Modulation Of Aggregation Research Articles

MSCAReg‐Net: Multi‐scale complexity‐aware convolutional neural network for deformable image registration

AbstractDeep learning‐based image registration (DLIR) has been widely developed, but it remains challenging in perceiving small and large deformations. Besides, the effectiveness of the DLIR methods was also rarely validated on the downstream tasks. In the study, a multi‐scale complexity‐aware registration network (MSCAReg‐Net) was proposed by devising a complexity‐aware technique to facilitate DLIR under a single‐resolution framework. Specifically, the complexity‐aware technique devised a multi‐scale complexity‐aware module (MSCA‐Module) to perceive deformations with distinct complexities, and employed a feature calibration module (FC‐Module) and a feature aggregation module (FA‐Module) to facilitate the MSCA‐Module by generating more distinguishable deformation features. Experimental results demonstrated the superiority of the proposed MSCAReg‐Net over the existing methods in terms of registration accuracy. Besides, other than the indices of Dice similarity coefficient (DSC) and percentage of voxels with non‐positive Jacobian determinant (), a comprehensive evaluation of the registration performance was performed by applying this method on a downstream task of multi‐atlas hippocampus segmentation (MAHS). Experimental results demonstrated that this method contributed to a better hippocampus segmentation over other DLIR methods, and a comparable segmentation performance with the leading SyN method. The comprehensive assessment including DSC, , and the downstream application on MAHS demonstrated the advances of this method.

A Deep-Learning-Based Multimodal Data Fusion Framework for Urban Region Function Recognition

Accurate and efficient classification maps of urban functional zones (UFZs) are crucial to urban planning, management, and decision making. Due to the complex socioeconomic UFZ properties, it is increasingly challenging to identify urban functional zones by using remote-sensing images (RSIs) alone. Point-of-interest (POI) data and remote-sensing image data play important roles in UFZ extraction. However, many existing methods only use a single type of data or simply combine the two, failing to take full advantage of the complementary advantages between them. Therefore, we designed a deep-learning framework that integrates the above two types of data to identify urban functional areas. In the first part of the complementary feature-learning and fusion module, we use a convolutional neural network (CNN) to extract visual features and social features. Specifically, we extract visual features from RSI data, while POI data are converted into a distance heatmap tensor that is input into the CNN with gated attention mechanisms to extract social features. Then, we use a feature fusion module (FFM) with adaptive weights to fuse the two types of features. The second part is the spatial-relationship-modeling module. We designed a new spatial-relationship-learning network based on a vision transformer model with long- and short-distance attention, which can simultaneously learn the global and local spatial relationships of the urban functional zones. Finally, a feature aggregation module (FGM) utilizes the two spatial relationships efficiently. The experimental results show that the proposed model can fully extract visual features, social features, and spatial relationship features from RSIs and POIs for more accurate UFZ recognition.

Real-Time Dynamic Gesture Recognition Algorithm Based on Adaptive Information Fusion and Multi-Scale Optimization Transformer

Gesture recognition is a popular technology in the field of computer vision and an important technical mean of achieving human-computer interaction. To address problems such as the limited long-range feature extraction capability of existing dynamic gesture recognition networks based on convolutional operators, we propose a dynamic gesture recognition algorithm based on spatial pyramid pooling Transformer and optical flow information fusion. We take advantage of Transformer’s large receptive field to reduce model computation while improving the model’s ability to extract features at different scales by embedding spatial pyramid pooling. We use the optical flow algorithm with the global motion aggregation module to obtain an optical flow map of hand motion, and to extract the key frames based on the similarity minimization principle. We also design an adaptive feature fusion method to fuse the spatial and temporal features of the dual channels. Finally, we demonstrate the effectiveness of model components on model recognition enhancement through ablation experiments. We conduct training and validation on the SCUT-DHGA dynamic gesture dataset and on a dataset we collected, and we perform real-time dynamic gesture recognition tests using the trained model. The results show that our algorithm achieves high accuracy even while keeping the parameters balanced. It also achieves fast and accurate recognition of dynamic gestures in real-time tests.

