Automated detection of lymph node metastasis (LNM) holds great potential to alleviate the workload of doctors and reduce misinterpretations. Despite the practical successes achieved, effectively addressing the highly complex and heterogeneous tumor microenvironment remains an open and challenging problem, especially when tumor subtypes intermingle and are difficult to delineate. In this paper, we propose a multi-task adaptive resolution network, named MAR-Net, for LNM detection and subtyping in complex mixed-type cancers. Specifically, we construct a resolution-aware module to mine heterogeneous diagnostic information, which exploits the multi-scale pyramid information and adaptively combines multi-resolution structured features for comprehensive representation. Additionally, we adopt a multi-task learning approach that simultaneously addresses LNM detection and subtyping, reducing model instability during optimization and improving performance across both tasks. More importantly, to rectify the potential misclassification of tumor subtypes, we elaborately design a hierarchical subtying refinement (HSR) algorithm that leverages a generic segmentation model informed by pathologists' prior knowledge. Evaluations have been conducted on three private and one public cancer datasets (554 WSIs, 4.8 million patches). Our experimental results demonstrate that the proposed method consistently achieves superior performance compared to the state-of-the-art methods, achieving 0.5% to 3.2% higher AUC in LNM detection and 3.8% to 4.4% higher AUC in LNM subtyping.

The joint optimization of representation learning and clustering in the embedding space has experienced a breakthrough in recent years. In spite of the advance, clustering with representation learning has been limited to flat-level categories, which often involves cohesive clustering with a focus on instance relations. To overcome the limitations of flat clustering, we introduce hierarchically-clustered representation learning (HCRL), which simultaneously optimizes representation learning and hierarchical clustering in the embedding space. Compared with a few prior works, HCRL firstly attempts to consider a generation of deep embeddings from every component of the hierarchy, not just leaf components. In addition to obtaining hierarchically clustered embeddings, we can reconstruct data by the various abstraction levels, infer the intrinsic hierarchical structure, and learn the level-proportion features. We conducted evaluations with image and text domains, and our quantitative analyses showed competent likelihoods and the best accuracies compared with the baselines.

Recently, training with adversarial examples, which are generated by adding a small but worst-case perturbation on input examples, has improved the generalization performance of neural networks. In contrast to the biased individual inputs to enhance the generality, this paper introduces adversarial dropout, which is a minimal set of dropouts that maximize the divergence between 1) the training supervision and 2) the outputs from the network with the dropouts. The identified adversarial dropouts are used to automatically reconfigure the neural network in the training process, and we demonstrated that the simultaneous training on the original and the reconfigured network improves the generalization performance of supervised and semi-supervised learning tasks on MNIST, SVHN, and CIFAR-10. We analyzed the trained model to find the performance improvement reasons. We found that adversarial dropout increases the sparsity of neural networks more than the standard dropout. Finally, we also proved that adversarial dropout is a regularization term with a rank-valued hyper-parameter that is different from a continuous-valued parameter to specify the strength of the regularization.

Despite the proliferation of topic models, the organization of topics from the probabilistic models needs improvement in two ways: the better structured presentation of topics and the incorporation of domain knowledge on the corpus. The structured presentation, i.e., the hierarchical topic model, helps in categorizing similar topics; the incorporation of domain knowledge enables the concentrated sampling of predefined keywords in the mixture parameter learning. This paper presents a hierarchical topic models with incorporated domain knowledge, called Guided Hierarchical Topic Model (GHTM). Specifically, we allocated the prior information from the knowledge to the Dirichlet Forest prior. From the prior adjustment, we obtained the topic tree guided by the domain knowledge. This paper also contributes in enumerating four different knowledge extraction methods and applying the extracted knowledge to GHTM. We evaluated the performance of GHTM in terms of the hierarchical clustering accuracy, and we found a significant improvement of hierarchical clustering measured by F-measures. This improvement is also verified by the perplexity analyses. Additionally, we measured topic quality with KL-divergence and visualization, and these confirm the ability to better separate topic distributions. Finally, we tested the hierarchical topic quality through human experiments, and this also revealed significant improvements originating from the guidance.

Disasters and responses have evolved over-time, and the evolution has been affected by various factors, such as societal change, climate change, and technological advance. To better prepare the future disasters, we need to estimate the evolution trend of the past disasters and the responses. This paper analyzes the academic articles of the field with network-text analyses. The analyses captured the word level and the topic level evolution over-time with statistical significance tests. Further, we turn the text mining results into the network analysis data to identify the key words and topics in the evolution paths. The proposed method suggests the swift of interests, i.e. the new ways of organizational interoperation, the evolution of logistic issues, in the disaster and response field.