Background: Chest CT is used for the assessment of the severity of patients infected with novel coronavirus 2019 (COVID-19). We collected chest CT scans of 202 patients diagnosed with the COVID-19, and try to develop a rapid, accurate and automatic tool for severity screening follow-up therapeutic treatment.Methods: A total of 729 2D axial plan slices with 246 severe cases and 483 non-severe cases were employed in this study. By taking the advantages of the pre-trained deep neural network, four pre-trained off-the-shelf deep models (Inception-V3, ResNet-50, ResNet-101, DenseNet-201) were exploited to extract the features from these CT scans. These features are then fed to multiple classifiers (linear discriminant, linear SVM, cubic SVM, KNN and Adaboost decision tree) to identify the severe and non-severe COVID-19 cases. Three validation strategies (holdout validation, tenfold cross-validation and leave-one-out) are employed to validate the feasibility of proposed pipelines.Results and conclusion: The experimental results demonstrate that classification of the features from pre-trained deep models shows the promising application in COVID-19 severity screening, whereas the DenseNet-201 with cubic SVM model achieved the best performance. Specifically, it achieved the highest severity classification accuracy of 95.20% and 95.34% for tenfold cross-validation and leave-one-out, respectively. The established pipeline was able to achieve a rapid and accurate identification of the severity of COVID-19. This may assist the physicians to make more efficient and reliable decisions.

Human activity recognition is an imbalance classification problem in essence since various human actions may occur at different frequencies. Traditional ensemble class imbalance learning methods integrate resampling technique with multi-classifier models, which obtain better generalization than single ones. However, the number of base classifiers is often determined in advance, resulting in the redundant structure of a multi-classifier and larger computational cost. Moreover, various combinations of base classifiers may have similar recognition accuracy, forming a multimodel optimization problem. To address the issue, a dual-ensemble class imbalance learning method is presented, in which two ensemble learning models are nested each other. For each sub-dataset, three heterogeneous sub-classifiers compose of internal ensemble learning model, and the one with the highest recognition accuracy is selected as base classifier. In external ensemble learning model, an optimal combination that contains the smallest number of base classifiers and identifies human actions most exactly is found by multimodal evolutionary algorithms. Based on seven imbalanced activity datasets derived from localization data for person activity, statistical experimental results show that the proposed evolutionary dual-ensemble class imbalance learning method provides the simplest ensemble structure with the best accuracy for imbalanced data that outperforms other five widely-used ensemble classification methods on all metrics.

Purpose: The objective of this study is to construct a computer aided diagnosis system for normal people and pneumoconiosis using X-raysand deep learning algorithms. Materials and methods: 1760 anonymous digital X-ray images of real patients between January 2017 and June 2020 were collected for this experiment. In order to concentrate the feature extraction ability of the model more on the lung region and restrain the influence of external background factors, a two-stage pipeline from coarse to fine was established. First, the U-Net model was used to extract the lung regions on each sides of the collection images. Second, the ResNet-34 model with transfer learning strategy was implemented to learn the image features extracted in the lung region to achieve accurate classification of pneumoconiosis patients and normal people. Results: Among the 1760 cases collected, the accuracy and the area under curve of the classification model were 92.46% and 89% respectively. Conclusion: The successful application of deep learning in the diagnosis of pneumoconiosis further demonstrates the potential of medical artificial intelligence and proves the effectiveness of our proposed algorithm. However, when we further classified pneumoconiosis patients and normal subjects into four categories, we found that the overall accuracy decreased to 70.1%. We will use the CT modality in future studies to provide more details of lung regions.

Diabetic retinopathy (DR) is a leading cause of visual blindness. However if DR can be diagnosed and treated early, 90% of DR causing blindness can be prevented significantly. Microaneurysms (MAs) and exudates (EXs), as signs of DR, can be used for early DR diagnosis. However, MAs and EXs segmentation is a challenging task due to the low contrast of the lesions, the interference of noises, and the imbalance between the lesion areas and the background. In this paper, an enhanced residual U-Net (ERU-Net) for MAs and EXs segmentation is proposed. ERU-Net obtains three U-paths, which are composed by three upsampling paths together with one downsampling path. With such three U-paths structure, ERU-Net can enhance the corresponding features fusion and capture more details of fundus images. Also, a residual block is constructed in ERU-Net to extract more representative features. In the experiments, we evaluate the performance of ERU-Net for MAs and EXs segmentation on three public datasets, E-Ophtha, IDRiD, and DDR. The ERU-Net obtains the AUC values of 0.9956, 0.9962, 0.9801, 0.9866, 0.9679, 0.9609 for MAs and EXs segmentation on these three datasets, respectively, which are greater than that of the original U-Net. Compared with some traditional methods, convolutional neural networks and other recent U-Nets, ERU-Net also performs competitively. Besides, we have applied ERU-Net to segment optic disc (OD) on the DRISHTI-GS1 dataset, achieving the highest Jaccard index of 0.994 compared with the existing methods. The numerical results indicate that ERU-Net is a promising network for medical image segmentation.