The temporal and spatial information of electroencephalogram (EEG) are essential for the emotion recognition model to learn the discriminative features. Hence, we propose a novel hybrid spatial-temporal feature fusion neural network (STFFNN) to extract the discriminative features and integrate complementary information. The generated power topographic maps, which capture dependencies among the electrodes, are fed to convolutional neural network (CNN) for spatial feature learning. Furthermore, instance normalizations (INs) and batch normalizations (BNs) within the CNN are appropriately combined to alleviate the individual difference and preserve the domain-invariant information. Meanwhile, a feedforward network is adopted for temporal feature learning. Due to the high dimensionality of EEG features, we propose a grid-search-based configurational optimization method to robustly reduce the dimensionality. Finally, inspired by the multimodal fusion strategies that leverage the complementarity of data to obtain more robust predictions, we utilize a bidirectional long short-term memory (Bi-LSTM) network for temporal and spatial feature fusion. To validate the effectiveness of the proposed method, the tenfold cross-validation experiments and subject-dependent experiments are both conducted on the DEAP database. The experimental results demonstrate that the proposed method achieves outstanding performance in emotion recognition with arousal and valence level.

An automatic vision-based sewer inspection plays a key role of sewage system in a modern city. Recent advances focus on utilizing a deep learning model to realize the sewer inspection system, benefiting from the capability of data-driven feature extraction. However, the ambiguity of sewer defects in the feature space is ignored, deteriorating the performance of sewer inspection. There are two reasons for such ambiguity. First, the defect-irrelevant region interferes the feature extraction of the model. Second, the setting of multilabel is an inherent challenge of extracting discriminative feature for different defect classes from defect-relevant region. In this article, we propose a multilabel sewer defect classification method, which can purify the sewer defect components in latent spaces, thereby mitigating the ambiguity of sewer defects. Specifically, a novel self-purification module (SPM) is modeled to disentangle the ambiguity of sewer defect feature, which consists of intraclass purification (ICP) and interclass decorrelation (ICD). ICP utilizes the task-aware information to purify the sewer features, and ICD aims to eliminate the cross correlation and defect-irrelevant components simultaneously. Moreover, to ensure the reliability of SPM, center global alignment (CGA) is introduced to avoid the trivial solution. Experimental results demonstrate the superiority of the proposed method compared with seven state-of-the-art methods on the latest benchmark Sewer-ML. The proposed method outperforms the others approximately 8% $\mathrm {F2_{\text {CIW}}}$ with a tolerant inference speed. Finally, the robustness of the proposed method is verified in two perturbed scenarios, where the reliable performance can be guaranteed against the limited perturbations.

Segmentation of left and right ventricles from 3D echocardiographic images is premised and key for quantitative analysis of cardiac function, which is important for pediatric cardiac diagnosis. Compared with 2D echocardiography, 3D echocardiography can fully represent ventricular structure without geometric inference. However, it usually takes experts several hours to obtain a 3D segmentation mask of the left and right ventricles. Therefore, a fast and automatic segmentation method is highly desired. Unfortunately, 3D echocardiography suffers from low contrast, unclear left and right ventricles borders, and blind zone. Existing segmentation methods usually have poor performance at ventricular boundaries. To deal with these problems, we propose a novel dual-branch TransV-Net (DBTV). DBTV comprises two parallel, interleaved, and relatively independent V-shaped encoder-decoder branches. The main branch acts on the original data to extract image features, and the auxiliary branch acts on edge maps to extract the additional edge features. To suppress noise and enhance the edge information, extra concatenations are added to bridge the features from the main and auxiliary branches. To reduce object missing caused by blind zone, a 3D transformer-based module is proposed in the bottom layer of the dual-branch structure to extract the global contexts. We do experiments on a self-collected dataset with 120 3D echocardiographic images from 60 cardiac sequences, and the dice score of 0.913 and 0.880 are obtained in the left and right ventricle segments, respectively. Each inference takes about two-thirds of a second for a single 3D frame.

Rib fractures are a common and potentially severe injury that can be challenging and labor-intensive to detect in CT scans. While there have been efforts to address this field, the lack of large-scale annotated datasets and evaluation benchmarks has hindered the development and validation of deep learning algorithms. To address this issue, the RibFrac Challenge was introduced, providing a benchmark dataset of over 5,000 rib fractures from 660 CT scans, with voxel-level instance mask annotations and diagnosis labels for four clinical categories (buckle, nondisplaced, displaced, or segmental). The challenge includes two tracks: a detection (instance segmentation) track evaluated by an FROC-style metric and a classification track evaluated by an F1-style metric. During the MICCAI 2020 challenge period, 243 results were evaluated, and seven teams were invited to participate in the challenge summary. The analysis revealed that several top rib fracture detection solutions achieved performance comparable or even better than human experts. Nevertheless, the current rib fracture classification solutions are hardly clinically applicable, which can be an interesting area in the future. As an active benchmark and research resource, the data and online evaluation of the RibFrac Challenge are available at the challenge website (https://ribfrac. grand-challenge.org/). In addition, we further analyzed the impact of two post-challenge advancements—largescale pretraining and rib segmentation—based on our internal baseline for rib fracture detection. These findings lay a foundation for future research and development in AI-assisted rib fracture diagnosis.

Few-shot image classification, whose goal is to generalize to unseen tasks with scarce labeled data, has developed rapidly over the years. However, in traditional few-shot learning methods with CNNs, non-local features and long-rang dependencies of the image may be lost, and this leads to a poor generalization of the trained model. With the advantage of the self-attention mechanism of Transformer, researchers have tried to use vision transformer to improve few-shot learning recently. However, these methods are more complicated and take up a lot of computing resources, and there is no baseline to measure their effectiveness. We propose a new method called ViTFSL-baseline. We take advantage of vision transformer and train our model on all train set without episodic training. Meanwhile, we design a new nearest-neighbor classifier to used for few-shot image classification. Furthermore, in order to narrow the gap between difference of same class, we introduce centroid calibration in classifier after the feature extraction of backbone. We run the experiments on popular benchmarks to show that our method is a simple and effective for few-shot image classification. Our approach could be taken as the baseline upon vision transformer for few-shot learning.