High-dimensional multinomial multiclass severity scoring of COVID-19 pneumonia using CT radiomics features and machine learning algorithms

Differential privacy preserved federated learning for prognostic modeling in COVID-19 patients using large multi-institutional chest CT dataset

BACKGROUND

Notwithstanding the encouraging results of previous studies reporting on the efficiency of deep learning (DL) in COVID-19 prognostication, clinical adoption of the developed methodology still needs to be improved. To overcome this limitation, we set out to predict the prognosis of a large multi-institutional cohort of patients with COVID-19 using a DL-based model.

PURPOSE

This study aimed to evaluate the performance of deep privacy-preserving federated learning (DPFL) in predicting COVID-19 outcomes using chest CT images.

METHODS

After applying inclusion and exclusion criteria, 3055 patients from 19 centers, including 1599 alive and 1456 deceased, were enrolled in this study. Data from all centers were split (randomly with stratification respective to each center and class) into a training/validation set (70%/10%) and a hold-out test set (20%). For the DL model, feature extraction was performed on 2D slices, and averaging was performed at the final layer to construct a 3D model for each scan. The DensNet model was used for feature extraction. The model was developed using centralized and FL approaches. For FL, we employed DPFL approaches. Membership inference attack was also evaluated in the FL strategy. For model evaluation, different metrics were reported in the hold-out test sets. In addition, models trained in two scenarios, centralized and FL, were compared using the DeLong test for statistical differences.

RESULTS

The centralized model achieved an accuracy of 0.76, while the DPFL model had an accuracy of 0.75. Both the centralized and DPFL models achieved a specificity of 0.77. The centralized model achieved a sensitivity of 0.74, while the DPFL model had a sensitivity of 0.73. A mean AUC of 0.82 and 0.81 with 95% confidence intervals of (95% CI: 0.79-0.85) and (95% CI: 0.77-0.84) were achieved by the centralized model and the DPFL model, respectively. The DeLong test did not prove statistically significant differences between the two models (p-value = 0.98). The AUC values for the inference attacks fluctuate between 0.49 and 0.51, with an average of 0.50 ± 0.003 and 95% CI for the mean AUC of 0.500 to 0.501.

CONCLUSION

The performance of the proposed model was comparable to centralized models while operating on large and heterogeneous multi-institutional datasets. In addition, the model was resistant to inference attacks, ensuring the privacy of shared data during the training process.

Towards Improved XAI-Based Epidemiological Research into the Next Potential Pandemic

By applying AI techniques to a variety of pandemic-relevant data, artificial intelligence (AI) has substantially supported the control of the spread of the SARS-CoV-2 virus. Along with this, epidemiological machine learning studies of SARS-CoV-2 have been frequently published. While these models can be perceived as precise and policy-relevant to guide governments towards optimal containment policies, their black box nature can hamper building trust and relying confidently on the prescriptions proposed. This paper focuses on interpretable AI-based epidemiological models in the context of the recent SARS-CoV-2 pandemic. We systematically review existing studies, which jointly incorporate AI, SARS-CoV-2 epidemiology, and explainable AI approaches (XAI). First, we propose a conceptual framework by synthesizing the main methodological features of the existing AI pipelines of SARS-CoV-2. Upon the proposed conceptual framework and by analyzing the selected epidemiological studies, we reflect on current research gaps in epidemiological AI toolboxes and how to fill these gaps to generate enhanced policy support in the next potential pandemic.

