Fully sparse fusion makes an excellent balance between efficiency and accuracy in multi-modal 3D object detection. However, most existing methods focus on foreground objects while overlooking background context. This oversight compromises detection robustness, especially for occluded or small-sized objects, leading to suboptimal detection performance. To address this limitation, we propose a novel fully sparse fusion framework (PLPFusion), which introduces a hierarchical Plane-Line-Pixel representation to progressively model the object-context relationships. PLPFusion comprises three key modules: the Plane Enhancement Module (PEM), the Line Alignment Module (LAM) and the Pixel-Level Aggregation Module (PLAM). Firstly, PEM utilizes geometric cues from LiDAR feature planes to generate spatially-aware object queries. Secondly, LAM further refines these queries with geometric priors for semantic awareness. Lastly, PLAM aggregates pixel-level context to enhance discriminative completeness by leveraging the semantically-aware object queries. On the nuScenes benchmark, PLPFusion achieves 71.9% mAP and 74.0% NDS, outperforming the baseline method FUTR3D by +2.5% mAP and +1.9% NDS, respectively. On the KITTI benchmark, it achieves 72.68% BEV mAP and 67.39% 3D mAP. These results confirm its robustness and effectiveness in diverse multi-modal 3D scenarios. The code of PLPFusion is available on the https://github.com/Text357/PLPFusion.

The reconstruction of monocular endoscope video scenes is essential for enhancing the application and analysis of surgical endoscopic images. However, restricted by the narrow space of endoscopic movement and the obstruction of vision within cavities, it is difficult for most conventional methods to perform high-quality reconstruction. To address these challenges, a novel dynamic growing 3D Gaussian splatting architecture is proposed to construct the 3D model of endoscopic scene without precomputed camera poses or Structure from Motion. Firstly, to establish spatial feature associations between interframes, a 2D-3D displacement fields are designed by utilizing dense feature matches and depth prediction. On this basis, a novel displacement field variational optimization is developed to obtain relative poses by minimizing the energy functional associated with field transformation. Secondly, to address the constraint of the endoscopic view, by Gaussian sequential transformation and differential gradient field optimization, a novel Sequential Gaussian Growing Module is proposed to grow the local Gaussian model sequentially. Finally, a novel Forward-Reconstruction&Backward-Optimization architecture is proposed to generate the global Gaussian model. The evaluation is conducted on two public endoscopic datasets: Scared and C3VD. The experimental results demonstrate that the proposed method outperforms state-of-the-art methods in both quantitative metrics (PSNR, SSIM, LPIPS, ATE, RMSE, MAE) and qualitative comparisons. The project page is https://iheckzza.github.io/ DG-3DGS/.

Pelvic fracture reduction planning is clinically critical yet technically demanding due to the complex anatomical structure of pelvis and the topological discontinuities introduced by fractures. Existing computer-assisted planning approaches dominantly rely on shape-based models, overlooking the rich CT intensity information that is essential for accurate and patient-specific planning. To address this limitation, we propose SIRDiff, a novel framework that incorporates anatomical shape and CT intensity information to generate biomechanically plausible reference models for pelvic fracture reduction planning. SIRDiff comprises three key components: 1) the structure-aware diffusion model to reconstruct the global anatomical structure, 2) the topology-adaptive structural conditioning strategy that maps fracture landmarks into a healthy anatomical graph domain for robust structure guidance, and 3) the detail-preserved autoencoder to ensure the fine-grained image reconstruction from latent representations. Additionally, SIRDiff adopts a multi-task learning approach to jointly predict the reference CT image and corresponding bone segmentation map, which enhances its potential for clinical application and ensures better anatomical consistency. Despite being trained exclusively on synthetic fracture data, SIRDiff shows the strong generalizability to real clinical cases and consistently outperforms existing methods across multiple clinically relevant evaluation metrics, demonstrating its potential as a robust and deployable solution for pelvic fracture reduction planning.

