path uses AHSP modules for learning multiscale contextual features and the other is a shallow convolutional path for capturing fine details. The two paths interact with each other for learning effective representations. Based on the extracted features, a simple decoder is added for COVID-19 segmentation. For comparing MiniSeg to previous methods, we build a comprehensive COVID-19 segmentation benchmark. Extensive experiments demonstrate that the proposed MiniSeg achieves better accuracy because its only 83k parameters make it less prone to overfitting. Its high efficiency also makes it easy to deploy and develop. The code has been released at https://github.com/yun-liu/MiniSeg.

Decoupled Unbiased Teacher for Source-Free Domain Adaptive Medical Object Detection

Source-free domain adaptation (SFDA) aims to adapt a lightweight pretrained source model to unlabeled new domains without the original labeled source data. Due to the privacy of patients and storage consumption concerns, SFDA is a more practical setting for building a generalized model in medical object detection. Existing methods usually apply the vanilla pseudo-labeling technique, while neglecting the bias issues in SFDA, leading to limited adaptation performance. To this end, we systematically analyze the biases in SFDA medical object detection by constructing a structural causal model (SCM) and propose an unbiased SFDA framework dubbed decoupled unbiased teacher (DUT). Based on the SCM, we derive that the confounding effect causes biases in the SFDA medical object detection task at the sample level, feature level, and prediction level. To prevent the model from emphasizing easy object patterns in the biased dataset, a dual invariance assessment (DIA) strategy is devised to generate counterfactual synthetics. The synthetics are based on unbiased invariant samples in both discrimination and semantic perspectives. To alleviate overfitting to domain-specific features in SFDA, we design a cross-domain feature intervention (CFI) module to explicitly deconfound the domain-specific prior with feature intervention and obtain unbiased features. Besides, we establish a correspondence supervision prioritization (CSP) strategy for addressing the prediction bias caused by coarse pseudo-labels by sample prioritizing and robust box supervision. Through extensive experiments on multiple SFDA medical object detection scenarios, DUT yields superior performance over previous state-of-the-art unsupervised domain adaptation (UDA) and SFDA counterparts, demonstrating the significance of addressing the bias issues in this challenging task. The code is available at https://github.com/CUHK-AIM-Group/Decoupled-Unbiased-Teacher.

Self-supervised learning for medical image classification: a systematic review and implementation guidelines

Advancements in deep learning and computer vision provide promising solutions for medical image analysis, potentially improving healthcare and patient outcomes. However, the prevailing paradigm of training deep learning models requires large quantities of labeled training data, which is both time-consuming and cost-prohibitive to curate for medical images. Self-supervised learning has the potential to make significant contributions to the development of robust medical imaging models through its ability to learn useful insights from copious medical datasets without labels. In this review, we provide consistent descriptions of different self-supervised learning strategies and compose a systematic review of papers published between 2012 and 2022 on PubMed, Scopus, and ArXiv that applied self-supervised learning to medical imaging classification. We screened a total of 412 relevant studies and included 79 papers for data extraction and analysis. With this comprehensive effort, we synthesize the collective knowledge of prior work and provide implementation guidelines for future researchers interested in applying self-supervised learning to their development of medical imaging classification models.

Automated Quantification of Pneumonia Infected Volume in Lung CT Images: A Comparison with Subjective Assessment of Radiologists

OBJECTIVE

To help improve radiologists' efficacy of disease diagnosis in reading computed tomography (CT) images, this study aims to investigate the feasibility of applying a modified deep learning (DL) method as a new strategy to automatically segment disease-infected regions and predict disease severity.

METHODS

We employed a public dataset acquired from 20 COVID-19 patients, which includes manually annotated lung and infections masks, to train a new ensembled DL model that combines five customized residual attention U-Net models to segment disease infected regions followed by a Feature Pyramid Network model to predict disease severity stage. To test the potential clinical utility of the new DL model, we conducted an observer comparison study. First, we collected another set of CT images acquired from 80 COVID-19 patients and process images using the new DL model. Second, we asked two chest radiologists to read images of each CT scan and report the estimated percentage of the disease-infected lung volume and disease severity level. Third, we also asked radiologists to rate acceptance of DL model-generated segmentation results using a 5-scale rating method.

