Hepatocellular carcinoma (HCC) is a common malignant tumor in China. In the present study, we aimed to construct and verify a prediction model of recurrence in HCC patients using databases (TCGA, AMC and Inserm) and machine learning methods and obtain the gene signature that could predict early relapse of HCC. Statistical methods, such as feature selection, survival analysis and Chi-Square test in R software, were used to analyze and select mutant genes related to disease free survival (DFS), race and vascular invasion. In addition, whole-exome sequencing was performed on 10 HCC patients recruited from our center, and the sequencing results were compared with the databases. Using the databases and machine learning methods, the prediction model of recurrence was constructed and optimized, and the selected mutant genes were verified in the test group. The accuracy of prediction was 74.19%. Moreover, these 10 patients from our center were used to verify these mutant genes and the prediction model, and a success rate of 80% was achieved. Collectively, we discovered recurrence-related genes and established recurrence prediction model of recurrence for HCC patients, which could provide significant guidance for clinical prediction of recurrence.

Deep learning-based face recognition models are vulnerable to adversarial attacks. To curb these attacks, most defense methods aim to improve the robustness of recognition models against adversarial perturbations. However, the generalization capacities of these methods are quite limited. In practice, they are still vulnerable to unseen adversarial attacks. Deep learning models are fairly robust to general perturbations, such as Gaussian noises. A straightforward approach is to inactivate the adversarial perturbations so that they can be easily handled as general perturbations. In this paper, a plug-and-play adversarial defense method, named perturbation inactivation (PIN), is proposed to inactivate adversarial perturbations for adversarial defense. We discover that the perturbations in different subspaces have different influences on the recognition model. There should be a subspace, called the immune space, in which the perturbations have fewer adverse impacts on the recognition model than in other subspaces. Hence, our method estimates the immune space and inactivates the adversarial perturbations by restricting them to this subspace. The proposed method can be generalized to unseen adversarial perturbations since it does not rely on a specific kind of adversarial attack method. This approach not only outperforms several state-of-the-art adversarial defense methods but also demonstrates a superior generalization capacity through exhaustive experiments. Moreover, the proposed method can be successfully applied to four commercial APIs without additional training, indicating that it can be easily generalized to existing face recognition systems.

Efficient medical image segmentation aims to provide accurate pixel- wise predictions with a lightweight implementation framework. However, existing lightweight networks generally overlook the generalizability of the cross-domain medical segmentation tasks. In this paper, we propose Generalizable Knowledge Distillation (GKD), a novel framework for enhancing the performance of lightweight networks on cross-domain medical segmentation by generalizable knowledge distillation from powerful teacher networks. Considering the domain gaps between different medical datasets, we propose the Model-Specific Alignment Networks (MSAN) to obtain the domain-invariant representations. Meanwhile, a customized Alignment Consistency Training (ACT) strategy is designed to promote the MSAN training. Based on the domain-invariant vectors in MSAN, we propose two generalizable distillation schemes, Dual Contrastive Graph Distillation (DCGD) and Domain-Invariant Cross Distillation (DICD). In DCGD, two implicit contrastive graphs are designed to model the intra-coupling and inter-coupling semantic correlations. Then, in DICD, the domain-invariant semantic vectors are reconstructed from two networks ( i.e. , teacher and student) with a crossover manner to achieve simultaneous generalization of lightweight networks, hierarchically. Moreover, a metric named Fréchet Semantic Distance (FSD) is tailored to verify the effectiveness of the regularized domain-invariant features. Extensive experiments conducted on the Liver, Retinal Vessel and Colonoscopy segmentation datasets demonstrate the superiority of our method, in terms of performance and generalization ability on lightweight networks. Our code will be available at GKD Framework.

With the widespread use of face masks due to the COVID-19 pandemic, accurate masked face recognition has become more crucial than ever. While several studies have investigated masked face recognition using convolutional neural networks (CNNs), there is a paucity of research exploring the use of plain Vision Transformers (ViTs) for this task. Unlike ViT models used in image classification, object detection, and semantic segmentation, the model trained by modern face recognition losses struggles to converge when trained from scratch. To this end, this paper initializes the model parameters via a proxy task of patch reconstruction and observes that the ViT backbone exhibits improved training stability with satisfactory performance for face recognition. Beyond the training stability, two strategies based on prompts are proposed to integrate holistic and masked face recognition in a single framework, namely FaceT. Along with popular holistic face recognition benchmarks, several open-sourced masked face recognition benchmarks are collected for evaluation. Our extensive experiments demonstrate that the proposed FaceT performs on par or better than state-of-the-art CNNs on both holistic and masked face recognition benchmarks. Codes will be made available at https://github.com/zyainfal/Joint-Holistic-and-Masked-Face-Recognition.

3D human pose and shape estimation from a single RGB image is an appealing yet challenging task. Due to the graph-like nature of human parametric models, a growing number of graph neural network-based approaches have been proposed and achieved promising results. However, existing methods build graphs for different instances based on the same template SMPL mesh, neglecting the geometric perception of individual properties. In this work, we propose an end-to-end method named Personalized Graph Generation (PGG) to construct the geometry-aware graph from an intermediate predicted human mesh. Specifically, a convolutional module initially regresses a coarse SMPL mesh tailored for each sample. Guided by the 3D structure of this personalized mesh, PGG extracts the local features from the 2D feature map. Then, these geometry-aware features are integrated with the specific coarse SMPL parameters as vertex features. Furthermore, a body-oriented adjacency matrix is adaptively generated according to the coarse mesh. It considers individual full-body relations between vertices, enhancing the perception of body geometry. Finally, a graph attentional module is utilized to predict the residuals to get the final results. Quantitative experiments across four benchmarks and qualitative comparisons on more datasets show that the proposed method outperforms state-of-the-art approaches for 3D human pose and shape estimation.