An intelligent detection method for plasmodium based on self-supervised learning and attention mechanism.

Background: Malaria remains a severe life-threatening disease caused by plasmodium parasites. Microscopy is widely used for malaria diagnosis. However, it relies heavily on the skills and experience of inspectors. Due to low-level medical services and the lack of skilled inspectors, misdiagnoses are frequently made in some areas. Methods: In recent years, many successful applications of CNN models have been reported. Unlike images in the ImageNet, the image of plasmodium only has a tiny defect area with a large amount of information. In addition, the dataset is extremely unbalanced: the number of positive samples is much less than that of negative samples. This paper proposes a classification network by combining attention mechanism and ResNeSt for plasmodium detection and using self-supervised learning to pre-train the network. First, the positive samples were adopted to pre-train the network. Then, attention modules were taken to highlight the feature area. To support current and future research, we also constructed a plasmodium dataset with Plasmodium falciparum, Plasmodium vivax, Plasmodium ovale, and Plasmodium malaria and non-Plasmodium. Through self-supervised learning, a large amount of unlabeled data is used to mine the representational features, thus improving the feature extraction capability of the model and achieving higher accuracy, while saving the physician's labeling time and improving the classification accuracy. Results: The experiments show that our model exhibits an excellent performance and that the test accuracy, sensitivity, and specificity attain 97.8%, 96.5%, and 98.9%, respectively. Conclusion: The AI classification method proposed in this paper can effectively assist clinicians in the diagnosis and provide a basis for the automatic detection of malaria parasites in the future.

Automatic Sparse Connectivity Learning for Neural Networks.

Since sparse neural networks usually contain many zero weights, these unnecessary network connections can potentially be eliminated without degrading network performance. Therefore, well-designed sparse neural networks have the potential to significantly reduce the number of floating-point operations (FLOPs) and computational resources. In this work, we propose a new automatic pruning method-sparse connectivity learning (SCL). Specifically, a weight is reparameterized as an elementwise multiplication of a trainable weight variable and a binary mask. Thus, network connectivity is fully described by the binary mask, which is modulated by a unit step function. We theoretically prove the fundamental principle of using a straight-through estimator (STE) for network pruning. This principle is that the proxy gradients of STE should be positive, ensuring that mask variables converge at their minima. After finding Leaky ReLU, Softplus, and identity STEs can satisfy this principle, we propose to adopt identity STE in SCL for discrete mask relaxation. We find that mask gradients of different features are very unbalanced; hence, we propose to normalize mask gradients of each feature to optimize mask variable training. In order to automatically train sparse masks, we include the total number of network connections as a regularization term in our objective function. As SCL does not require pruning criteria or hyperparameters defined by designers for network layers, the network is explored in a larger hypothesis space to achieve optimized sparse connectivity for the best performance. SCL overcomes the limitations of existing automatic pruning methods. Experimental results demonstrate that SCL can automatically learn and select important network connections for various baseline network structures. Deep learning models trained by SCL outperform the state-of-the-art human-designed and automatic pruning methods in sparsity, accuracy, and FLOPs reduction.

COVID-19 personal health mention detection from tweets using dual convolutional neural network.

Twitter offers extensive and valuable information on the spread of COVID-19 and the current state of public health. Mining tweets could be an important supplement for public health departments in monitoring the status of COVID-19 in a timely manner and taking the appropriate actions to minimize its impact. Identifying personal health mentions (PHM) is the first step of social media public health surveillance. It aims to identify whether a person's health condition is mentioned in a tweet, and it serves as a crucial method in tracking pandemic conditions in real time. However, social media texts contain noise, many creative and novel phrases, sarcastic emoji expressions, and misspellings. In addition, the class imbalance issue is usually very serious. To address these challenges, we built a COVID-19 PHM dataset containing more than 11,000 annotated tweets, and we proposed a dual convolutional neural network (CNN) framework using this dataset. An auxiliary CNN in the dual CNN structure provides supplemental information for the primary CNN in order to detect PHMs from tweets more effectively. The experiment shows that the proposed structure could alleviate the effect of class imbalance and could achieve promising results. This automated approach could monitor public health in real time and save disease-prevention departments from the tedious manual work in public health surveillance.

Using the maximum between-class variance for automatic gridding of cDNA microarray images.