PatchAugNet: Patch feature augmentation-based heterogeneous point cloud place recognition in large-scale street scenes

Point Cloud Place Recognition (PCPR) in street scenes is an essential task in the fields of autonomous driving, robot navigation, and urban map updating. However, the domain gap between heterogeneous point clouds and the difficulty of feature characterization in large-scale complex street scenes pose significant challenges for existing PCPR methods. Most PCPR methods only take into account point clouds collected by the same platforms and sensors, thus they are with poor domain transferability. In this paper, we propose PatchAugNet, which utilizes patch feature augmentation and adaptive pyramid feature aggregation to achieve better performance and generalizability for Heterogeneous Point Cloud-based Place Recognition (HPCPR) tasks. Firstly, multi-scale local features are extracted by the pyramid feature extraction module. Secondly, local features are enhanced by the patch feature augmentation module to overcome the domain gap problem and achieve better feature representation as well as network generalizability. Finally, a global feature is generated using an adaptive pyramid feature aggregation module, which automatically adjusts and balances the proportion of intra-scale and inter-scale features according to the scene content. To evaluate the performance of PatchAugNet, a large-scale heterogeneous point cloud dataset consisting of high-precision Mobile Laser Scanning (MLS) point clouds and helmet-mounted Portable Laser Scanning (PLS) point clouds is collected. The dataset covers various street scenes with a length of over 20 km. The comprehensive experimental results indicate that PatchAugNet achieves State-Of-The-Art (SOTA) performance with 83.43 % recall@top1% and 60.34 % recall@top1 on unseen large-scale street scenes, outperforming existing SOTA PCPR methods by + 9.57 recall@top1% and + 15.50 recall@top1, while exhibiting better generalizability. For source code and detailed experimental results, please refer to: https://github.com/WHU-USI3DV/PatchAugNet.

Optimized voxel transformer for 3D detection with spatial-semantic feature aggregation

In this paper, we propose a novel 3D object detection model that leverages the advantages of the Voxel Transformer (VoTr) and the Confident IoU-Aware Single-Stage Object Detector (CIA-SSD) to address the challenges of detecting objects in 3D point clouds. Our model adopts the VoTr as its backbone, which enables long-range interactions between voxels via a self-attention mechanism. This overcomes the limitations of conventional voxel-based 3D detectors, which struggle to capture sufficient contextual information due to their restricted receptive fields. Our model also integrates the sparse voxel module and the submanifold voxel module, which efficiently process empty and non-empty voxel positions, effectively handling the natural sparsity and abundance of non-empty voxels. Moreover, inspired by the CIA-SSD design, our model incorporates the Spatial-Semantic Feature Aggregation (SSFA) module, which allows for the adaptive fusion of high-level abstract semantic features and low-level spatial features, ensuring accurate predictions of bounding boxes and classification confidence. Furthermore, based on the IoU-aware confidence rectification module, which refines the alignment between confidence scores and localization accuracy, we devise an Optimized RPN (Region Proposal Network) Detection Head module as a dense head to further predict the IoU loss and improve the accuracy. In this paper, we combine two state-of-the-art techniques to provide a precise and efficient solution for 3D object detection in point clouds. We evaluate our model on the KITTI dataset1 and achieve 76.56 % accuracy in terms of AP3D (%) Hard.

