
陈旭鑫
研究助理教授
电话:
地址:国际校区C3c 907
邮箱:xuxinchen@scut.edu.cn
2023-2025 埃默里大学医学院温希普癌症研究所,博士后
2022-2023 俄克拉荷马医学影像与癌症转化研究中心,博士后
2017-2022 俄克拉荷马大学,电子与计算机工程,博士
2013-2017 南昌大学,通信工程,学士
医学图像分析,多模态医疗大模型,人工智能医疗诊断、乳腺癌检测与诊断
长期聚焦人工智能乳腺癌诊断技术研究,采用深度学习与领域知识融合的研究思路,提出跨视角的多视图融合架构,设计参数高效的大模型域适配机制,构建基于临床规范的可交互多任务协同诊断框架,突破了人工智能乳腺癌诊断中的知识融入、模型适配和人机交互三大瓶颈,显著提升了诊断准确率与临床可用性。作为核心成员,参与美国 NIH 资助的 P20(1130 万美元)和 R01(250 万美元)项目,负责乳腺癌智能诊断模型的研发工作。迄今发表论文 30 篇(第一作者 10 篇),单篇最高引用近 1000 次,成果入选全球 Top 1% 高被引论文。研究成果两次获 SPIE Medical Imaging 国际人工智能医学影像会议最佳论文奖(2024 年第二名、2025 年前五名),核心技术被 NVIDIA 与哈佛医学院团队采用,并在全球最大规模乳腺癌检测挑战赛(RSNA 主办、Kaggle 承办,145 国 1687 队参赛)中获第四名。在学术服务方面,担任 Bioengineering 期刊客座编辑,并为 Journal of Hematology & Oncology 等多家高水平期刊担任审稿人。
Chen, X., Wang, X., Zhang, K., Fung, K. M., Thai, T. C., Moore, K., Mannel, R. S., Liu, H., Zheng, B., & Qiu, Y. (2022). Recent advances and clinical applications of deep learning in medical image analysis. Medical image analysis, 79, 102444. https://doi.org/10.1016/j.media.2022.102444
Chen, X., Li, Y., Hu, M., Salari, E., Chen, X., Qiu, R. L., Zheng, B., & Yang, X. (2024). Mammo-CLIP: Leveraging contrastive language-image pre-training (CLIP) for enhanced breast cancer diagnosis with multi-view mammography. arXiv preprint arXiv:2404.15946.https://arxiv.org/abs/2404.15946
Chen, X., Zhang, K., Abdoli, N., Gilley, P. W., Wang, X., Liu, H., Zheng, B., & Qiu, Y. (2022). Transformers Improve Breast Cancer Diagnosis from Unregistered Multi-View Mammograms. Diagnostics, 12(7), 1549. https://doi.org/10.3390/diagnostics12071549
Chen, X., Zargari, A., Hollingsworth, A. B., Liu, H., Zheng, B., & Qiu, Y. (2019). Applying a new quantitative image analysis scheme based on global mammographic features to assist diagnosis of breast cancer. Computer methods and programs in biomedicine, 179, 104995. https://doi.org/10.1016/j.cmpb.2019.104995
Chen, X., Liu, W., Thai, T. C., Castellano, T., Gunderson, C. C., Moore, K., Mannel, R. S., Liu, H., Zheng, B., & Qiu, Y. (2020). Developing a new radiomics-based CT image marker to detect lymph node metastasis among cervical cancer patients. Computer methods and programs in biomedicine, 197, 105759. https://doi.org/10.1016/j.cmpb.2020.105759
Chen, X., Hu, M., Zhang, K., Abdoli, N., Sadri, Y., Gilley, P., Chekuri, O. S. V., Omoumi, F. H., Qiu, Y., Zheng, B., & Yang, X. (2024). David vs. Goliath: Large foundation models are not outperforming small models in multi-view mammogram breast cancer prediction. In Proceedings of SPIE Medical Imaging 2024: Computer-Aided Diagnosis (Vol. 12927, 129270X). SPIE. https://doi.org/10.1117/12.3007054