Zhenghua Xu

MEC: Medical Evidence Capsules for Retrieval-Augmented Generation in Medical Multimodal Question Answering

Zhenghua Xu, Xinwei Dai, Bo Wang, Tian Tian

cn (code pays fourni par la source)

Novel 12S/16S rRNA Markers for Quantitative Metabarcoding of Mammalian Mixtures

Pei Yu, Changxin Wang, Yuanfeng Liu, Zhenghua Xu et autres

cn (code pays fourni par la source)

Label space compression and prompt alignment for collaborative inference with small and large language models

Bo Li, Zhenghua Xu, Shikun Zhang, Wei Ye

cn (code pays fourni par la source)

Advancing federated semi-supervised medical image segmentation: A duo of interactive denoising pseudo-labels and convolutional contrastive learning

Zhenghua Xu, Yujun Zhang, Bo Li, Gaoxi Zhou et autres

cn, at (code pays fourni par la source)

Semi-supervised medical image lesion detection based on multi-head feature fusion

Zhenghua Xu, Hexiang Zhang, Runhe Yang, Weipeng Liu et autres

cn, at, gb (code pays fourni par la source)

Federated Learning with Global Model Hint for Medical Image Object Detection

Zhenghua Xu, Gaoxi Zhou, Haitao Zhang, Runhe Yang et autres

Building an ideal medical image object detection model often requires sufficient training data, which can be challenging to obtain in practical scenarios. Manual annotation is labor-intensive, and sharing datasets may raise data privacy concerns. Although federated learning can partially address these issues, …

cn, gb (code pays fourni par la source)

Pseudo-Global Based Sequential Contribution Estimation for Federated Semi-Supervised Medical Image Segmentation

Gaoxi Zhou, Zhenghua Xu, Bo Li, Yujun Zhang et autres

Federated semi-supervised learning (FSSL) for medical image segmentation has been extensively studied in recent years. Due to the requirement of specialized knowledge and equipment for annotating medical data, only a very limited number of medical institutions have a small amount of labeled …

cn, gb (code pays fourni par la source)

AttCL-GAN: Attentional contrastive learning-based generative adversarial network for modality completion of medical images

Zhenghua Xu

cn, at, gb (code pays fourni par la source)

AMLP: Adjustable Masking Lesion Patches for Self-Supervised Medical Image Segmentation

Xiangtao Wang, Ruizhi Wang, Thomas Lukasiewicz, Zhenghua Xu

Self-supervised masked image modeling (MIM) methods have shown promising performances on analyzing natural images. However, directly applying such methods to medical image segmentation tasks still cannot achieve satisfactory results. The challenges arise from the facts that (i) medical images are inherently more …

cn, gb (code pays fourni par la source)

Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG

Bo Li, Tian Tian, Zhenghua Xu, Hao Cheng et autres

Dynamic retrieval-augmented generation (RAG) allows large language models (LLMs) to fetch external knowledge on demand, offering greater adaptability than static RAG. A central challenge in this setting lies in determining the optimal timing for retrieval. Existing methods often trigger retrieval based on …

You Need Glimpse Before Segmentation: Stochastic Detector-Actor-Critic for Medical Image Segmentation

Zhenghua Xu, Yunxin Liu, Di Yuan, Weipeng Liu et autres

Medical images often contain more redundant background areas than natural images, potentially introducing noise and degrading image segmentation performance. Inspired by doctors' diagnostic processes, where they identify the lesion area before conducting a detailed analysis, we introduce a novel Stochastic Detector-Actor-Critic (SDAC) …

cn, gb (code pays fourni par la source)

High-Performance Indigenous Lactiplantibacillus plantarum Strains for Enhanced Malolactic Fermentation and Wine Quality

Yongzhang Zhu, Ni Chen, Zhenghua Xu, Jingyue Liu et autres

Malolactic fermentation (MLF), a key enological process for wine deacidification and aroma and flavor development, is predominantly mediated by lactic acid bacteria. This study characterized 342 indigenous Lactiplantibacillus plantarum (L. plantarum) isolates, a potential starter species underexploited for MLF, from China’s Jiaodong …

cn, us (code pays fourni par la source)