MAEU‐NET: A novel supervised architecture for brain tumor segmentation

AbstractA brain tumor is an abnormal growth of cells that damages the neural system and may lead to severe conditions. These cells are irregular in shape and size, and as a result, the manual analysis of these cells from magnetic resonance (MR) images is a cumbersome and time‐consuming task. To alleviate these issues, a novel U‐Net inspired MAEU‐Net (Multiscale context Aggregation and Edge activation U‐Net) is implemented to detect the brain tumor pixels from MR images more precisely. The encoder block of the proposed model is improved by integrating with multiscale feature aggregation and convolution block attention modules (CBAM) enabling the model to extract both pertinent low‐level and high‐level features. Further, the extracted features are subjected to a parallel pooling module to elevate the features that extract the tumor pixels. In addition to this, the output features of the last encoder are fed to a parallel dilated context aggregation module to mitigate the hyper‐parameter size and further elevate the receptive field strength of the proposed model. Apart from this, edge‐enhanced modules are incorporated with skip connections which concatenate the feature maps of the decoder with respective edge‐enhanced encoder feature maps. As a result, this module increases the aspect ratio and reduces blurry edge problems. To illustrate the performance of the proposed MAEU‐Net, it is trained and tested using Kaggle LGG, BraTS 2018, and BraTS 2021 publicly available datasets. The proposed model outperformed the previously existing models by achieving the test loss, dice coefficient, sensitivity, and specificity of 0.0590, 0.901, 0.942, and 0.998, respectively. Simultaneously, the proposed model is quantitatively analyzed by performing ablation and comparative studies and presented that the proposed MAEU‐Net is superior to other previous existing models like U‐Net++, SegNet, etc.

Structural asymmetric convolution for wireframe parsing

Simultaneously extracting junctions and their corresponding line segments from images presents a promising approach to structural environment cognition. However, conventional methods employ square convolution for line feature extraction, resulting in the exclusion of long-range dependencies and the generation of suboptimal wireframe predictions. In this paper, we introduce an efficient and concise parsing method named Structural Asymmetric Convolution-based Wireframe Parser (SACWP). Taking advantage of the inherent similarities between structural asymmetric convolution and the predominant distribution of line segments in man-made environments, we propose a Structural Asymmetric Convolution module (SAC) that captures long-range contextual features while efficiently filtering out irrelevant information from neighboring pixels. Additionally, we introduce a feature aggregation module based on dilated convolution (DCFA) to seamlessly integrate contextual information from multiple receptive fields. We thoroughly evaluate our approach on the Wireframe and YorkUrban datasets, achieving preferable results of 69.3% and 29.7% msAP respectively. On the other hand, the promising results adequately demonstrate the effectiveness of SACWP to Wireframe Parsing task.

MCNet: A multi-level context-aware network for the segmentation of adrenal gland in CT images

Accurate segmentation of the adrenal gland from abdominal computed tomography (CT) scans is a crucial step towards facilitating the computer-aided diagnosis of adrenal-related diseases such as essential hypertension and adrenal tumors. However, the small size of the adrenal gland, which occupies less than 1% of the abdominal CT slice, poses a significant challenge to accurate segmentation. To address this problem, we propose a novel multi-level context-aware network (MCNet) to segment adrenal glands in CT images. Our MCNet mainly consists of two components, i.e., the multi-level context aggregation (MCA) module and multi-level context guidance (MCG) module. Specifically, the MCA module employs multi-branch dilated convolutional layers to capture geometric information, which enables handling of changes in complex scenarios such as variations in the size and shape of objects. The MCG module, on the other hand, gathers valuable features from the shallow layer and leverages the complete utilization of feature information at different resolutions in various codec stages. Finally, we evaluate the performance of the MCNet on two CT datasets, including our clinical dataset (Ad-Seg) and a publicly available dataset known as Distorted Golden Standards (DGS), from different perspectives. Compared to ten other state-of-the-art segmentation methods, our MCNet achieves 71.34% and 75.29% of the best Dice similarity coefficient on the two datasets, respectively, which is at least 2.46% and 1.19% higher than other segmentation methods.

Rooftop PV Segmenter: A Size-Aware Network for Segmenting Rooftop Photovoltaic Systems from High-Resolution Imagery

