no code implementations • 27 Apr 2024 • Zhongzhen Huang, Kui Xue, Yongqi Fan, Linjie Mu, Ruoyu Liu, Tong Ruan, Shaoting Zhang, Xiaofan Zhang
With experimental results, we show that our framework brings notable performance improvements and surpasses the previous counterparts in the evidence retrieval process in terms of evidence retrieval accuracy.
no code implementations • 23 Apr 2024 • Qiao Deng, Zhongzhen Huang, Yunqi Wang, Zhichuan Wang, Zhao Wang, Xiaofan Zhang, Qi Dou, Yeung Yu Hui, Edward S. Hui
Medical vision-language pre-training has emerged as a promising approach for learning domain-general representations of medical image and text.
1 code implementation • 12 Mar 2024 • Linrui Dai, Rongzhao Zhang, Zhongzhen Huang, Xiaofan Zhang
Secondly, our Conditional Image Generator autoregressively generates CT slices conditioned on a corresponding mask slice to incorporate both style information and anatomical guidance.
no code implementations • 4 Mar 2024 • Zhongzhen Huang, Linda Wei, Shaoting Zhang, Xiaofan Zhang
Combining images from multi-modalities is beneficial to explore various information in computer vision, especially in the medical domain.
1 code implementation • 7 Dec 2023 • Yankai Jiang, Zhongzhen Huang, Rongzhao Zhang, Xiaofan Zhang, Shaoting Zhang
The long-tailed distribution problem in medical image analysis reflects a high prevalence of common conditions and a low prevalence of rare ones, which poses a significant challenge in developing a unified model capable of identifying rare or novel tumor categories not encountered during training.
no code implementations • CVPR 2023 • Zhongzhen Huang, Xiaofan Zhang, Shaoting Zhang
Radiology report generation aims to automatically generate a clinically accurate and coherent paragraph from the X-ray image, which could relieve radiologists from the heavy burden of report writing.
no code implementations • 31 Jul 2022 • Zhipeng Zhang, Zhimin Wei, Zhongzhen Huang, Rui Niu, Peng Wang
However, one unsolved issue of these models is that the number of reasoning steps needs to be pre-defined and fixed before inference, ignoring the varying complexity of expressions.
no code implementations • 7 May 2022 • Zhipeng Zhang, Xinglin Hou, Kai Niu, Zhongzhen Huang, Tiezheng Ge, Yuning Jiang, Qi Wu, Peng Wang
Therefore, we present a dataset, E-MMAD (e-commercial multimodal multi-structured advertisement copywriting), which requires, and supports much more detailed information in text generation.