Gridding is the first and most important step to separate the spots into distinct areas in microarray image analysis. Human intervention is necessary for most gridding methods, even if some so-called fully automatic approaches also need preset parameters. The applicability of these methods is limited in certain domains and will cause variations in the gene expression results. In addition, improper gridding, which is influenced by both the misalignment and high noise level, will affect the high throughput analysis. In this paper, we have presented a fully automatic gridding technique to break through the limitation of traditional mathematical morphology gridding methods. First, a preprocessing algorithm was applied for noise reduction. Subsequently, the optimal threshold was gained by using the improved Otsu method to actually locate each spot. In order to diminish the error, the original gridding result was optimized according to the heuristic techniques by estimating the distribution of the spots. Intensive experiments on six different data sets indicate that our method is superior to the traditional morphology one and is robust in the presence of noise. More importantly, the algorithm involved in our method is simple. Furthermore, human intervention and parameters presetting are unnecessary when the algorithm is applied in different types of microarray images.

Methods of forward feature selection based on the aggregation of classifiers generated by single attribute.

Compared to backward feature selection (BFS) method in gene expression data analysis, forward feature selection (FFS) method can obtain an expected feature subset with less iteration. However, the number of FFS method is considerably less than that of BFS method. More efficient FFS methods need to be developed. In this paper, two FFS methods based on the pruning of the classifier ensembles generated by single attribute are proposed for gene selection. The main contributions are as follows: (1) a new loss function, p-insensitive loss function, is proposed to overcome the disadvantage of the margin Euclidean distance loss function in the pruning of classifier ensembles; (2) two FFS methods based on the margin Euclidean distance loss function and the p-insensitive loss function, named as FFS-ACSA1 and FFS-ACSA2 respectively, are proposed; (3) the comparison experiments on four gene expression datasets show that FFS-ACSA2 obtains the best results among three FFS methods (i.e. signal-to-noise ratio (SNR), FFS-ACSA1 and FFS-ACSA2), and is competitive to the famous support vector machine-based recursive feature elimination (SVM-RFE), while FFS-ACSA1 is unstable.

Improving the computational efficiency of recursive cluster elimination for gene selection.

The gene expression data are usually provided with a large number of genes and a relatively small number of samples, which brings a lot of new challenges. Selecting those informative genes becomes the main issue in microarray data analysis. Recursive cluster elimination based on support vector machine (SVM-RCE) has shown the better classification accuracy on some microarray data sets than recursive feature elimination based on support vector machine (SVM-RFE). However, SVM-RCE is extremely time-consuming. In this paper, we propose an improved method of SVM-RCE called ISVM-RCE. ISVM-RCE first trains a SVM model with all clusters, then applies the infinite norm of weight coefficient vector in each cluster to score the cluster, finally eliminates the gene clusters with the lowest score. In addition, ISVM-RCE eliminates genes within the clusters instead of removing a cluster of genes when the number of clusters is small. We have tested ISVM-RCE on six gene expression data sets and compared their performances with SVM-RCE and linear-discriminant-analysis-based RFE (LDA-RFE). The experiment results on these data sets show that ISVM-RCE greatly reduces the time cost of SVM-RCE, meanwhile obtains comparable classification performance as SVM-RCE, while LDA-RFE is not stable.

Integrated application of uniform design and least-squares support vector machines to transfection optimization.

BACKGROUND: Transfection in mammalian cells based on liposome presents great challenge for biological professionals. To protect themselves from exogenous insults, mammalian cells tend to manifest poor transfection efficiency. In order to gain high efficiency, we have to optimize several conditions of transfection, such as amount of liposome, amount of plasmid, and cell density at transfection. However, this process may be time-consuming and energy-consuming. Fortunately, several mathematical methods, developed in the past decades, may facilitate the resolution of this issue. This study investigates the possibility of optimizing transfection efficiency by using a method referred to as least-squares support vector machine, which requires only a few experiments and maintains fairly high accuracy. RESULTS: A protocol consists of 15 experiments was performed according to the principle of uniform design. In this protocol, amount of liposome, amount of plasmid, and the number of seeded cells 24 h before transfection were set as independent variables and transfection efficiency was set as dependent variable. A model was deduced from independent variables and their respective dependent variable. Another protocol made up by 10 experiments was performed to test the accuracy of the model. The model manifested a high accuracy. Compared to traditional method, the integrated application of uniform design and least-squares support vector machine greatly reduced the number of required experiments. What's more, higher transfection efficiency was achieved. CONCLUSION: The integrated application of uniform design and least-squares support vector machine is a simple technique for obtaining high transfection efficiency. Using this novel method, the number of required experiments would be greatly cut down while higher efficiency would be gained. Least-squares support vector machine may be applicable to many other problems that need to be optimized.