Classification performance assessment for imbalanced multiclass data

The evaluation of diagnostic systems is pivotal for ensuring the deployment of high-quality solutions, especially given the pronounced context-sensitivity of certain systems, particularly in fields such as biomedicine. Of notable importance are predictive models where the target variable can encompass multiple values (multiclass), especially when these classes exhibit substantial frequency disparities (imbalance). In this study, we introduce the Imbalanced Multiclass Classification Performance (IMCP) curve, specifically designed for multiclass datasets (unlike the ROC curve), and characterized by its resilience to class distribution variations (in contrast to accuracy or Fβ -score). Moreover, the IMCP curve facilitates individual performance assessment for each class within the diagnostic system, shedding light on the confidence associated with each prediction-an aspect of particular significance in medical diagnosis. Empirical experiments conducted with real-world data in a multiclass context (involving 35 types of tumors) featuring a high level of imbalance demonstrate that both the IMCP curve and the area under the IMCP curve serve as excellent indicators of classification quality.

Left Ventricular Myocardial Dysfunction Evaluation in Thalassemia Patients Using Echocardiographic Radiomic Features and Machine Learning Algorithms

Heart failure caused by iron deposits in the myocardium is the primary cause of mortality in beta-thalassemia major patients. Cardiac magnetic resonance imaging (CMRI) T2* is the primary screening technique used to detect myocardial iron overload, but inherently bears some limitations. In this study, we aimed to differentiate beta-thalassemia major patients with myocardial iron overload from those without myocardial iron overload (detected by T2*CMRI) based on radiomic features extracted from echocardiography images and machine learning (ML) in patients with normal left ventricular ejection fraction (LVEF > 55%) in echocardiography. Out of 91 cases, 44 patients with thalassemia major with normal LVEF (> 55%) and T2* ≤ 20 ms and 47 people with LVEF > 55% and T2* > 20 ms as the control group were included in the study. Radiomic features were extracted for each end-systolic (ES) and end-diastolic (ED) image. Then, three feature selection (FS) methods and six different classifiers were used. The models were evaluated using various metrics, including the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE). Maximum relevance-minimum redundancy-eXtreme gradient boosting (MRMR-XGB) (AUC = 0.73, ACC = 0.73, SPE = 0.73, SEN = 0.73), ANOVA-MLP (AUC = 0.69, ACC = 0.69, SPE = 0.56, SEN = 0.83), and recursive feature elimination-K-nearest neighbors (RFE-KNN) (AUC = 0.65, ACC = 0.65, SPE = 0.64, SEN = 0.65) were the best models in ED, ES, and ED&ES datasets. Using radiomic features extracted from echocardiographic images and ML, it is feasible to predict cardiac problems caused by iron overload.

Time-to-event overall survival prediction in glioblastoma multiforme patients using magnetic resonance imaging radiomics

PURPOSE

Glioblastoma Multiforme (GBM) represents the predominant aggressive primary tumor of the brain with short overall survival (OS) time. We aim to assess the potential of radiomic features in predicting the time-to-event OS of patients with GBM using machine learning (ML) algorithms.

MATERIALS AND METHODS

One hundred nineteen patients with GBM, who had T1-weighted contrast-enhanced and T2-FLAIR MRI sequences, along with clinical data and survival time, were enrolled. Image preprocessing methods included 64 bin discretization, Laplacian of Gaussian (LOG) filters with three Sigma values and eight variations of Wavelet Transform. Images were then segmented, followed by the extraction of 1212 radiomic features. Seven feature selection (FS) methods and six time-to-event ML algorithms were utilized. The combination of preprocessing, FS, and ML algorithms (12 × 7 × 6 = 504 models) was evaluated by multivariate analysis.

RESULTS

Our multivariate analysis showed that the best prognostic FS/ML combinations are the Mutual Information (MI)/Cox Boost, MI/Generalized Linear Model Boosting (GLMB) and MI/Generalized Linear Model Network (GLMN), all of which were done via the LOG (Sigma = 1 mm) preprocessing method (C-index = 0.77). The LOG filter with Sigma = 1 mm preprocessing method, MI, GLMB and GLMN achieved significantly higher C-indices than other preprocessing, FS, and ML methods (all p values < 0.05, mean C-indices of 0.65, 0.70, and 0.64, respectively).