Computed tomography (CT) and cone-beam computed tomography (CBCT) image registration play pivotal roles in computer-assisted navigation for orthopedic surgery. Traditional methods often apply uniform deformation models, neglecting the biomechanical differences between rigid structures and soft tissues, which compromises registration accuracy, especially during significant bone displacements. To address this issue, we introduce RE-Reg, a rigid-elastic CT-CBCT image registration framework that jointly learns rigid bone motion and soft tissue deformation. RE-Reg incorporates a rigid alignment (RA) module to estimate global bone motion and an elastic deformation (ED) module to model soft tissue deformation, preserving bony structures through bone shape preservation (BSP) loss. Our comprehensive evaluation on publicly available datasets demonstrates that RE-Reg significantly outperforms existing methods in terms of registration accuracy and rigid bone structure preservation, achieving a 1.3% improvement in Dice similarity coefficient (DSC) and a 23% reduction in rigid bone deformation ( % Δ vol ) compared with the best baseline. This framework not only enhances anatomical fidelity but also ensures biomechanical plausibility and provides a valuable tool for image-guided orthopedic surgery. This code is available at https://github.com/Zq-Huang/RE-Reg.

Surgical navigation has evolved significantly through advances in augmented reality, virtual reality, and mixed reality, improving precision and safety across many clinical applications, including neurosurgery, maxillofacial, spinal, and arthroplasty procedures. By integrating preoperative imaging with real-time intraoperative data, these systems provide dynamic guidance, reduce radiation exposure, and minimize tissue damage. Key challenges persist, including intraoperative registration accuracy, flexible tissue deformation, respiratory compensation, and real-time imaging quality. Emerging solutions include artificial intelligence-driven segmentation, deformation-field modeling, and hybrid registration techniques. Future developments will include lightweight, portable systems, improved non-rigid registration algorithms, and greater clinical adoption. Despite advances in rigid-tissue applications, soft-tissue navigation requires additional innovation to address motion variability and registration reliability, ultimately advancing minimally invasive surgery and precision medicine.

Clinical scoring in X-ray coronary angiography image sequences is widely used for revascularization decision-making in cases of coronary artery disease. Accurately recognizing coronary artery branches is a fundamental step in assessing the severity of quantitative stenosis. Existing methods employ a multistage process that includes view separation, skeletonization, graph building, and classification using topological features. However, the graph often suffers from skeleton errors, leading to incorrect topological connections during the classification stage, which requires manual correction. To address these issues, we propose a unified-stage coronary artery branch recognition network (UniCABR) that integrates the segmentation, skeletonization, and graph-building stages. Specifically, we design a dependency-aware module to build dependency graphs in both semantic and spatial domains, avoiding the use of rigid inter-branch topological connections and thus eliminating the need for manual correction of misconnections resulting from skeleton errors. Furthermore, to suppress nontarget branches according to clinical criteria and enhance the performance of side branches, we introduce a small feature supplementation module coupled with an adaptive merged binary supervision method at the pixel level. Extensive experiments on two datasets and a generalization study demonstrate the superiority of UniCABR in performance and generalization ability for coronary artery branch recognition tasks.

The structured light (SL)-based three-dimensional (3D) measurement techniques with deep learning have been widely studied to improve measurement efficiency, among which fringe projection profilometry (FPP) and speckle projection profilometry (SPP) are two popular methods. However, they generally use a single projection pattern for reconstruction, resulting in fringe order ambiguity or poor reconstruction accuracy. To alleviate these problems, we propose a parallel dual-branch Convolutional Neural Network (CNN)-Transformer network (PDCNet), to take advantage of convolutional operations and self-attention mechanisms for processing different SL modalities. Within PDCNet, a Transformer branch is used to capture global perception in the fringe images, while a CNN branch is designed to collect local details in the speckle images. To fully integrate complementary features, we design a double-stream attention aggregation module (DAAM) that consists of a parallel attention subnetwork for aggregating multi-scale spatial structure information. This module can dynamically retain local and global representations to the maximum extent. Moreover, an adaptive mixture density head with bimodal Gaussian distribution is proposed for learning a representation that is precise near discontinuities. Compared to the standard disparity regression strategy, this adaptive mixture head can effectively improve performance at object boundaries. Extensive experiments demonstrate that our method can reduce fringe order ambiguity while producing high-accuracy results on self-made datasets.

The application of structured light (SL) techniques has achieved remarkable success in three-dimensional (3D) measurements. Traditional methods generally calculate SL information pixel by pixel to obtain the measurement results. Recently, the rise of deep learning (DL) has led to significant developments in this task. However, existing DL-based methods generally learn all features within the image in an end-to-end manner, ignoring the distinction between SL and non-SL information. Therefore, these methods may encounter difficulties in focusing on subtle variations in SL patterns across different scenes, thereby degrading measurement precision. To overcome this challenge, we propose a novel SL Image Planar-Topography Feature Decomposition Network (SIDNet). To fully utilize the information from different SL modality images (fringe and speckle), we decompose different modalities into topography features (modality-specific) and planar features (modality-shared). A physics-driven decomposition loss is proposed to make the topography/planar features dissimilar/similar, which guides the network to distinguish between SL and non-SL information. Moreover, to obtain modality-fused features with global overview and local detail information, we propose a wrapped phase-driven feature fusion module. Specifically, a novel Tri-modality Mamba block is designed to integrate different sources with the guidance of the wrapped phase features. Extensive experiments demonstrate the superiority of our SIDNet in multiple simulated 3D measurement scenes. Moreover, our method shows better generalization ability than other DL models and can be directly applicable to unseen real-world scenes.

Facial point clouds collected in practical applications often suffer from pose variations and occlusion. Existing studies typically focus on either pose estimation or landmarks localization, neglecting to fully utilize the effective information from various facial features, thus limiting the improvement of prediction accuracy. Therefore, we propose an innovative 3D facial multi-task prediction network. The proposed network embeds the output of related tasks into feature extraction from the point level to the global level based on the physical dependencies between tasks. This facilitates explicit multi-task knowledge transfer, enabling the simultaneous prediction of facial landmarks, occlusion, and head pose. We introduce a training strategy based on posterior knowledge correction to iteratively refine and improve multi-task prediction results. Moreover, no single dataset provides annotations for all these tasks at once, so we synthesized a 3D landmarks, occlusion and pose (3D-LOP) dataset, which includes annotations for landmarks coordinates, occlusion probability, and head pose. The proposed method was compared with state-of-the-art methods on two public datasets and 3D-LOP. The landmarks localization accuracy improved by 7.1% on the two public datasets, and the pose estimation accuracy and stability on 3D-LOP improved by 28.5% and 32.7%, respectively. The performance on wild data also shows its potential in practical applications.

Radiology report generation, which automatically generates diagnostic textual reports from medical images, plays a crucial role in improving clinical efficiency and diagnostic accuracy. However, existing radiology report generation models face numerous challenges, such as lack of interpretability as well as description inaccuracy. To address these issues, we propose an integrated framework that enhances radiology report generation by combining target detection with contextual alignment of relevant region descriptions. Target detection focuses on clinically significant areas within medical images, while contextual alignment ensures that the generated text is directly linked to visual findings. Additionally, we introduce a full-spectrum feature fusion method that combines both high- and low-frequency features from the images. This approach captures details and broader structures, allowing the model to gain a more comprehensive and hierarchical understanding of the images. We validated the effectiveness of our method on the public dataset MIMIC-CXR. The results indicate that our method outperforms previous approaches on multiple evaluation metrics. Notably, in terms of the average of the six traditional metrics, our method (VTAG) achieved a significant improvement of 14.3%, compared to the state-of-the-art model MLRG.

Semi-supervised medical image segmentation has made significant strides, yet most existing methods are confined to single-modality data, limiting both the volume of data and the generalizability of the models. Multi-modal data can provide richer information, expand the dataset and enhance model robustness. However, integrating multi-modal learning into semi-supervised medical image segmentation presents challenges, primarily in how to deal with the scarcity of labels and alignment across different modalities simultaneously. In this paper, we propose PrixMatch, a multi-modal semi-supervised model with a teacher-student strategy for medical image segmentation. Initially, we propose a cross-modal data augmentation strategy, which randomly exchanges image blocks of the same location between different modalities, to guide the student model to learn cross-modal consistency without the need for additional network modules. Secondly, we design a cross-modal adaptive pseudo-label threshold setting strategy, which can align the prior anatomical knowledge of different modalities, and combine the modal-aligned prior knowledge and model learning state to filter the pseudo-labels at the pixel-level, flexibly alleviating the confirmation bias that occurs during semi-supervised training. Experiments demonstrate that PrixMatch achieves a Dice Similarity Coefficient (DSC) of 87.2% on the BTCV (CT) and CHAOS (MR) multi-modal datasets with only 10% labeling ratio, bringing nearly 5.5% improvement over the latest state-of-the-art method.

In recent years, 4D medical image involving structural and motion information of tissue has attracted increasing attention. The key to the 4D image reconstruction is to stack the 2D slices based on matching the aligned motion states. In this study, the distribution of the 2D slices with the different motion states is modeled as a manifold graph, and the reconstruction is turned to be the graph alignment. An embedding-alignment fusion-based graph convolution network (GCN) with a mixed-learning strategy is proposed to align the graphs. Herein, the embedding and alignment processes of graphs interact with each other to realize a precise alignment with retaining the manifold distribution. The mixed strategy of self- and semi-supervised learning makes the alignment sparse to avoid the mismatching caused by outliers in the graph. In the experiment, the proposed 4D reconstruction approach is validated on the different modalities including Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Ultrasound (US). We evaluate the reconstruction accuracy and compare it with those of state-of-the-art methods. The experiment results demonstrate that our approach can reconstruct a more accurate 4D image.

Disease knowledge graphs have emerged as a powerful tool for artificial intelligence to connect, organize, and access diverse information about diseases. Relations between disease concepts are often distributed across multiple datasets, including unstructured plain text datasets and incomplete disease knowledge graphs. Extracting disease relations from multimodal data sources is thus crucial for constructing accurate and comprehensive disease knowledge graphs. We introduce REMAP, a multimodal approach for disease relation extraction. The REMAP machine learning approach jointly embeds a partial, incomplete knowledge graph and a medical language dataset into a compact latent vector space, aligning the multimodal embeddings for optimal disease relation extraction. Additionally, REMAP utilizes a decoupled model structure to enable inference in single-modal data, which can be applied under missing modality scenarios. We apply the REMAP approach to a disease knowledge graph with 96,913 relations and a text dataset of 1.24 million sentences. On a dataset annotated by human experts, REMAP improves language-based disease relation extraction by 10.0% (accuracy) and 17.2% (F1-score) by fusing disease knowledge graphs with language information. Furthermore, REMAP leverages text information to recommend new relationships in the knowledge graph, outperforming graph-based methods by 8.4% (accuracy) and 10.4% (F1-score). REMAP is a flexible multimodal approach for extracting disease relations by fusing structured knowledge and language information. This approach provides a powerful model to easily find, access, and evaluate relations between disease concepts.

Automatic liver tumor segmentation plays a key role in radiation therapy of hepatocellular carcinoma. In this paper, we propose a novel densely connected U-Net model with criss-cross attention (CC-DenseUNet) to segment liver tumors in computed tomography (CT) images. The dense interconnections in CC-DenseUNet ensure the maximum information flow between encoder layers when extracting intra-slice features of liver tumors. Moreover, the criss-cross attention is used in CC-DenseUNet to efficiently capture only the necessary and meaningful non-local contextual information of CT images containing liver tumors. We evaluated the proposed CC-DenseUNet on the LiTS dataset and the 3DIRCADb dataset. Experimental results show that the proposed method reaches the state-of-the-art performance for liver tumor segmentation. We further experimentally demonstrate the robustness of the proposed method on a clinical dataset comprising 20 CT volumes.

Automatic segmentation of port-wine stains (PWS) from clinical images is critical for accurate diagnosis and objective assessment of PWS. However, this is a challenging task due to the color heterogeneity, low contrast, and indistinguishable appearance of PWS lesions. To address such challenges, we propose a novel multi-color space adaptive fusion network (M-CSAFN) for PWS segmentation. First, a multi-branch detection model is constructed based on six typical color spaces, which utilizes rich color texture information to highlight the difference between lesions and surrounding tissues. Second, an adaptive fusion strategy is used to fuse complementary predictions, which address the significant differences within the lesions caused by color heterogeneity. Third, a structural similarity loss with color information is proposed to measure the detail error between predicted lesions and truth lesions. Additionally, a PWS clinical dataset consisting of 1413 image pairs was established for the development and evaluation of PWS segmentation algorithms. To verify the effectiveness and superiority of the proposed method, we compared it with other state-of-the-art methods on our collected dataset and four publicly available skin lesion datasets (ISIC 2016, ISIC 2017, ISIC 2018, and PH2). The experimental results show that our method achieves remarkable performance in comparison with other state-of-the-art methods on our collected dataset, achieving 92.29% and 86.14% on Dice and Jaccard metrics, respectively. Comparative experiments on other datasets also confirmed the reliability and potential capability of M-CSAFN in skin lesion segmentation.

Lung cancer is with the highest morbidity and mortality, and early detection of cancerous changes is essential to reduce the risk of death. To achieve this, it is necessary to reduce the false positive rate of detection. In this paper, we propose a novel asymmetric residual network, called 3D ARCNN, to reduce false positive rate of lung nodules detection. 3D ARCNN consists of asymmetric convolutional and multilayer cascaded residual network structures. To solve the problem of deep neural network with large amounts of parameters and poor reproduction ability, the proposed model uses asymmetric convolution to reduce model parameters and enhance the generalization ability of the model. In addition, the model uses an internally cascaded multi-stage residual to prevent the gradient vanishing and exploding problems of deep networks. Experiments are performed on the public dataset LUNA16. Our method achieved high detection sensitivity of 91.6%, 92.7%, 93.2% and 95.8% at 1, 2, 4 and 8 false positives per scan, respectively, which got an average CPM index of 0.912. Experimental results show that the proposed 3D ARCNN is very useful for reducing the false positive rate of lung nodules in the clinic.

OBJECTIVE: Electronic Health Record (EHR) based phenotyping is a crucial yet challenging problem in the biomedical field. Though clinicians typically determine patient-level diagnoses via manual chart review, the sheer volume and heterogeneity of EHR data renders such tasks challenging, time-consuming, and prohibitively expensive, thus leading to a scarcity of clinical annotations in EHRs. Weakly supervised learning algorithms have been successfully applied to various EHR phenotyping problems, due to their ability to leverage information from large quantities of unlabeled samples to better inform predictions based on a far smaller number of patients. However, most weakly supervised methods are subject to the challenge to choose the right cutoff value to generate an optimal classifier. Furthermore, since they only utilize the most informative features (i.e., main ICD and NLP counts) they may fail for episodic phenotypes that cannot be consistently detected via ICD and NLP data. In this paper, we propose a label-efficient, weakly semi-supervised deep learning algorithm for EHR phenotyping (WSS-DL), which overcomes the limitations above. MATERIALS AND METHODS: WSS-DL classifies patient-level disease status through a series of learning stages: 1) generating silver standard labels, 2) deriving enhanced-silver-standard labels by fitting a weakly supervised deep learning model to data with silver standard labels as outcomes and high dimensional EHR features as input, and 3) obtaining the final prediction score and classifier by fitting a supervised learning model to data with a minimal number of gold standard labels as the outcome, and the enhanced-silver-standard labels and a minimal set of most informative EHR features as input. To assess the generalizability of WSS-DL across different phenotypes and medical institutions, we apply WSS-DL to classify a total of 17 diseases, including both acute and chronic conditions, using EHR data from three healthcare systems. Additionally, we determine the minimum quantity of training labels required by WSS-DL to outperform existing supervised and semi-supervised phenotyping methods. RESULTS: The proposed method, in combining the strengths of deep learning and weakly semi-supervised learning, successfully leverages the crucial phenotyping information contained in EHR features from unlabeled samples. Indeed, the deep learning model's ability to handle high-dimensional EHR features allows it to generate strong phenotype status predictions from silver standard labels. These predictions, in turn, provide highly effective features in the final logistic regression stage, leading to high phenotyping accuracy in notably small subsets of labeled data (e.g. n = 40 labeled samples). CONCLUSION: Our method's high performance in EHR datasets with very small numbers of labels indicates its potential value in aiding doctors to diagnose rare diseases as well as conditions susceptible to misdiagnosis.

The automatic segmentation of liver and tumor is important for hepatic tumor surgery. In this paper, we propose a novel densely connected U-Net (CC-DenseUNet), which integrates criss-cross attention (CCA) module, to segment the liver and tumor in computed tomography (CT) volumes. The dense interconnections in CC-DenseUNet ensure the maximum information flow between encoder layers when extracting intraslice features of liver and tumors. Moreover, the CCA module is used in CC-DenseUNet to efficiently capture only the necessary and meaningful non-local contextual information of CT images containing liver or tumors. We evaluated the proposed CCDenseUNet on the Liver Tumor Segmentation Challenge and 3DIRCADb datasets. Experimental results show that our method outperformed the state-of-the-art methods in liver tumor segmentation and achieved a highly competitive performance in liver segmentation.

The ability to avoid collisions with moving obstacles, such as commercial aircraft is critical to the safe operation of unmanned aerial vehicles (UAVs) and other air traffic. This paper presents the design and implementation of sampling-based path planning methods for a UAV to avoid collision with commercial aircraft and other moving obstacles. In detail, the authors develop and demonstrate a method based on the closed-loop rapidly-exploring random tree algorithm and three variations of it. The variations are: 1) simplification of trajectory generation strategy; 2) utilization of intermediate waypoints; 3) collision prediction using reachable set. The methods were validated in software-in-the-loop simulations, hardware-in-the-loop simulations, and real flight experiments. It is shown that the algorithms are able to generate collision free paths in real time for the different types of UAVs among moving obstacles of different numbers, approaching angles, and speeds.

We present the design and implementation of an aircraft collision avoidance algorithm for Unmanned Aerial Vehicles (UAVs). Automatic Dependent Surveillance-Broadcast (ADS-B) is used to detect aircraft. The UAV needs to fly through pre-assigned waypoints while avoiding collisions with other aircraft. The aircraft are indifferent to the UAV. A collision with aircraft are detected by simulating the UAV's trajectory along the path of assigned waypoints using its closed-loop dynamics. A sampling based algorithm is used for collision avoidance path planning. A second collision check is performed on the generated path with the updated UAV and aircraft's states. The path will be re-planned if it leads to a collision. The algorithm was validated in Software-In-the-Loop Simulation (SITL). ADS-B data obtained from commercial aircraft flying over the Phoenix Skyharbor airport were used for simulating the collisions. The paper shows that the algorithm enables the UAV to avoid multiple aircraft with different approaching angles and speeds.

We experimentally evaluated the efficacy of various autonomous supervised classification techniques for detecting transient geophysical phenomena. We demonstrated methods of detecting volcanic plumes on the planetary satellites Io and Enceladus using spacecraft images from the Voyager, Galileo, New Horizons, and Cassini missions. We successfully detected 73–95% of known plumes in images from all four mission datasets.Additionally, we showed that the same techniques are applicable to differentiating geologic features, such as plumes and mountains, which exhibit similar appearances in images.

We present a fast, robust road detection algorithm for aerial images taken from an Unmanned Aerial Vehicle. A histogram-based adaptive threshold algorithm is used to detect possible road regions in an image. A probabilistic hough transform based line segment detection combined with a clustering method is implemented to further extract the road. The proposed algorithm has been extensively tested on desert and urban images obtained using an Unmanned Aerial Vehicle. Our results indicate that we are able to successfully and accurately detect roads in 97% of the images. We experimentally validated our algorithm on over ten thousand (10,000) aerial images obtained using our UAV. These images consist of intersecting roads, bifurcating roads and roundabouts in various conditions with significant changes in lighting and intensity. Our algorithm is able to successfully detect single roads effectively in almost all the images. It is also able to detect at least one road in over 95% of the images containing bifurcating or intersecting roads.