RESULTS

Data analysis results show that agreement of disease severity classification between the DL model and radiologists is >90% in 45 testing cases. Furthermore, >73% of cases received a high rating score (≥4) from two radiologists.

CONCLUSION

This study demonstrates the feasibility of developing a new DL model to automatically segment disease-infected regions and quantitatively predict disease severity, which may help avoid tedious effort and inter-reader variability in subjective assessment of disease severity in future clinical practice.

A comprehensive survey of deep learning research on medical image analysis with focus on transfer learning

This survey aims to identify commonly used methods, datasets, future trends, knowledge gaps, constraints, and limitations in the field to provide an overview of current solutions used in medical image analysis in parallel with the rapid developments in transfer learning (TL). Unlike previous studies, this survey grouped the last five years of current studies for the period between January 2017 and February 2021 according to different anatomical regions and detailed the modality, medical task, TL method, source data, target data, and public or private datasets used in medical imaging. Also, it provides readers with detailed information on technical challenges, opportunities, and future research trends. In this way, an overview of recent developments is provided to help researchers to select the most effective and efficient methods and access widely used and publicly available medical datasets, research gaps, and limitations of the available literature.

Review on the Evaluation and Development of Artificial Intelligence for COVID-19 Containment

Artificial intelligence has significantly enhanced the research paradigm and spectrum with a substantiated promise of continuous applicability in the real world domain. Artificial intelligence, the driving force of the current technological revolution, has been used in many frontiers, including education, security, gaming, finance, robotics, autonomous systems, entertainment, and most importantly the healthcare sector. With the rise of the COVID-19 pandemic, several prediction and detection methods using artificial intelligence have been employed to understand, forecast, handle, and curtail the ensuing threats. In this study, the most recent related publications, methodologies and medical reports were investigated with the purpose of studying artificial intelligence's role in the pandemic. This study presents a comprehensive review of artificial intelligence with specific attention to machine learning, deep learning, image processing, object detection, image segmentation, and few-shot learning studies that were utilized in several tasks related to COVID-19. In particular, genetic analysis, medical image analysis, clinical data analysis, sound analysis, biomedical data classification, socio-demographic data analysis, anomaly detection, health monitoring, personal protective equipment (PPE) observation, social control, and COVID-19 patients' mortality risk approaches were used in this study to forecast the threatening factors of COVID-19. This study demonstrates that artificial-intelligence-based algorithms integrated into Internet of Things wearable devices were quite effective and efficient in COVID-19 detection and forecasting insights which were actionable through wide usage. The results produced by the study prove that artificial intelligence is a promising arena of research that can be applied for disease prognosis, disease forecasting, drug discovery, and to the development of the healthcare sector on a global scale. We prove that artificial intelligence indeed played a significantly important role in helping to fight against COVID-19, and the insightful knowledge provided here could be extremely beneficial for practitioners and research experts in the healthcare domain to implement the artificial-intelligence-based systems in curbing the next pandemic or healthcare disaster.

XDecompo: Explainable Decomposition Approach in Convolutional Neural Networks for Tumour Image Classification

