Xiangyu Zhao

Xiangyu Zhao, Di Zang, Sheng Wang et al.

Brain network analysis for traumatic brain injury (TBI) patients is critical for its consciousness level assessment and prognosis evaluation, which requires the segmentation of certain consciousness-related brain regions. However, it is difficult to construct a TBI segmentation model as manually annotated MR scans of TBI patients are hard to collect. Data augmentation techniques can be applied to alleviate the issue of data scarcity. However, conventional data augmentation strategies such as spatial and intensity transformation are unable to mimic the deformation and lesions in traumatic brains, which limits the performance of the subsequent segmentation task. To address these issues, we propose a novel medical image inpainting model named TBI-GAN to synthesize TBI MR scans with paired brain label maps. The main strength of our TBI-GAN method is that it can generate TBI images and corresponding label maps simultaneously, which has not been achieved in the previous inpainting methods for medical images. We first generate the inpainted image under the guidance of edge information following a coarse-to-fine manner, and then the synthesized intensity image is used as the prior for label inpainting. Furthermore, we introduce a registration-based template augmentation pipeline to increase the diversity of the synthesized image pairs and enhance the capacity of data augmentation. Experimental results show that the proposed TBI-GAN method can produce sufficient synthesized TBI images with high quality and valid label maps, which can greatly improve the 2D and 3D traumatic brain segmentation performance compared with the alternatives.

Yuqi Hu, Xiangyu Zhao, Gaowei Qing et al.

Background: MR-based subchondral bone effectively predicts knee osteoarthritis. However, its clinical application is limited by the cost and time of MR. Purpose: We aim to develop a novel distillation-learning-based method named SRRD for subchondral bone microstructural analysis using easily-acquired CT images, which leverages paired MR images to enhance the CT-based analysis model during training. Materials and Methods: Knee joint images of both CT and MR modalities were collected from October 2020 to May 2021. Firstly, we developed a GAN-based generative model to transform MR images into CT images, which was used to establish the anatomical correspondence between the two modalities. Next, we obtained numerous patches of subchondral bone regions of MR images, together with their trabecular parameters (BV / TV, Tb. Th, Tb. Sp, Tb. N) from the corresponding CT image patches via regression. The distillation-learning technique was used to train the regression model and transfer MR structural information to the CT-based model. The regressed trabecular parameters were further used for knee osteoarthritis classification. Results: A total of 80 participants were evaluated. CT-based regression results of trabecular parameters achieved intra-class correlation coefficients (ICCs) of 0.804, 0.773, 0.711, and 0.622 for BV / TV, Tb. Th, Tb. Sp, and Tb. N, respectively. The use of distillation learning significantly improved the performance of the CT-based knee osteoarthritis classification method using the CNN approach, yielding an AUC score of 0.767 (95% CI, 0.681-0.853) instead of 0.658 (95% CI, 0.574-0.742) (p<.001). Conclusions: The proposed SRRD method showed high reliability and validity in MR-CT registration, regression, and knee osteoarthritis classification, indicating the feasibility of subchondral bone microstructural analysis based on CT images.

Kai Li, Xingxing Weng, Yupeng Deng et al.

Extracting polygonal roofs and footprints from remote sensing images is critical for large-scale urban analysis. Most existing methods rely on segmentation-based models that assume clear semantic boundaries of roofs, but these approaches struggle in off- nadir images, where the roof and footprint are significantly displaced, and facade pixels are fused with the roof boundary. With the increasing availability of open vector map annotations, e.g., OpenStreetMap, utilizing historical labels for off-nadir image annotation has become viable because remote sensing images are georeferenced once captured. However, these historical labels commonly suffer from significant positional discrepancies with new images and only have one annotation (roof or footprint), which fails to describe the correct structures of a building. To address these discrepancies, we first introduce a concept of an alignment token, which encodes the correction vector to guide the label correction. Based on this concept, we then propose Drag OpenStreetMap Labels (DragOSM), a novel model designed to align dislocated historical labels with roofs and footprints. Specifically, DragOSM formulates the label alignment as an interactive denoising process, modeling the positional discrepancy as a Gaussian distribution. During training, it learns to correct these errors by simulating misalignment with random Gaussian perturbations; during inference, it iteratively refines the positions of input labels. To validate our method, we further present a new dataset, Repairing Buildings in OSM (ReBO), comprising 179,265 buildings with both OpenStreetMap and manually corrected annotations across 5,473 images from 41 cities. Experimental results on ReBO demonstrate the effectiveness of DragOSM. Code, dataset, and trained models are publicly available at https://github.com/likaiucas/DragOSM.git.

Xinyu Fang, Kangrui Mao, Haodong Duan et al.

The advent of large vision-language models (LVLMs) has spurred research into their applications in multi-modal contexts, particularly in video understanding. Traditional VideoQA benchmarks, despite providing quantitative metrics, often fail to encompass the full spectrum of video content and inadequately assess models' temporal comprehension. To address these limitations, we introduce MMBench-Video, a quantitative benchmark designed to rigorously evaluate LVLMs' proficiency in video understanding. MMBench-Video incorporates lengthy videos from YouTube and employs free-form questions, mirroring practical use cases. The benchmark is meticulously crafted to probe the models' temporal reasoning skills, with all questions human-annotated according to a carefully constructed ability taxonomy. We employ GPT-4 for automated assessment, demonstrating superior accuracy and robustness over earlier LLM-based evaluations. Utilizing MMBench-Video, we have conducted comprehensive evaluations that include both proprietary and open-source LVLMs for images and videos. MMBench-Video stands as a valuable resource for the research community, facilitating improved evaluation of LVLMs and catalyzing progress in the field of video understanding. The evalutation code of MMBench-Video will be integrated into VLMEvalKit: https://github.com/open-compass/VLMEvalKit.

Xiangyu Zhao, Peng Zhang, Fan Song et al.

Coronavirus Disease 2019 (COVID-19) has caused great casualties and becomes almost the most urgent public health events worldwide. Computed tomography (CT) is a significant screening tool for COVID-19 infection, and automated segmentation of lung infection in COVID-19 CT images will greatly assist diagnosis and health care of patients. However, accurate and automatic segmentation of COVID-19 lung infections remains to be challenging. In this paper we propose a dilated dual attention U-Net (D2A U-Net) for COVID-19 lesion segmentation in CT slices based on dilated convolution and a novel dual attention mechanism to address the issues above. We introduce a dilated convolution module in model decoder to achieve large receptive field, which refines decoding process and contributes to segmentation accuracy. Also, we present a dual attention mechanism composed of two attention modules which are inserted to skip connection and model decoder respectively. The dual attention mechanism is utilized to refine feature maps and reduce semantic gap between different levels of the model. The proposed method has been evaluated on open-source dataset and outperforms cutting edges methods in semantic segmentation. Our proposed D2A U-Net with pretrained encoder achieves a Dice score of 0.7298 and recall score of 0.7071. Besides, we also build a simplified D2A U-Net without pretrained encoder to provide a fair comparison with other models trained from scratch, which still outperforms popular U-Net family models with a Dice score of 0.7047 and recall score of 0.6626. Our experiment results have shown that by introducing dilated convolution and dual attention mechanism, the number of false positives is significantly reduced, which improves sensitivity to COVID-19 lesions and subsequently brings significant increase to Dice score.

Jingtong Gao, Ling Pan, Yejing Wang et al.

Reinforcement Learning (RL) has emerged as a pivotal method for improving the reasoning capabilities of Large Language Models (LLMs). However, prevalent RL approaches such as Proximal Policy Optimization (PPO) and Group-Regularized Policy Optimization (GRPO) face critical limitations due to their reliance on sparse outcome-based rewards and inadequate mechanisms for incentivizing exploration. These limitations result in inefficient guidance for reasoning. Specifically, sparse rewards fail to deliver sufficient feedback, particularly for challenging problems. Furthermore, such rewards induce systematic biases that prioritize exploitation of familiar trajectories over novel solution discovery. These shortcomings critically hinder performance in complex reasoning tasks, which inherently demand iterative refinement across intermediate steps. To address these challenges, we propose an Intrinsic Motivation guidEd exploratioN meThOd foR LLM Reasoning (i-MENTOR), a method designed to deliver dense rewards and amplify exploration in the RL-based paradigm. i-MENTOR introduces three innovations: trajectory-aware exploration rewards that mitigate bias in token-level strategies while maintaining computational efficiency; error-conditioned reward allocation to ensure efficient exploration on challenging samples while intrinsically stabilizing training; and advantage-preserving integration that maintains advantage distribution integrity while incorporating exploratory guidance. Experiments across 4 public datasets demonstrate i-MENTOR's effectiveness, achieving a 22.23\% improvement on AIME 2024.

Jiawei Cheng, Jingyuan Wang, Yichuan Zhang et al.

POI representation learning plays a crucial role in handling tasks related to user mobility data. Recent studies have shown that enriching POI representations with multimodal information can significantly enhance their task performance. Previously, the textual information incorporated into POI representations typically involved only POI categories or check-in content, leading to relatively weak textual features in existing methods. In contrast, large language models (LLMs) trained on extensive text data have been found to possess rich textual knowledge. However leveraging such knowledge to enhance POI representation learning presents two key challenges: first, how to extract POI-related knowledge from LLMs effectively, and second, how to integrate the extracted information to enhance POI representations. To address these challenges, we propose POI-Enhancer, a portable framework that leverages LLMs to improve POI representations produced by classic POI learning models. We first design three specialized prompts to extract semantic information from LLMs efficiently. Then, the Dual Feature Alignment module enhances the quality of the extracted information, while the Semantic Feature Fusion module preserves its integrity. The Cross Attention Fusion module then fully adaptively integrates such high-quality information into POI representations and Multi-View Contrastive Learning further injects human-understandable semantic information into these representations. Extensive experiments on three real-world datasets demonstrate the effectiveness of our framework, showing significant improvements across all baseline representations.