CONCLUSION

ML algorithms are capable of predicting the time-to-event OS of patients using MRI-based radiomic and clinical features. MRI-based radiomics analysis in combination with clinical variables might appear promising in assisting clinicians in the survival prediction of patients with GBM. Further research is needed to establish the applicability of radiomics in the management of GBM in the clinic.

An AI-powered patient triage platform for future viral outbreaks using COVID-19 as a disease model

Over the last century, outbreaks and pandemics have occurred with disturbing regularity, necessitating advance preparation and large-scale, coordinated response. Here, we developed a machine learning predictive model of disease severity and length of hospitalization for COVID-19, which can be utilized as a platform for future unknown viral outbreaks. We combined untargeted metabolomics on plasma data obtained from COVID-19 patients (n = 111) during hospitalization and healthy controls (n = 342), clinical and comorbidity data (n = 508) to build this patient triage platform, which consists of three parts: (i) the clinical decision tree, which amongst other biomarkers showed that patients with increased eosinophils have worse disease prognosis and can serve as a new potential biomarker with high accuracy (AUC = 0.974), (ii) the estimation of patient hospitalization length with ± 5 days error (R2 = 0.9765) and (iii) the prediction of the disease severity and the need of patient transfer to the intensive care unit. We report a significant decrease in serotonin levels in patients who needed positive airway pressure oxygen and/or were intubated. Furthermore, 5-hydroxy tryptophan, allantoin, and glucuronic acid metabolites were increased in COVID-19 patients and collectively they can serve as biomarkers to predict disease progression. The ability to quickly identify which patients will develop life-threatening illness would allow the efficient allocation of medical resources and implementation of the most effective medical interventions. We would advocate that the same approach could be utilized in future viral outbreaks to help hospitals triage patients more effectively and improve patient outcomes while optimizing healthcare resources.

Improve the performance of CT-based pneumonia classification via source data reweighting

Pneumonia is a life-threatening disease. Computer tomography (CT) imaging is broadly used for diagnosing pneumonia. To assist radiologists in accurately and efficiently detecting pneumonia from CT scans, many deep learning methods have been developed. These methods require large amounts of annotated CT scans, which are difficult to obtain due to privacy concerns and high annotation costs. To address this problem, we develop a three-level optimization based method which leverages CT data from a source domain to mitigate the lack of labeled CT scans in a target domain. Our method automatically identifies and downweights low-quality source CT data examples which are noisy or have large domain discrepancy with target data, by minimizing the validation loss of a target model trained on reweighted source data. On a target dataset with 2218 CT scans and a source dataset with 349 CT images, our method achieves an F1 score of 91.8% in detecting pneumonia and an F1 score of 92.4% in detecting other types of pneumonia, which are significantly better than those achieved by state-of-the-art baseline methods.

Dynamic learning for imbalanced data in learning chest X-ray and CT images

Massive annotated datasets are necessary for networks of deep learning. When a topic is being researched for the first time, as in the situation of the viral epidemic, handling it with limited annotated datasets might be difficult. Additionally, the datasets are quite unbalanced in this situation, with limited findings coming from significant instances of the novel illness. We offer a technique that allows a class balancing algorithm to understand and detect lung disease signs from chest X-ray and CT images. Deep learning techniques are used to train and evaluate images, enabling the extraction of basic visual attributes. The training objects' characteristics, instances, categories, and relative data modeling are all represented probabilistically. It is possible to identify a minority category in the classification process by using an imbalance-based sample analyzer. In order to address the imbalance problem, learning samples from the minority class are examined. The Support Vector Machine (SVM) is used to categorize images in clustering. Physicians and medical professionals can use the CNN model to validate their initial assessments of malignant and benign categorization. The proposed technique for class imbalance (3-Phase Dynamic Learning (3PDL)) and parallel CNN model (Hybrid Feature Fusion (HFF)) for multiple modalities achieve a high F1 score of 96.83 and precision is 96.87, its outstanding accuracy and generalization suggest that it may be utilized to create a pathologist's help tool.

