高峰(研究员,博士生导师)

研究方向:本团队致力于构建“AI原生未来医院”(AI-Native Future Hospital)的技术底座。 面对医疗资源供需失衡的结构性矛盾,我们确立了 “协同智能(Collaborative Intelligence)” 核心战略,超越传统的辅助诊疗工具研发,聚焦于多智能体协作(Multi-Agent Orchestration) 与下一代大模型架构的探索。我们的核心目标是研发具备独立决策能力与边界感知能力的AI医生(AI Doctor 3.0),推动医疗服务从“被动医疗”向“主动健康管理”的范式转移,实现“AI主导基础流量,人类专家负责高阶决策”的人机协同新模式。

主要技术方向包括:

  • 医疗认知智能体(决策大脑): 摒弃易产生幻觉的传统端到端模型,前瞻性布局“无限上下文”与“思维链解耦” 架构。通过将临床指南与循证医学证据外挂为动态知识库,构建透明、可溯源的Agent编排系统,实现对复杂临床任务的自主拆解与推理。
  • 医学多模态基础模型(全维感知): 针对医学数据标注瓶颈,利用自监督学习(SSL) 构建通用的医学视觉与语言基座(如CRCFound)。通过多模态对齐技术,打破影像像素空间与基因序列空间的壁垒,实现对患者全生命周期数据的全维语义理解。
  • 智能外科计算(外科操作): 遵循从 “增强智能” 向 “具身智能” 演进的路径。近期聚焦于基于动态场景感知(如SegMamba-V2)的AR手术导航,为医生提供“透视视野”;远期致力于构建手术机器人的“认知地图”,实现从视觉辅助向手术动作自动化执行的跨越。
  • 可解释组学挖掘(机制洞察): 坚持“可解释性优先” 。研发稀疏化、模块化的神经网络架构(如TMO-Net),确保AI模型的预测结果能映射至具体的基因通路与病理生理学机制,不仅提供精准预测,更驱动医学科学发现(AI for Science)。
课题组主页:fenggaolab.org


个人介绍:中山大学百人计划引进人才,现任国家智能社会治理实验专家组成员、上海人工智能实验室顾问科学家、香港科技大学(广州)BSBE学域兼任副教授。同时担任多家国际SCI期刊(如CCDT、Life、Frontiers等)的客座主编。作为国际癌症基因组联盟(ICGC-ARGO)肠癌项目数据分析负责人,高峰研究员领导团队建立了涵盖患者全生命周期的PB级大数据及分析平台。团队目前正致力于“AI原生未来医院” 的顶层设计与构建,重点研发下一代医疗智能体系统(AI Doctor 3.0)。近年来,在 Gastroenterology, Hepatology, Medical Image Analysis, Nature Communications, Advanced Science 等顶级国际期刊发表SCI论文 60余篇(总影响因子超过 600分,其中影响因子大于10的论文 27篇)。开发了 3D RP-Net, TMO-Net, Brim, CRCFound 等多项具有影响力的医学AI算法与工具。已获授权国家发明专利 17项。曾获中山大学第六届“芙兰奖”(团队成员)和WILEY威立中国开放科学2022年度作者奖。


代表性论文代表性项目荣誉

1.PCsRNAdb: a comprehensive resource of small noncoding RNAs across cancers, Nucleic Acids Research, 2025

2.Personalized risk strati cation in colorectal cancer via PIANOS system, Nature Communications, 2025
3.SegMamba-V2: Long-range Sequential ModelingMamba For General 3D Medical Image Segmentation, IEEE Transactions on Medical Imaging, 2025
4.CRCFound: A Colorectal Cancer CT Image Foundation Model Based on Self-Supervised Learning, Advanced Sciences, 2025
5.Interpretable Multimodal Fusion Model for Bridged Histology and Genomics Survival Prediction in Pan-Cancer, Advanced Science, 2025
6.Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis, Genomics Proteomics and Bioinformatics, 2025
7.Immunological microenvironment differences between left and right colon cancer: dynamic interactions of CASC15+ KLK6+ epithelial subpopulation with T cells and mast cells, International Journal of Surgery, 2025
8.Lactylation of SLC26A3 in the Acidic Tumor Microenvironment Promotes Malignant Progression of Colorectal Carcinoma, Cell Death & Disease, 2025
9.TMO-Net: An Explainable Pretrained Multi-omics Model for Multi-task Learning in Oncology, Genome Biology, 2024
10.Deciphering Tertiary Lymphoid Structure Heterogeneity Reveals Prognostic Signature and Therapeutic Potentials for Colorectal Cancer: A Multicenter Retrospective Cohort Study, International Journal of Surgery, 2024
11.Senescence‐based Colorectal Cancer Subtyping Reveals Distinct Molecular Characteristics and Therapeutic Strategies, MedComm, 2023
12.A Longitudinal MRI-based Artificial Intelligence System to Predict Pathological Complete Response after Neoadjuvant Therapy in Rectal Cancer: A Multicenter Validation Study, Diseases of the Colon & Rectum, 2023
13.The Growth Pattern of Liver Metastases on MRI Predicts Early Recurrence in Patients with Colorectal Cancer: A Multicenter Study, European Radiology, 2022
14.Segmentation Only Uses Sparse Annotations: Unified Weakly and Semi-supervised Learning in Medical Images, Medical Image Analysis, 2022
15.CT-based Radiogenomic Analysis Dissects Intratumor Heterogeneity and Predicts Prognosis of Colorectal Cancer: A Multi-institutional Retrospective Study, Journal of Translational Medicine, 2022
16.A Novel Cell‐free DNA Methylation‐based Model Improves the Early Detection of Colorectal Cancer, Molecular Oncology, 2021
17.Predicting Treatment Response from Longitudinal Images Using Multi-task Deep Learning, