Automatic segmentation of liver tumors is crucial to assist radiologists in clinical diagnosis. While various deep learning-based algorithms have been proposed, such as U-Net and its variants, the inability to explicitly model long-range dependencies in CNN limits the extraction of complex tumor features. Some recent researchers have applied Transformer-based 3D networks to analyze medical images. However, the previous methods focus on modeling the local information (eg. edge) or global information (eg. morphology) with fixed network weights. To learn and extract complex tumor features of varied tumor size, location, and morphology for more accurate segmentation, we propose a Dynamic Hierarchical Transformer Network, named DHT-Net. The DHT-Net mainly contains a Dynamic Hierarchical Transformer (DHTrans) structure and an Edge Aggregation Block (EAB). The DHTrans first automatically senses the tumor location region by Dynamic Adaptive Convolution, which employs hierarchical operations with the different receptive field sizes to learn the features of various tumors, thus enhancing the semantic representation ability of tumor features. Then, to adequately capture the irregular morphological features in the target tumor region, DHTrans aggregates global tumor shape and local texture information in a complementary manner. In addition, we introduce the EAB to extract detailed edge features in the shallow fine-grained details of the network, which provides sharp boundaries of liver tissue and tumor regions. We evaluate our method on two challenging public datasets, LiTS and 3DIRCADb. The proposed method has shown superior liver and tumor segmentation performance compared to several state-of-the-art 2D, 3D, and 2.5D hybrid models. The code is available at https://github.com/Lry777/DHT-Net

Educational exercises are crucial factors in the successful implementation of online education as they play a key role in assessing students’ learning and supporting teachers in instruction. These exercises encompass two primary types of data: text and images. However, existing methods for extracting exercise features only focus on the textual data, neglecting the rich semantic information present in the image data. Consequently, the exercise characterization vector generated by these methods struggles to fully characterize the exercise. To address these limitations, this paper proposes a multimodal information fusion-based exercise characterization model called MIFM. The MIFM model tackles the challenges of current exercise modeling methods by performing extraction and fusion operations on the heterogeneous features present in exercises. It employs a dual-stream architecture to separately extract features from images and text, and establishes connections between heterogeneous data using cross-modality attention methods. Finally, the heterogeneous features are fused using a Bi-LSTM combined with a multi-head attention mechanism. The resulting model produces a multimodal exercise characterization vector that fuses both modalities and incorporates three knowledge elements. In the experiments, by using the model to replace the exercise characterization modules in the three educational tasks, specifically, it achieves an increased ACC value of 72.35% in the knowledge mapping task, a heightened PCC value of 46.83% in the exercise difficulty prediction task, and an elevated AUC value of 62.57% in the student performance prediction task.

Person re-identification is the technique of identifying the same person in different camera shots, known as ReID for short. Most existing models focus on single-modality person re-identification involving only visible images. However, the visible modality is not suitable for low-light environments or at night, when crime is frequent. In contrast, infrared images can reflect the nighttime environment, and most surveillance systems are equipped with dual-mode cameras that can automatically switch between visible and infrared modalities based on light conditions. In contrast to visible-light cameras, infrared (IR) cameras can still capture enough information from the scene in those dark environments. Therefore, the problem of visible-infrared cross-modality person re-identification (VI-ReID) is proposed. To improve the identification rate of cross-modality person re-identification, a cross-modality person re-identification method based on a two-branch network is proposed. Firstly, we use infrared image colorization technology to convert infrared images into color images to reduce the differences between modalities and propose a visible-infrared cross-modality person re-identification algorithm based on Two-Branch Network with Double Constraints (VI-TBNDC), which consists of two main components: a two-branch network for feature extraction and a double-constrained identity loss for feature learning. The two-branch network extracts the features of both data sets separately, and the double-constrained identity loss ensures that the learned feature representations are discriminative enough to distinguish different people from two different patterns. The effectiveness of the proposed method is verified by extensive experimental analysis, and the method achieves good recognition accuracy on the visible-infrared image person re-identification standard dataset SYSU-MM01.

Single nucleotide variants (SNVs) are very common in human genome and pose a significant effect on cellular proliferation and tumorigenesis in various cancers. Somatic variant and germline variant are the two forms of SNVs. They are the major drivers of inherited diseases and acquired tumors respectively. A reasonable analysis of the next generation sequencing data profiles from cancer genomes could provide crucial information for cancer diagnosis and treatment. Accurate detection of SNVs and distinguishing the two forms are still considered challenging tasks in cancer analysis. Herein, we propose a new approach, LDSSNV, to detect somatic SNVs without matched normal samples. LDSSNV predicts SNVs by training the XGboost classifier on a concise combination of features and distinguishes the two forms based on linkage disequilibrium which is a trait between germline mutations. LDSSNV provides two modes to distinguish the somatic variants from germline variants, the single-mode and multiple-mode by respectively using a single tumor sample and multiple tumor samples. The performance of the proposed method is assessed on both simulation data and real sequencing datasets. The analysis shows that the LDSSNV method outperforms competing methods and can become a robust and reliable tool for analyzing tumor genome variation.