SS-TBN: A Semi-Supervised Tri-Branch Network for COVID-19 Screening and Lesion Segmentation.

Insufficient annotated data and minor lung lesions pose big challenges for computed tomography (CT)-aided automatic COVID-19 diagnosis at an early outbreak stage. To address this issue, we propose a Semi-Supervised Tri-Branch Network (SS-TBN). First, we develop a joint TBN model for dual-task application scenarios of image segmentation and classification such as CT-based COVID-19 diagnosis, in which pixel-level lesion segmentation and slice-level infection classification branches are simultaneously trained via lesion attention, and individual-level diagnosis branch aggregates slice-level outputs for COVID-19 screening. Second, we propose a novel hybrid semi-supervised learning method to make full use of unlabeled data, combining a new double-threshold pseudo labeling method specifically designed to the joint model and a new inter-slice consistency regularization method specifically tailored to CT images. Besides two publicly available external datasets, we collect internal and our own external datasets including 210,395 images (1,420 cases versus 498 controls) from ten hospitals. Experimental results show that the proposed method achieves state-of-the-art performance in COVID-19 classification with limited annotated data even if lesions are subtle, and that segmentation results promote interpretability for diagnosis, suggesting the potential of the SS-TBN in early screening in insufficient labeled data situations at the early stage of a pandemic outbreak like COVID-19.

Subsequence and distant supervision based active learning for relation extraction of Chinese medical texts.

In recent years, relation extraction on unstructured texts has become an important task in medical research. However, relation extraction requires a large amount of labeled corpus, manually annotating sequences is time consuming and expensive. Therefore, efficient and economical methods for annotating sequences are required to ensure the performance of relational extraction. This paper proposes a method of subsequence and distant supervision based active learning. The method is annotated by selecting information-rich subsequences as a sampling unit instead of the full sentences in traditional active learning. Additionally, the method saves the labeled subsequence texts and their corresponding labels in a dictionary which is continuously updated and maintained, and pre-labels the unlabeled set through text matching based on the idea of distant supervision. Finally, the method combines a Chinese-RoBERTa-CRF model for relation extraction in Chinese medical texts. Experimental results test on the CMeIE dataset achieves the best performance compared to existing methods. And the best F1 value obtained between different sampling strategies is 55.96%.

Boosting automatic COVID-19 detection performance with self-supervised learning and batch knowledge ensembling.

PROBLEM: Detecting COVID-19 from chest X-ray (CXR) images has become one of the fastest and easiest methods for detecting COVID-19. However, the existing methods usually use supervised transfer learning from natural images as a pretraining process. These methods do not consider the unique features of COVID-19 and the similar features between COVID-19 and other pneumonia. AIM: In this paper, we want to design a novel high-accuracy COVID-19 detection method that uses CXR images, which can consider the unique features of COVID-19 and the similar features between COVID-19 and other pneumonia. METHODS: Our method consists of two phases. One is self-supervised learning-based pertaining; the other is batch knowledge ensembling-based fine-tuning. Self-supervised learning-based pretraining can learn distinguished representations from CXR images without manually annotated labels. On the other hand, batch knowledge ensembling-based fine-tuning can utilize category knowledge of images in a batch according to their visual feature similarities to improve detection performance. Unlike our previous implementation, we introduce batch knowledge ensembling into the fine-tuning phase, reducing the memory used in self-supervised learning and improving COVID-19 detection accuracy. RESULTS: On two public COVID-19 CXR datasets, namely, a large dataset and an unbalanced dataset, our method exhibited promising COVID-19 detection performance. Our method maintains high detection accuracy even when annotated CXR training images are reduced significantly (e.g., using only 10% of the original dataset). In addition, our method is insensitive to changes in hyperparameters. CONCLUSION: The proposed method outperforms other state-of-the-art COVID-19 detection methods in different settings. Our method can reduce the workloads of healthcare providers and radiologists.

Efficient Data-Driven Machine Learning Models for Cardiovascular Diseases Risk Prediction.

Cardiovascular diseases (CVDs) are now the leading cause of death, as the quality of life and human habits have changed significantly. CVDs are accompanied by various complications, including all pathological changes involving the heart and/or blood vessels. The list of pathological changes includes hypertension, coronary heart disease, heart failure, angina, myocardial infarction and stroke. Hence, prevention and early diagnosis could limit the onset or progression of the disease. Nowadays, machine learning (ML) techniques have gained a significant role in disease prediction and are an essential tool in medicine. In this study, a supervised ML-based methodology is presented through which we aim to design efficient prediction models for CVD manifestation, highlighting the SMOTE technique's superiority. Detailed analysis and understanding of risk factors are shown to explore their importance and contribution to CVD prediction. These factors are fed as input features to a plethora of ML models, which are trained and tested to identify the most appropriate for our objective under a binary classification problem with a uniform class probability distribution. Various ML models were evaluated after the use or non-use of Synthetic Minority Oversampling Technique (SMOTE), and comparing them in terms of Accuracy, Recall, Precision and an Area Under the Curve (AUC). The experiment results showed that the Stacking ensemble model after SMOTE with 10-fold cross-validation prevailed over the other ones achieving an Accuracy of 87.8%, Recall of 88.3%, Precision of 88% and an AUC equal to 98.2%.

Emotional Distress During COVID-19 by Mental Health Conditions and Economic Vulnerability: Retrospective Analysis of Survey-Linked Twitter Data With a Semisupervised Machine Learning Algorithm.

BACKGROUND: Monitoring the psychological conditions of social media users during rapidly developing public health crises, such as the COVID-19 pandemic, using their posts on social media has rapidly gained popularity as a relatively easy and cost-effective method. However, the characteristics of individuals who created these posts are largely unknown, making it difficult to identify groups of individuals most affected by such crises. In addition, large annotated data sets for mental health conditions are not easily available, and thus, supervised machine learning algorithms can be infeasible or too costly. OBJECTIVE: This study proposes a machine learning framework for the real-time surveillance of mental health conditions that does not require extensive training data. Using survey-linked tweets, we tracked the level of emotional distress during the COVID-19 pandemic by the attributes and psychological conditions of social media users in Japan. METHODS: We conducted online surveys of adults residing in Japan in May 2022 and collected their basic demographic information, socioeconomic status, and mental health conditions, along with their Twitter handles (N=2432). We computed emotional distress scores for all the tweets posted by the study participants between January 1, 2019, and May 30, 2022 (N=2,493,682) using a semisupervised algorithm called latent semantic scaling (LSS), with higher values indicating higher levels of emotional distress. After excluding users by age and other criteria, we examined 495,021 (19.85%) tweets generated by 560 (23.03%) individuals (age 18-49 years) in 2019 and 2020. We estimated fixed-effect regression models to examine their emotional distress levels in 2020 relative to the corresponding weeks in 2019 by the mental health conditions and characteristics of social media users. RESULTS: The estimated level of emotional distress of our study participants increased in the week when school closure started (March 2020), and it peaked at the beginning of the state of emergency (estimated coefficient=0.219, 95% CI 0.162-0.276) in early April 2020. Their level of emotional distress was unrelated to the number of COVID-19 cases. We found that the government-induced restrictions disproportionately affected the psychological conditions of vulnerable individuals, including those with low income, precarious employment, depressive symptoms, and suicidal ideation. CONCLUSIONS: This study establishes a framework to implement near-real-time monitoring of the emotional distress level of social media users, highlighting a great potential to continuously monitor their well-being using survey-linked social media posts as a complement to administrative and large-scale survey data. Given its flexibility and adaptability, the proposed framework is easily extendable for other purposes, such as detecting suicidality among social media users, and can be used on streaming data for continuous measurement of the conditions and sentiment of any group of interest.

FaxMatch: Multi-Curriculum Pseudo-Labeling for semi-supervised medical image classification.

BACKGROUND: Semi-supervised learning (SSL) can effectively use information from unlabeled data to improve model performance, which has great significance in medical imaging tasks. Pseudo-labeling is a classical SSL method that uses a model to predict unlabeled samples and selects the prediction with the highest confidence level as the pseudo-labels and then uses the generated pseudo-labels to train the model. Most of the current pseudo-label-based SSL algorithms use predefined fixed thresholds for all classes to select unlabeled data. PURPOSE: However, data imbalance is a common problem in medical image tasks, where the use of fixed threshold to generate pseudo-labels ignores different classes of learning status and learning difficulties. The aim of this study is to develop an algorithm to solve this problem. METHODS: In this work, we propose Multi-Curriculum Pseudo-Labeling (MCPL), which evaluates the learning status of the model for each class at each epoch and automatically adjusts the thresholds for each class. We apply MCPL to FixMatch and propose a new SSL framework for medical image classification, which we call the improved algorithm FaxMatch. To mitigate the impact of incorrect pseudo-labels on the model, we use label smoothing (LS) strategy to generate soft labels (SL) for pseudo-labels. RESULTS: We have conducted extensive experiments to evaluate our method on two public benchmark medical image classification datasets: the ISIC 2018 skin lesion analysis and COVID-CT datasets. Experimental results show that our method outperforms fully supervised baseline, which uses only labeled data to train the model. Moreover, our method also outperforms other state-of-the-art methods. CONCLUSIONS: We propose MCPL and construct a semi-supervised medical image classification framework to reduce the reliance of the model on a large number of labeled images and reduce the manual workload of labeling medical image data.

Supervised Machine Learning Models to Identify Early-Stage Symptoms of SARS-CoV-2.

The coronavirus disease (COVID-19) pandemic was caused by the SARS-CoV-2 virus and began in December 2019. The virus was first reported in the Wuhan region of China. It is a new strain of coronavirus that until then had not been isolated in humans. In severe cases, pneumonia, acute respiratory distress syndrome, multiple organ failure or even death may occur. Now, the existence of vaccines, antiviral drugs and the appropriate treatment are allies in the confrontation of the disease. In the present research work, we utilized supervised Machine Learning (ML) models to determine early-stage symptoms of SARS-CoV-2 occurrence. For this purpose, we experimented with several ML models, and the results showed that the ensemble model, namely Stacking, outperformed the others, achieving an Accuracy, Precision, Recall and F-Measure equal to 90.9% and an Area Under Curve (AUC) of 96.4%.

Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature With Unsupervised Word Embeddings and Machine Learning: Evidence-Based Study.

BACKGROUND: Evidence from peer-reviewed literature is the cornerstone for designing responses to global threats such as COVID-19. In massive and rapidly growing corpuses, such as COVID-19 publications, assimilating and synthesizing information is challenging. Leveraging a robust computational pipeline that evaluates multiple aspects, such as network topological features, communities, and their temporal trends, can make this process more efficient. OBJECTIVE: We aimed to show that new knowledge can be captured and tracked using the temporal change in the underlying unsupervised word embeddings of the literature. Further imminent themes can be predicted using machine learning on the evolving associations between words. METHODS: Frequently occurring medical entities were extracted from the abstracts of more than 150,000 COVID-19 articles published on the World Health Organization database, collected on a monthly interval starting from February 2020. Word embeddings trained on each month's literature were used to construct networks of entities with cosine similarities as edge weights. Topological features of the subsequent month's network were forecasted based on prior patterns, and new links were predicted using supervised machine learning. Community detection and alluvial diagrams were used to track biomedical themes that evolved over the months. RESULTS: We found that thromboembolic complications were detected as an emerging theme as early as August 2020. A shift toward the symptoms of long COVID complications was observed during March 2021, and neurological complications gained significance in June 2021. A prospective validation of the link prediction models achieved an area under the receiver operating characteristic curve of 0.87. Predictive modeling revealed predisposing conditions, symptoms, cross-infection, and neurological complications as dominant research themes in COVID-19 publications based on the patterns observed in previous months. CONCLUSIONS: Machine learning-based prediction of emerging links can contribute toward steering research by capturing themes represented by groups of medical entities, based on patterns of semantic relationships over time.

Predicting the behavioral intentions of hospice and palliative care providers from real-world data using supervised learning: A cross-sectional survey study.

Background: Hospice and palliative care (HPC) aims to improve end-of-life quality and has received much more attention through the lens of an aging population in the midst of the coronavirus disease pandemic. However, several barriers remain in China due to a lack of professional HPC providers with positive behavioral intentions. Therefore, we conducted an original study introducing machine learning to explore individual behavioral intentions and detect factors of enablers of, and barriers to, excavating potential human resources and improving HPC accessibility. Methods: A cross-sectional study was designed to investigate healthcare providers' behavioral intentions, knowledge, attitudes, and practices in hospice care (KAPHC) with an indigenized KAPHC scale. Binary Logistic Regression and Random Forest Classifier (RFC) were performed to model impacting and predict individual behavioral intentions. Results: The RFC showed high sensitivity (accuracy = 0.75; F1 score = 0.84; recall = 0.94). Attitude could directly or indirectly improve work enthusiasm and is the most efficient approach to reveal behavioral intentions. Continuous practice could also improve individual confidence and willingness to provide HPC. In addition, scientific knowledge and related skills were the foundation of implementing HPC. Conclusion: Individual behavioral intention is crucial for improving HPC accessibility, particularly at the initial stage. A well-trained RFC can help estimate individual behavioral intentions to organize a productive team and promote additional policies.

Outcome prediction during an ICU surge using a purely data-driven approach: A supervised machine learning case-study in critically ill patients from COVID-19 Lombardy outbreak.

PURPOSE: COVID-19 disease frequently affects the lungs leading to bilateral viral pneumonia, progressing in some cases to severe respiratory failure requiring ICU admission and mechanical ventilation. Risk stratification at ICU admission is fundamental for resource allocation and decision making. We assessed performances of three machine learning approaches to predict mortality in COVID-19 patients admitted to ICU using early operative data from the Lombardy ICU Network. METHODS: This is a secondary analysis of prospectively collected data from Lombardy ICU network. A logistic regression, balanced logistic regression and random forest were built to predict survival on two datasets: dataset A included patient demographics, medications before admission and comorbidities, and dataset B included respiratory data the first day in ICU. RESULTS: Models were trained on 1484 patients on four outcomes (7/14/21/28 days) and reached the greatest predictive performance at 28 days (F1-score: 0.75 and AUC: 0.80). Age, number of comorbidities and male gender were strongly associated with mortality. On dataset B, mode of ventilatory assistance at ICU admission and fraction of inspired oxygen were associated with an increase in prediction performances. CONCLUSIONS: Machine learning techniques might be useful in emergency phases to reach good predictive performances maintaining interpretability to gain knowledge on complex situations and enhance patient management and resources.

Active deep learning from a noisy teacher for semi-supervised 3D image segmentation: Application to COVID-19 pneumonia infection in CT.

Supervised deep learning has become a standard approach to solving medical image segmentation tasks. However, serious difficulties in attaining pixel-level annotations for sufficiently large volumetric datasets in real-life applications have highlighted the critical need for alternative approaches, such as semi-supervised learning, where model training can leverage small expert-annotated datasets to enable learning from much larger datasets without laborious annotation. Most of the semi-supervised approaches combine expert annotations and machine-generated annotations with equal weights within deep model training, despite the latter annotations being relatively unreliable and likely to affect model optimization negatively. To overcome this, we propose an active learning approach that uses an example re-weighting strategy, where machine-annotated samples are weighted (i) based on the similarity of their gradient directions of descent to those of expert-annotated data, and (ii) based on the gradient magnitude of the last layer of the deep model. Specifically, we present an active learning strategy with a query function that enables the selection of reliable and more informative samples from machine-annotated batch data generated by a noisy teacher. When validated on clinical COVID-19 CT benchmark data, our method improved the performance of pneumonia infection segmentation compared to the state of the art.

A training strategy for hybrid models to break the curse of dimensionality.

Mechanistic/data-driven hybrid modeling is a key approach when the mechanistic details of the processes at hand are not sufficiently well understood, but also inferring a model purely from data is too complex. By the integration of first principles into a data-driven approach, hybrid modeling promises a feasible data demand alongside extrapolation. In this work, we introduce a learning strategy for tree-structured hybrid models to perform a binary classification task. Given a set of binary labeled data, the challenge is to use them to develop a model that accurately assesses labels of new unlabeled data. Our strategy employs graph-theoretic methods to analyze the data and deduce a function that maps input features to output labels. Our focus here is on data sets represented by binary features in which the label assessment of unlabeled data points is always extrapolation. Our strategy shows the existence of small sets of data points within given binary data for which knowing the labels allows for extrapolation to the entire valid input space. An implementation of our strategy yields a notable reduction of training-data demand in a binary classification task compared with different supervised machine learning algorithms. As an application, we have fitted a tree-structured hybrid model to the vital status of a cohort of COVID-19 patients requiring intensive-care unit treatment and mechanical ventilation. Our learning strategy yields the existence of patient cohorts for whom knowing the vital status enables extrapolation to the entire valid input space of the developed hybrid model.

Semi-supervised COVID-19 CT image segmentation using deep generative models.

BACKGROUND: A recurring problem in image segmentation is a lack of labelled data. This problem is especially acute in the segmentation of lung computed tomography (CT) of patients with Coronavirus Disease 2019 (COVID-19). The reason for this is simple: the disease has not been prevalent long enough to generate a great number of labels. Semi-supervised learning promises a way to learn from data that is unlabelled and has seen tremendous advancements in recent years. However, due to the complexity of its label space, those advancements cannot be applied to image segmentation. That being said, it is this same complexity that makes it extremely expensive to obtain pixel-level labels, making semi-supervised learning all the more appealing. This study seeks to bridge this gap by proposing a novel model that utilizes the image segmentation abilities of deep convolution networks and the semi-supervised learning abilities of generative models for chest CT images of patients with the COVID-19. RESULTS: We propose a novel generative model called the shared variational autoencoder (SVAE). The SVAE utilizes a five-layer deep hierarchy of latent variables and deep convolutional mappings between them, resulting in a generative model that is well suited for lung CT images. Then, we add a novel component to the final layer of the SVAE which forces the model to reconstruct the input image using a segmentation that must match the ground truth segmentation whenever it is present. We name this final model StitchNet. CONCLUSION: We compare StitchNet to other image segmentation models on a high-quality dataset of CT images from COVID-19 patients. We show that our model has comparable performance to the other segmentation models. We also explore the potential limitations and advantages in our proposed algorithm and propose some potential future research directions for this challenging issue.

A regularization-driven Mean Teacher model based on semi-supervised learning for medical image segmentation.

Objective.A semi-supervised learning method is an essential tool for applying medical image segmentation. However, the existing semi-supervised learning methods rely heavily on the limited labeled data. The generalization performance of image segmentation is improved to reduce the need for the number of labeled samples and the difficulty of parameter tuning by extending the consistency regularization.Approach.We propose a new regularization-driven Mean Teacher model based on semi-supervised learning for medical image segmentation in this work. We introduce a regularization-driven strategy with virtual adversarial training to improve segmentation performance and the robustness of the Mean Teacher model. We optimize the unsupervised loss function and the regularization term with an entropy minimum to smooth the decision boundary.Main results.We extensively evaluate the proposed method on the International Skin Imaging Cooperation 2017(ISIC2017) and COVID-19 CT segmentation datasets. Our proposed approach gains more accurate results on challenging 2D images for semi-supervised medical image segmentation. Compared with the state-of-the-art methods, the proposed approach has significantly improved and is superior to other semi-supervised segmentation methods.Significance.The proposed approach can be extended to other medical segmentation tasks and can reduce the burden of physicians to some extent.

Semi-Supervised Adversarial Learning Using LSTM for Human Activity Recognition.

The training of Human Activity Recognition (HAR) models requires a substantial amount of labeled data. Unfortunately, despite being trained on enormous datasets, most current models have poor performance rates when evaluated against anonymous data from new users. Furthermore, due to the limits and problems of working with human users, capturing adequate data for each new user is not feasible. This paper presents semi-supervised adversarial learning using the LSTM (Long-short term memory) approach for human activity recognition. This proposed method trains annotated and unannotated data (anonymous data) by adapting the semi-supervised learning paradigms on which adversarial learning capitalizes to improve the learning capabilities in dealing with errors that appear in the process. Moreover, it adapts to the change in human activity routine and new activities, i.e., it does not require prior understanding and historical information. Simultaneously, this method is designed as a temporal interactive model instantiation and shows the capacity to estimate heteroscedastic uncertainty owing to inherent data ambiguity. Our methodology also benefits from multiple parallel input sequential data predicting an output exploiting the synchronized LSTM. The proposed method proved to be the best state-of-the-art method with more than 98% accuracy in implementation utilizing the publicly available datasets collected from the smart home environment facilitated with heterogeneous sensors. This technique is a novel approach for high-level human activity recognition and is likely to be a broad application prospect for HAR.

A Self Supervised StyleGAN for Image Annotation and Classification With Extremely Limited Labels.

The recent success of learning-based algorithms can be greatly attributed to the immense amount of annotated data used for training. Yet, many datasets lack annotations due to the high costs associated with labeling, resulting in degraded performances of deep learning methods. Self-supervised learning is frequently adopted to mitigate the reliance on massive labeled datasets since it exploits unlabeled data to learn relevant feature representations. In this work, we propose SS-StyleGAN, a self-supervised approach for image annotation and classification suitable for extremely small annotated datasets. This novel framework adds self-supervision to the StyleGAN architecture by integrating an encoder that learns the embedding to the StyleGAN latent space, which is well-known for its disentangled properties. The learned latent space enables the smart selection of representatives from the data to be labeled for improved classification performance. We show that the proposed method attains strong classification results using small labeled datasets of sizes 50 and even 10. We demonstrate the superiority of our approach for the tasks of COVID-19 and liver tumor pathology identification.

Using Explainable Supervised Machine Learning to Predict Burnout in Healthcare Professionals.

Burnout in healthcare professionals (HCPs) is a multi-factorial problem. There are limited studies utilizing machine learning approaches to predict HCPs' burnout during the COVID-19 pandemic. A survey consisting of demographic characteristics and work system factors was administered to 450 HCPs during the pandemic (participation rate: 59.3%). The highest performing machine learning model had an area under the receiver operating curve of 0.81. The eight key features that best predicted burnout are excessive workload, inadequate staffing, administrative burden, professional relationships, organizational culture, values and expectations, intrinsic motivation, and work-life integration. These findings provide evidence for resource allocation and implementation of interventions to reduce HCPs' burnout and improve the quality of care.

WVALE: Weak variational autoencoder for localisation and enhancement of COVID-19 lung infections.