The photovoltaic (PV) industry boom has accelerated the need for accurately understanding the spatial distribution of PV energy systems. The synergy of remote sensing and artificial intelligence presents significant prospects for PV energy monitoring. Currently, numerous studies have focused on extracting rooftop PV systems from airborne or satellite imagery, but their small-scale and size-varying characteristics make the segmentation results suffer from PV internal incompleteness and small PV omission. To address these issues, this study proposed a size-aware deep learning network called Rooftop PV Segmenter (RPS) for segmenting small-scale rooftop PV systems from high-resolution imagery. In detail, the RPS network introduced a Semantic Refinement Module (SRM) to sense size variations of PV panels and reconstruct high-resolution deep semantic features. Moreover, a Feature Aggregation Module (FAM) enhanced the representation of robust features by continuously aggregating deeper features into shallower ones. In the output stage, a Deep Supervised Fusion Module (DSFM) was employed to constrain and fuse the outputs at different scales to achieve more refined segmentation. The proposed RPS network was tested and shown to outperform other models in producing segmentation results closer to the ground truth, with the F1 score and IoU reaching 0.9186 and 0.8495 on the publicly available California Distributed Solar PV Array Dataset (C-DSPV Dataset), and 0.9608 and 0.9246 on the self-annotated Heilbronn Rooftop PV System Dataset (H-RPVS Dataset). This study has provided an effective solution for obtaining a refined small-scale energy distribution database.

Improved semantic segmentation network using normal vector guidance for LiDAR point clouds

Abstract As Light Detection and Ranging (LiDAR) sensors become increasingly prevalent in the field of autonomous driving, the need for accurate semantic segmentation of three-dimensional points grows accordingly. To address this challenge, we propose a novel network model that enhances segmentation performance by utilizing normal vector information. Firstly, we present a method to improve the accuracy of normal estimation by using the intensity and reflection angles of the light emitted from the LiDAR sensor. Secondly, we introduce a novel local feature aggregation module that integrates normal vector information into the network to improve the performance of local feature extraction. The normal information is closely related to the local structure of the shape of an object, which helps the network to associate unique features with corresponding objects. We propose four different structures for local feature aggregation, evaluate them, and choose the one that shows the best performance. Experiments using the SemanticKITTI dataset demonstrate that the proposed architecture outperforms both the baseline models, RandLA-Net, and other existing methods, achieving mean intersection over union of 57.9%. Furthermore, it shows highly competitive performance compared with RandLA-Net for small and dynamic objects in a real road environment. For example, it yielded 95.2% for cars, 47.4% for bicycles, 41.0% for motorcycles, 57.4% for bicycles, and 53.2% for pedestrians.

Dynamic hypergraph convolutional network for multimodal sentiment analysis

Multimodal sentiment analysis (MSA) aims to detect the sentiments from language (text), audio, and visual (facial expressions) modalities. The main challenge in MSA is how to efficiently model intra-modality and inter-modality dynamics. With the advent of graph convolution network (GCN), graph-based models are proposed to solve the challenge. However, general graphs contain only two nodes per edge, which limits the exploitation of high-order interactions. Moreover, current graph-based models mainly aggregate the features of each node during fusion, while the features of connected edges are not well mined. In this paper, we introduce dynamic hypergraph convolution networks to MSA for the first time and propose a Multimodal Dynamic Hypergraph Network (MDH) to learn intra- and inter-modality dynamics. Hypergraphs provide a natural approach to capture transcendental pairwise relations, and their potential for MSA remains unexplored. MDH mainly consists of three components: Unimodal Encoder, Dynamic Hypergraph Enhancement Network (DHEN), and HyperFusion module. Specifically, DHEN is composed of Cross-modal Affine, Hypergraph Construction, and Hypergraph Aggregation modules. As for the intra-modality dynamics, MDH utilizes Hypergraph Construction and Aggregation modules to model the interactions within time steps for each modality. As for the inter-modality dynamics, MDH implements Cross-modal Affine and HyperFusion modules to learn the relationships of the modalities. In addition, multi-task learning has been implemented to optimize the learning process for multimodal tasks. Experiments show that MDH outperforms graph-based models on CMU-MOSI and CMU-MOSEI datasets, as well as obtains new state-of-the-art results on CH-SIMS dataset. Furthermore, we conduct external experiments to explore the effectiveness of MDH and the effect of model depth with different graph networks.