Of the various tumour types, colorectal cancer and brain tumours are still considered among the most serious and deadly diseases in the world. Therefore, many researchers are interested in improving the accuracy and reliability of diagnostic medical machine learning models. In computer-aided diagnosis, self-supervised learning has been proven to be an effective solution when dealing with datasets with insufficient data annotations. However, medical image datasets often suffer from data irregularities, making the recognition task even more challenging. The class decomposition approach has provided a robust solution to such a challenging problem by simplifying the learning of class boundaries of a dataset. In this paper, we propose a robust self-supervised model, called XDecompo, to improve the transferability of features from the pretext task to the downstream task. XDecompo has been designed based on an affinity propagation-based class decomposition to effectively encourage learning of the class boundaries in the downstream task. XDecompo has an explainable component to highlight important pixels that contribute to classification and explain the effect of class decomposition on improving the speciality of extracted features. We also explore the generalisability of XDecompo in handling different medical datasets, such as histopathology for colorectal cancer and brain tumour images. The quantitative results demonstrate the robustness of XDecompo with high accuracy of 96.16% and 94.30% for CRC and brain tumour images, respectively. XDecompo has demonstrated its generalization capability and achieved high classification accuracy (both quantitatively and qualitatively) in different medical image datasets, compared with other models. Moreover, a post hoc explainable method has been used to validate the feature transferability, demonstrating highly accurate feature representations.

COVID-19 diagnosis via chest X-ray image classification based on multiscale class residual attention

Aiming at detecting COVID-19 effectively, a multiscale class residual attention (MCRA) network is proposed via chest X-ray (CXR) image classification. First, to overcome the data shortage and improve the robustness of our network, a pixel-level image mixing of local regions was introduced to achieve data augmentation and reduce noise. Secondly, multi-scale fusion strategy was adopted to extract global contextual information at different scales and enhance semantic representation. Last but not least, class residual attention was employed to generate spatial attention for each class, which can avoid inter-class interference and enhance related features to further improve the COVID-19 detection. Experimental results show that our network achieves superior diagnostic performance on COVIDx dataset, and its accuracy, PPV, sensitivity, specificity and F1-score are 97.71%, 96.76%, 96.56%, 98.96% and 96.64%, respectively; moreover, the heat maps can endow our deep model with somewhat interpretability.

Self-Supervised Autoregressive Domain Adaptation for Time Series Data

Unsupervised domain adaptation (UDA) has successfully addressed the domain shift problem for visual applications. Yet, these approaches may have limited performance for time series data due to the following reasons. First, they mainly rely on the large-scale dataset (i.e., ImageNet) for source pretraining, which is not applicable for time series data. Second, they ignore the temporal dimension on the feature space of the source and target domains during the domain alignment step. Finally, most of the prior UDA methods can only align the global features without considering the fine-grained class distribution of the target domain. To address these limitations, we propose a SeLf-supervised AutoRegressive Domain Adaptation (SLARDA) framework. In particular, we first design a self-supervised (SL) learning module that uses forecasting as an auxiliary task to improve the transferability of source features. Second, we propose a novel autoregressive domain adaptation technique that incorporates temporal dependence of both source and target features during domain alignment. Finally, we develop an ensemble teacher model to align class-wise distribution in the target domain via a confident pseudo labeling approach. Extensive experiments have been conducted on three real-world time series applications with 30 cross-domain scenarios. The results demonstrate that our proposed SLARDA method significantly outperforms the state-of-the-art approaches for time series domain adaptation. Our source code is available at: https://github.com/mohamedr002/SLARDA.

Investigating the Performance of FixMatch for COVID-19 Detection in Chest X-rays

The advent of the COVID-19 pandemic has resulted in medical resources being stretched to their limits. Chest X-rays are one method of diagnosing COVID-19; they are used due to their high efficacy. However, detecting COVID-19 manually by using these images is time-consuming and expensive. While neural networks can be trained to detect COVID-19, doing so requires large amounts of labeled data, which are expensive to collect and code. One approach is to use semi-supervised neural networks to detect COVID-19 based on a very small number of labeled images. This paper explores how well such an approach could work. The FixMatch algorithm, which is a state-of-the-art semi-supervised classification algorithm, was trained on chest X-rays to detect COVID-19, Viral Pneumonia, Bacterial Pneumonia and Lung Opacity. The model was trained with decreasing levels of labeled data and compared with the best supervised CNN models, using transfer learning. FixMatch was able to achieve a COVID F1-score of 0.94 with only 80 labeled samples per class and an overall macro-average F1-score of 0.68 with only 20 labeled samples per class. Furthermore, an exploratory analysis was conducted to determine the performance of FixMatch to detect COVID-19 when trained with imbalanced data. The results show a predictable drop in performance as compared to training with uniform data; however, a statistical analysis suggests that FixMatch may be somewhat robust to data imbalance, as in many cases, and the same types of mistakes are made when the amount of labeled data is decreased.

A Time-Series Self-Supervised Learning Approach to Detection of Cyber-physical Attacks in Water Distribution Systems

Water Distribution System (WDS) threats have significantly grown following the Maroochy shire incident, as evidenced by proofed attacks on water premises. As a result, in addition to traditional solutions (e.g., data encryption and authentication), attack detection is being proposed in WDS to reduce disruption cases. The attack detection system must meet two critical requirements: high accuracy and near real-time detection. This drives us to propose a two-stage detection system that uses self-supervised and unsupervised algorithms to detect Cyber-Physical (CP) attacks. Stage 1 uses heuristic adaptive self-supervised algorithms to achieve near real-time decision-making and detection sensitivity of 66% utilizing Boss. Stage 2 attempts to validate the detection of attacks using an unsupervised algorithm to maintain a detection accuracy of 94% utilizing Isolation Forest. Both stages are examined against time granularity and are empirically analyzed against a variety of performance evaluation indicators. Our findings demonstrate that the algorithms in stage 1 are less favored than those in the literature, but their existence enables near real-time decision-making and detection reliability. In stage 2, the isolation Forest algorithm, in contrast, gives excellent accuracy. As a result, both stages can collaborate to maximize accuracy in a near real-time attack detection system.

Role of Artificial Intelligence in COVID-19 Detection

The global pandemic of coronavirus disease (COVID-19) has caused millions of deaths and affected the livelihood of many more people. Early and rapid detection of COVID-19 is a challenging task for the medical community, but it is also crucial in stopping the spread of the SARS-CoV-2 virus. Prior substantiation of artificial intelligence (AI) in various fields of science has encouraged researchers to further address this problem. Various medical imaging modalities including X-ray, computed tomography (CT) and ultrasound (US) using AI techniques have greatly helped to curb the COVID-19 outbreak by assisting with early diagnosis. We carried out a systematic review on state-of-the-art AI techniques applied with X-ray, CT, and US images to detect COVID-19. In this paper, we discuss approaches used by various authors and the significance of these research efforts, the potential challenges, and future trends related to the implementation of an AI system for disease detection during the COVID-19 pandemic.

COVID-19 Diagnosis Using Capsule Network and Fuzzy C-Means and Mayfly Optimization Algorithm

The COVID-19 epidemic is spreading day by day. Early diagnosis of this disease is essential to provide effective preventive and therapeutic measures. This process can be used by a computer-aided methodology to improve accuracy. In this study, a new and optimal method has been utilized for the diagnosis of COVID-19. Here, a method based on fuzzy C-ordered means (FCOM) along with an improved version of the enhanced capsule network (ECN) has been proposed for this purpose. The proposed ECN method is improved based on mayfly optimization (MFO) algorithm. The suggested technique is then implemented on the chest X-ray COVID-19 images from publicly available datasets. Simulation results are assessed by considering a comparison with some state-of-the-art methods, including FOMPA, MID, and 4S-DT. The results show that the proposed method with 97.08% accuracy and 97.29% precision provides the highest accuracy and reliability compared with the other studied methods. Moreover, the results show that the proposed method with a 97.1% sensitivity rate has the highest ratio. And finally, the proposed method with a 97.47% F1-score rate gives the uppermost value compared to the others.