Swin-textural: A novel textural features-based image classification model for COVID-19 detection on chest computed tomography

Background

Chest computed tomography (CT) has a high sensitivity for detecting COVID-19 lung involvement and is widely used for diagnosis and disease monitoring. We proposed a new image classification model, swin-textural, that combined swin-based patch division with textual feature extraction for automated diagnosis of COVID-19 on chest CT images. The main objective of this work is to evaluate the performance of the swin architecture in feature engineering.

Material and method

We used a public dataset comprising 2167, 1247, and 757 (total 4171) transverse chest CT images belonging to 80, 80, and 50 (total 210) subjects with COVID-19, other non-COVID lung conditions, and normal lung findings. In our model, resized 420 × 420 input images were divided using uniform square patches of incremental dimensions, which yielded ten feature extraction layers. At each layer, local binary pattern and local phase quantization operations extracted textural features from individual patches as well as the undivided input image. Iterative neighborhood component analysis was used to select the most informative set of features to form ten selected feature vectors and also used to select the 11th vector from among the top selected feature vectors with accuracy >97.5%. The downstream kNN classifier calculated 11 prediction vectors. From these, iterative hard majority voting generated another nine voted prediction vectors. Finally, the best result among the twenty was determined using a greedy algorithm.

Results

Swin-textural attained 98.71% three-class classification accuracy, outperforming published deep learning models trained on the same dataset. The model has linear time complexity.

Conclusions

Our handcrafted computationally lightweight swin-textural model can detect COVID-19 accurately on chest CT images with low misclassification rates. The model can be implemented in hospitals for efficient automated screening of COVID-19 on chest CT images. Moreover, findings demonstrate that our presented swin-textural is a self-organized, highly accurate, and lightweight image classification model and is better than the compared deep learning models for this dataset.

Two-step machine learning to diagnose and predict involvement of lungs in COVID-19 and pneumonia using CT radiomics

OBJECTIVE

To develop a two-step machine learning (ML) based model to diagnose and predict involvement of lungs in COVID-19 and non COVID-19 pneumonia patients using CT chest radiomic features.

METHODS

Three hundred CT scans (3-classes: 100 COVID-19, 100 pneumonia, and 100 healthy subjects) were enrolled in this study. Diagnostic task included 3-class classification. Severity prediction score for COVID-19 and pneumonia was considered as mild (0-25%), moderate (26-50%), and severe (>50%). Whole lungs were segmented utilizing deep learning-based segmentation. Altogether, 107 features including shape, first-order histogram, second and high order texture features were extracted. Pearson correlation coefficient (PCC≥90%) followed by different features selection algorithms were employed. ML-based supervised algorithms (Naïve Bays, Support Vector Machine, Bagging, Random Forest, K-nearest neighbors, Decision Tree and Ensemble Meta voting) were utilized. The optimal model was selected based on precision, recall and area-under-curve (AUC) by randomizing the training/validation, followed by testing using the test set.

RESULTS

Nine pertinent features (2 shape, 1 first-order, and 6 second-order) were obtained after features selection for both phases. In diagnostic task, the performance of 3-class classification using Random Forest was 0.909±0.026, 0.907±0.056, 0.902±0.044, 0.939±0.031, and 0.982±0.010 for precision, recall, F1-score, accuracy, and AUC, respectively. The severity prediction task using Random Forest achieved 0.868±0.123 precision, 0.865±0.121 recall, 0.853±0.139 F1-score, 0.934±0.024 accuracy, and 0.969±0.022 AUC.

CONCLUSION

The two-phase ML-based model accurately classified COVID-19 and pneumonia patients using CT radiomics, and adequately predicted severity of lungs involvement. This 2-steps model showed great potential in assessing COVID-19 CT images towards improved management of patients.