A Novel Adaptive Edge Aggregation and Multiscale Feature Interaction Detector for Object Detection in Remote Sensing Images

Object detection (OD) in remote sensing (RS) images is an important task in the field of computer vision. OD techniques have achieved impressive advances in recent years. However, complex background interference, large-scale variations, and dense instances pose significant challenges for OD. These challenges may lead to misalignment between features extracted by OD models and the features of real objects. To address these challenges, we explore a novel single-stage detection framework for the adaptive fusion of multiscale features and propose a novel adaptive edge aggregation and multiscale feature interaction detector (AEAMFI-Det) for OD in RS images. AEAMFI-Det consists of an adaptive edge aggregation (AEA) module, a feature enhancement module (FEM) embedded in a context-aware cross-attention feature pyramid network (2CA-FPN), and a pyramid squeeze attention (PSA) module. The AEA module employs an edge enhancement mechanism to guide the network to learn spatial multiscale nonlocal dependencies and solve the problem of feature misalignment between the network’s focus and the real object. The 2CA-FPN employs level-by-level feature fusion to enhance multiscale feature interactions and effectively mitigate the misalignment between the scales of the extracted features and the scales of real objects. The FEM is designed to capture the local and nonlocal contexts as auxiliary information to enhance the feature representation of information interaction between multiscale features in a cross-attention manner. We introduce the PSA module to establish long-term dependencies between multiscale spaces and channels for better interdependency refinement. Experimental results obtained using the NWPU VHR-10 and DIOR datasets demonstrate the superior performance of AEAMFI-Det in object classification and localization.

Asymmetric Dual-Direction Quasi-Recursive Network for Single Hyperspectral Image Super-Resolution

Single hyperspectral image super-resolution aims to reconstruct a high-resolution hyperspectral image from a low-resolution one, which does not use any auxiliary images. For now, existing super-resolution methods often ignore the difference between the features of neighbor and non-neighbor spectral bands, leaving the feature exploration untargeted. As a result, the complementary information of such bands has not been effectively exploited. To do so, we propose an asymmetric dual-direction quasi-recursive network for single hyperspectral image super-resolution, which separately explores the features among neighbor and non-neighbor bands via forward and backward units. By considering the high similarity among neighbor bands, each forward unit thoroughly exploits spatial-spectral features among such bands through two kinds of correspondence aggregation modules. It also preserves a spectral structure by a spectral band grouping strategy and a spatial-spectral consistency module. Owning to the inconsecutive spectra among non-neighbor bands, backward units focus on extracting spatial features in such bands. With the aid of a global feature context fusion module, the information of global non-neighbor context and neighbor bands are adaptively fused, thus improving information completeness and complementarity. Experimental results reported for natural and remote sensing hyperspectral image datasets demonstrate the proposed network not only outperforms the state-of-the-art methods in terms of reconstruction quality and noise suppression, but also requires a smaller memory footprint.

Branch Aggregation Attention Network for Robotic Surgical Instrument Segmentation.

Surgical instrument segmentation is of great significance to robot-assisted surgery, but the noise caused by reflection, water mist, and motion blur during the surgery as well as the different forms of surgical instruments would greatly increase the difficulty of precise segmentation. A novel method called Branch Aggregation Attention network (BAANet) is proposed to address these challenges, which adopts a lightweight encoder and two designed modules, named Branch Balance Aggregation module (BBA) and Block Attention Fusion module (BAF), for efficient feature localization and denoising. By introducing the unique BBA module, features from multiple branches are balanced and optimized through a combination of addition and multiplication to complement strengths and effectively suppress noise. Furthermore, to fully integrate the contextual information and capture the region of interest, the BAF module is proposed in the decoder, which receives adjacent feature maps from the BBA module and localizes the surgical instruments from both global and local perspectives by utilizing a dual branch attention mechanism. According to the experimental results, the proposed method has the advantage of being lightweight while outperforming the second-best method by 4.03%, 1.53%, and 1.34% in mIoU scores on three challenging surgical instrument datasets, respectively, compared to the existing state-of-the-art methods. Code is available at https://github.com/SWT-1014/BAANet.

HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding.

Encoding a driving scene into vector representations has been an essential task for autonomous driving that can benefit downstream tasks e.g., trajectory prediction. The driving scene often involves heterogeneous elements such as the different types of objects (agents, lanes, traffic signs) and the semantic relations between objects are rich and diverse. Meanwhile, there also exist relativity across elements, which means that the spatial relation is a relative concept and need be encoded in a ego-centric manner instead of in a global coordinate system. Based on these observations, we propose Heterogeneous Driving Graph Transformer (HDGT), a backbone modelling the driving scene as a heterogeneous graph with different types of nodes and edges. For heterogeneous graph construction, we connect different types of nodes according to diverse semantic relations. For spatial relation encoding, the coordinates of the node as well as its in-edges are in the local node-centric coordinate system. For the aggregation module in the graph neural network (GNN), we adopt the transformer structure in a hierarchical way to fit the heterogeneous nature of inputs. Experimental results show that HDGT achieves state-of-the-art performance for the task of trajectory prediction, on INTERACTION Prediction Challenge and Waymo Open Motion Challenge.

Semantic-Context Graph Network for Point-Based 3D Object Detection

Point-based indoor 3D object detection has received increasing attention with the large demand for augmented reality, autonomous driving, and robot technology in the industry. However, the detection precision suffers from inputs with semantic ambiguity, i.e., shape symmetries, occlusion, and texture missing, which would lead that different objects appearing similar from different viewpoints and then confusing the detection model. Typical point-based detectors relieve this problem via learning proposal representations with both geometric and semantic information, while the entangled representation may cause a reduction in both semantic and spatial discrimination. In this paper, we focus on alleviating the confusion from entanglement and then enhancing the proposal representation by considering the proposal’s semantics and the context in one scene. A semantic-context graph network (SCGNet) is proposed, which mainly includes two modules: a category-aware proposal recoding module (CAPR) and a proposal context aggregation module (PCAg). To produce semantically clear features from entanglement representation, the CAPR module learns a high-level semantic embedding for each category to extract discriminative semantic clues. In view of further enhancing the proposal representation and leveraging the semantic clues, the PCAg module builds a graph to mine the most relevant context in the scene. With few bells and whistles, the SCGNet achieves SOTA performance and obtains consistent gains when applying to different backbones (0.9% ~ 2.4% on ScanNet V2 and 1.6% ~ 2.2% on SUN RGB-D for mAP@0.25). Code is available at https://github.com/dsw-jlu-rgzn/SCGNet.

Pose-guided self and external attention feature matching and aggregation network for person re-identification

Traditional methods that use pose information for person re-identification (ReID) often focus only on relationships between different parts of the same sample and ignore the correlation between poses of different samples, which hinders further improvement in recognition accuracy. In view of this, this paper proposes a pose-guided self and external attention feature matching and aggregation net which contains a visual context self and external attention module and a pose-guided feature matching and aggregation module. It can divide global features into local features without strict spatial feature alignment, and enables the model to focus on pose correlation between different samples. Thus, it not only learns pose-related identity identification features, but also avoids interference from the samples with large pose changes. The visual context self and external attention module realizes feature embedding through a transformer-based image classification model ViT and a human pose estimation model. Also, it extracts encoder features and local features containing rich pose information by adding an external attention. The pose-guided feature matching and aggregation module obtains a learnable part semantic view through a transformer decoder and pose heat maps. Then, it matches and aggregates with local features, adaptively learns pose-related features, and enhances the robustness of the model to background and occlusion. In this paper, experiments are conducted based on three data sets, including Market-1501, DukeMTMC-reID and MSMT17. The Rank-1 values are 95.3%, 90.1%, and 82.5%, respectively, and the mAP values are 88.3%, 81.1%, and 64.1%, respectively. In conclusion, our method introduces an external attention into the ReID task, and the ReID model can obtain more accurate results by extracting pose-related identity identification features and avoiding interference from samples with large pose changes.