A Comprehensive Survey of COVID-19 Detection Using Medical Images

The outbreak of the Coronavirus disease 2019 (COVID-19) caused the death of a large number of people and declared as a pandemic by the World Health Organization. Millions of people are infected by this virus and are still getting infected every day. As the cost and required time of conventional Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests to detect COVID-19 is uneconomical and excessive, researchers are trying to use medical images such as X-ray and Computed Tomography (CT) images to detect this disease with the help of Artificial Intelligence (AI)-based systems, to assist in automating the scanning procedure. In this paper, we reviewed some of these newly emerging AI-based models that can detect COVID-19 from X-ray or CT of lung images. We collected information about available research resources and inspected a total of 80 papers till June 20, 2020. We explored and analyzed data sets, preprocessing techniques, segmentation methods, feature extraction, classification, and experimental results which can be helpful for finding future research directions in the domain of automatic diagnosis of COVID-19 disease using AI-based frameworks. It is also reflected that there is a scarcity of annotated medical images/data sets of COVID-19 affected people, which requires enhancing, segmentation in preprocessing, and domain adaptation in transfer learning for a model, producing an optimal result in model performance. This survey can be the starting point for a novice/beginner level researcher to work on COVID-19 classification.

Quantum Machine Learning Architecture for COVID-19 Classification Based on Synthetic Data Generation Using Conditional Adversarial Neural Network

Background

COVID-19 is a novel virus that affects the upper respiratory tract, as well as the lungs. The scale of the global COVID-19 pandemic, its spreading rate, and deaths are increasing regularly. Computed tomography (CT) scans can be used carefully to detect and analyze COVID-19 cases. In CT images/scans, ground-glass opacity (GGO) is found in the early stages of infection. While in later stages, there is a superimposed pulmonary consolidation.

Methods

This research investigates the quantum machine learning (QML) and classical machine learning (CML) approaches for the analysis of COVID-19 images. The recent developments in quantum computing have led researchers to explore new ideas and approaches using QML. The proposed approach consists of two phases: in phase I, synthetic CT images are generated through the conditional adversarial network (CGAN) to increase the size of the dataset for accurate training and testing. In phase II, the classification of COVID-19/healthy images is performed, in which two models are proposed: CML and QML.

Result

The proposed model achieved 0.94 precision (Pn), 0.94 accuracy (Ac), 0.94 recall (Rl), and 0.94 F1-score (Fe) on POF Hospital dataset while 0.96 Pn, 0.96 Ac, 0.95 Rl, and 0.96 Fe on UCSD-AI4H dataset.

Conclusion

The proposed method achieved better results when compared to the latest published work in this domain.

AI-Empowered Computational Examination of Chest Imaging for COVID-19 Treatment: A Review

Since the first case of coronavirus disease 2019 (COVID-19) was discovered in December 2019, COVID-19 swiftly spread over the world. By the end of March 2021, more than 136 million patients have been infected. Since the second and third waves of the COVID-19 outbreak are in full swing, investigating effective and timely solutions for patients' check-ups and treatment is important. Although the SARS-CoV-2 virus-specific reverse transcription polymerase chain reaction test is recommended for the diagnosis of COVID-19, the test results are prone to be false negative in the early course of COVID-19 infection. To enhance the screening efficiency and accessibility, chest images captured via X-ray or computed tomography (CT) provide valuable information when evaluating patients with suspected COVID-19 infection. With advanced artificial intelligence (AI) techniques, AI-driven models training with lung scans emerge as quick diagnostic and screening tools for detecting COVID-19 infection in patients. In this article, we provide a comprehensive review of state-of-the-art AI-empowered methods for computational examination of COVID-19 patients with lung scans. In this regard, we searched for papers and preprints on bioRxiv, medRxiv, and arXiv published for the period from January 1, 2020, to March 31, 2021, using the keywords of COVID, lung scans, and AI. After the quality screening, 96 studies are included in this review. The reviewed studies were grouped into three categories based on their target application scenarios: automatic detection of coronavirus disease, infection segmentation, and severity assessment and prognosis prediction. The latest AI solutions to process and analyze chest images for COVID-19 treatment and their advantages and limitations are presented. In addition to reviewing the rapidly developing techniques, we also summarize publicly accessible lung scan image sets. The article ends with discussions of the challenges in current research and potential directions in designing effective computational solutions to fight against the COVID-19 pandemic in the future.