Brain tumors are a pernicious cancer with one of the lowest five-year survival rates. Neurologists often use magnetic resonance imaging (MRI) to diagnose the type of brain tumor. Automated computer-assisted tools can help them speed up the diagnosis process and reduce the burden on the health care systems. Recent advances in deep learning for medical imaging have shown remarkable results, especially in the automatic and instant diagnosis of various cancers. However, we need a large amount of data (images) to train the deep learning models in order to obtain good results. Large public datasets are rare in medicine. This paper proposes a framework based on unsupervised deep generative neural networks to solve this limitation. We combine two generative models in the proposed framework: variational autoencoders (VAEs) and generative adversarial networks (GANs). We swap the encoder–decoder network after initially training it on the training set of available MR images. The output of this swapped network is a noise vector that has information of the image manifold, and the cascaded generative adversarial network samples the input from this informative noise vector instead of random Gaussian noise. The proposed method helps the GAN to avoid mode collapse and generate realistic-looking brain tumor magnetic resonance images. These artificially generated images could solve the limitation of small medical datasets up to a reasonable extent and help the deep learning models perform acceptably. We used the ResNet50 as a classifier, and the artificially generated brain tumor images are used to augment the real and available images during the classifier training. We compared the classification results with several existing studies and state-of-the-art machine learning models. Our proposed methodology noticeably achieved better results. By using brain tumor images generated artificially by our proposed method, the classification average accuracy improved from 72.63% to 96.25%. For the most severe class of brain tumor, glioma, we achieved 0.769, 0.837, 0.833, and 0.80 values for recall, specificity, precision, and F1-score, respectively. The proposed generative model framework could be used to generate medical images in any domain, including PET (positron emission tomography) and MRI scans of various parts of the body, and the results show that it could be a useful clinical tool for medical experts.

Deep learning has gained immense attention from researchers in medicine, especially in medical imaging. The main bottleneck is the unavailability of sufficiently large medical datasets required for the good performance of deep learning models. This paper proposes a new framework consisting of one variational autoencoder (VAE), two generative adversarial networks, and one auxiliary classifier to artificially generate realistic-looking skin lesion images and improve classification performance. We first train the encoder-decoder network to obtain the latent noise vector with the image manifold’s information and let the generative adversarial network sample the input from this informative noise vector in order to generate the skin lesion images. The use of informative noise allows the GAN to avoid mode collapse and creates faster convergence. To improve the diversity in the generated images, we use another GAN with an auxiliary classifier, which samples the noise vector from a heavy-tailed student t-distribution instead of a random noise Gaussian distribution. The proposed framework was named TED-GAN, with T from the t-distribution and ED from the encoder-decoder network which is part of the solution. The proposed framework could be used in a broad range of areas in medical imaging. We used it here to generate skin lesion images and have obtained an improved classification performance on the skin lesion classification task, rising from 66% average accuracy to 92.5%. The results show that TED-GAN has a better impact on the classification task because of its diverse range of generated images due to the use of a heavy-tailed t-distribution.

The decomposition-based multi-objective evolutionary algorithm (MOEA/D) has shown remarkable effectiveness in solving multi-objective problems (MOPs). In this paper, we integrate the quantum-behaved particle swarm optimization (QPSO) algorithm with the MOEA/D framework in order to make the QPSO be able to solve MOPs effectively, with the advantage of the QPSO being fully used. We also employ a diversity controlling mechanism to avoid the premature convergence especially at the later stage of the search process, and thus further improve the performance of our proposed algorithm. In addition, we introduce a number of nondominated solutions to generate the global best for guiding other particles in the swarm. Experiments are conducted to compare the proposed algorithm, DMO-QPSO, with four multi-objective particle swarm optimization algorithms and one multi-objective evolutionary algorithm on 15 test functions, including both bi-objective and tri-objective problems. The results show that the performance of the proposed DMO-QPSO is better than other five algorithms in solving most of these test problems. Moreover, we further study the impact of two different decomposition approaches, i.e., the penalty-based boundary intersection (PBI) and Tchebycheff (TCH) approaches, as well as the polynomial mutation operator on the algorithmic performance of DMO-QPSO.

Existing multilabel text classification methods rely on a complex manual design to mine label correlation, which has the risk of overfitting and ignores the relationship between text and labels. To solve the above problems, this paper proposes a multilabel text classification algorithm based on a transformer encoder–decoder, which can adaptively extract the dependency relationship between different labels and text. First, text representation learning is carried out through word embedding and a bidirectional long short-term memory network. Second, the global relationship of the text is modeled by the transformer encoder, and then the multilabel query is adaptively learned by the transformer decoder. Last, a weighted fusion strategy under the supervision of multiple loss functions is proposed to further improve the classification performance. The experimental results on the AAPD and RCV1-V2 datasets show that compared with the existing methods, the proposed algorithm achieves better classification results. The optimal micro-F1 reaches 73.4% and 87.8%, respectively, demonstrating the effectiveness of the proposed algorithm.

The goal of image splicing localization is to detect the tampered area in an input image. Deep learning models have shown good performance in such a task, but are generally unable to detect the boundaries of the tampered area well. In this paper, we propose a novel deep learning model for image splicing localization that not only considers local image features, but also extracts global information of images by using a multi-scale guided learning strategy. In addition, the model integrates spatial and channel self-attention mechanisms to focus on extracting important features instead of restraining unimportant or noisy features. The proposed model is trained on the CASIA v2.0 dataset, and its performance is tested on the CASIA v1.0, Columbia Uncompressed, and DSO-1 datasets. Experimental results show that, with the help of the multi-scale guided learning strategy and self-attention mechanisms, the proposed model can locate the tampered area more effectively than the state-of-the-art models.

Although deep learning has achieved great success in image classification, large amounts of labelled data are needed to make full use of the advantages of deep learning. However, annotating a large number of images is expensive and time-consuming, especially annotating medical images, which requires professional knowledge. Therefore, semi-supervised learning has shown its potential for medical image classification. In this paper, we propose a novel pseudo-labelling semi-supervised learning method for medical image classification. Firstly, we utilize the anti-curriculum strategy for model training to prevent the model from producing predictions with a high value from the samples which are similar with existed labeled data. Secondly, to produce more stable and accurate pseudo labels for unlabeled data, we generate the pseudo labels with ensemble predictions provided by the model with samples augmented by different augmentations. In addition, we refine the generated pseudo labels using the prediction of the model at the current epoch in order to make the model learn from itself and improve the model performance. Comparative experiments on the Chest X-ray14 dataset for a multi-label classification task and the ISIC 2018 dataset for a multi-class classification task are performed, and the experimental results show the effectiveness of our method.