LCA-Net: A Lightweight Cross-Stage Aggregated Neural Network for Fine-Grained Recognition of Crop Pests and Diseases

In the realm of smart agriculture technology’s rapid advancement, the integration of various sensors and Internet of Things (IoT) devices has become prevalent in the agricultural sector. Within this context, the precise identification of pests and diseases using unmanned robotic systems assumes a crucial role in ensuring food security, advancing agricultural production, and maintaining food reserves. Nevertheless, existing recognition models encounter inherent limitations such as suboptimal accuracy and excessive computational efforts when dealing with similar pests and diseases in real agricultural scenarios. Consequently, this research introduces the lightweight cross-layer aggregation neural network (LCA-Net). To address the intricate challenge of fine-grained pest identification in agricultural environments, our approach initially enhances the high-performance large-scale network through lightweight adaptation, concurrently incorporating a channel space attention mechanism. This enhancement culminates in the development of a cross-layer feature aggregation (CFA) module, meticulously engineered for seamless mobile deployment while upholding performance integrity. Furthermore, we devised the Cut-Max module, which optimizes the accuracy of crop pest and disease recognition via maximum response region pruning. Thorough experimentation on comprehensive pests and disease datasets substantiated the exceptional fine-grained performance of LCA-Net, achieving an impressive accuracy rate of 83.8%. Additional ablation experiments validated the proposed approach, showcasing a harmonious balance between performance and model parameters, rendering it suitable for practical applications in smart agricultural supervision.

SDA-Net: Self-distillation driven deformable attentive aggregation network for thyroid nodule identification in ultrasound images

Early detection and accurate identification of thyroid nodules are the major challenges in controlling and treating thyroid cancer that can be difficult even for expert physicians. Currently, many computer-aided diagnosis (CAD) systems have been developed to assist this clinical process. However, most of these systems are unable to well capture geometrically diverse thyroid nodule representations from ultrasound images with subtle and various characteristic differences, resulting in suboptimal diagnosis and lack of clinical interpretability, which may affect their credibility in the clinic. In this context, a novel end-to-end network equipped with a deformable attention network and a distillation-driven interaction aggregation module (DIAM) is developed for thyroid nodule identification. The deformable attention network learns to identify discriminative features of nodules under the guidance of the deformable attention module (DAM) and an online class activation mapping (CAM) mechanism and suggests the location of diagnostic features to provide interpretable predictions. DIAM is designed to take advantage of the complementarities of adjacent layers, thus enhancing the representation capabilities of aggregated features; driven by an efficient self-distillation mechanism, the identification process is complemented with more multi-scale semantic information to calibrate the diagnosis results. Experimental results on a large dataset with varying nodule appearances show that the proposed network can achieve competitive performance in nodule diagnosis and provide interpretability suitable for clinical needs.

Exosome Liberation by Human Neutrophils under L-Amino Acid Oxidase of Calloselasma rhodostoma Venom Action.

L-Amino acid oxidase (LAAO) is an enzyme found in snake venom that has multifaceted effects, including the generation of hydrogen peroxide (H2O2) during oxidative reactions, leading to various biological and pharmacological outcomes such as apoptosis, cytotoxicity, modulation of platelet aggregation, hemorrhage, and neutrophil activation. Human neutrophils respond to LAAO by enhancing chemotaxis, and phagocytosis, and releasing reactive oxygen species (ROS) and pro-inflammatory mediators. Exosomes cellular nanovesicles play vital roles in intercellular communication, including immune responses. This study investigates the impact of Calloselasma rhodostoma snake venom-derived LAAO (Cr-LAAO) on human neutrophil exosome release, including activation patterns, exosome formation, and content. Neutrophils isolated from healthy donors were stimulated with Cr-LAAO (100 μg/mL) for 3 h, followed by exosome isolation and analysis. Results show that Cr-LAAO induces the release of exosomes with distinct protein content compared to the negative control. Proteomic analysis reveals proteins related to the regulation of immune responses and blood coagulation. This study uncovers Cr-LAAO's ability to activate human neutrophils, leading to exosome release and facilitating intercellular communication, offering insights into potential therapeutic approaches for inflammatory and immunological disorders.