BACKGROUND AND OBJECTIVE: The COVID-19 pandemic is a major global health crisis of this century. The use of neural networks with CT imaging can potentially improve clinicians' efficiency in diagnosis. Previous studies in this field have primarily focused on classifying the disease on CT images, while few studies targeted the localisation of disease regions. Developing neural networks for automating the latter task is impeded by limited CT images with pixel-level annotations available to the research community. METHODS: This paper proposes a weakly-supervised framework named "Weak Variational Autoencoder for Localisation and Enhancement" (WVALE) to address this challenge for COVID-19 CT images. This framework includes two components: anomaly localisation with a novel WVAE model and enhancement of supervised segmentation models with WVALE. RESULTS: The WVAE model have been shown to produce high-quality post-hoc attention maps with fine borders around infection regions, while weak supervision segmentation shows results comparable to conventional supervised segmentation models. The WVALE framework can enhance the performance of a range of supervised segmentation models, including state-of-art models for the segmentation of COVID-19 lung infection. CONCLUSIONS: Our study provides a proof-of-concept for weakly supervised segmentation and an alternative approach to alleviate the lack of annotation, while its independence from classification & segmentation frameworks makes it easily integrable with existing systems.

SSA-Net: Spatial self-attention network for COVID-19 pneumonia infection segmentation with semi-supervised few-shot learning.

Coronavirus disease (COVID-19) broke out at the end of 2019, and has resulted in an ongoing global pandemic. Segmentation of pneumonia infections from chest computed tomography (CT) scans of COVID-19 patients is significant for accurate diagnosis and quantitative analysis. Deep learning-based methods can be developed for automatic segmentation and offer a great potential to strengthen timely quarantine and medical treatment. Unfortunately, due to the urgent nature of the COVID-19 pandemic, a systematic collection of CT data sets for deep neural network training is quite difficult, especially high-quality annotations of multi-category infections are limited. In addition, it is still a challenge to segment the infected areas from CT slices because of the irregular shapes and fuzzy boundaries. To solve these issues, we propose a novel COVID-19 pneumonia lesion segmentation network, called Spatial Self-Attention network (SSA-Net), to identify infected regions from chest CT images automatically. In our SSA-Net, a self-attention mechanism is utilized to expand the receptive field and enhance the representation learning by distilling useful contextual information from deeper layers without extra training time, and spatial convolution is introduced to strengthen the network and accelerate the training convergence. Furthermore, to alleviate the insufficiency of labeled multi-class data and the long-tailed distribution of training data, we present a semi-supervised few-shot iterative segmentation framework based on re-weighting the loss and selecting prediction values with high confidence, which can accurately classify different kinds of infections with a small number of labeled image data. Experimental results show that SSA-Net outperforms state-of-the-art medical image segmentation networks and provides clinically interpretable saliency maps, which are useful for COVID-19 diagnosis and patient triage. Meanwhile, our semi-supervised iterative segmentation model can improve the learning ability in small and unbalanced training set and can achieve higher performance.

TSRNet: Diagnosis of COVID-19 based on self-supervised learning and hybrid ensemble model.

BACKGROUND: As of Feb 27, 2022, coronavirus (COVID-19) has caused 434,888,591 infections and 5,958,849 deaths worldwide, dealing a severe blow to the economies and cultures of most countries around the world. As the virus has mutated, its infectious capacity has further increased. Effective diagnosis of suspected cases is an important tool to stop the spread of the pandemic. Therefore, we intended to develop a computer-aided diagnosis system for the diagnosis of suspected cases. METHODS: To address the shortcomings of commonly used pre-training methods and exploit the information in unlabeled images, we proposed a new pre-training method based on transfer learning with self-supervised learning (TS). After that, a new convolutional neural network based on attention mechanism and deep residual network (RANet) was proposed to extract features. Based on this, a hybrid ensemble model (TSRNet) was proposed for classifying lung CT images of suspected patients as COVID-19 and normal. RESULTS: Compared with the existing five models in terms of accuracy (DarkCOVIDNet: 98.08%; Deep-COVID: 97.58%; NAGNN: 97.86%; COVID-ResNet: 97.78%; Patch-based CNN: 88.90%), TSRNet has the highest accuracy of 99.80%. In addition, the recall, f1-score, and AUC of the model reached 99.59%, 99.78%, and 1, respectively. CONCLUSION: TSRNet can effectively diagnose suspected COVID-19 cases with the help of the information in unlabeled and labeled images, thus helping physicians to adopt early treatment plans for confirmed cases.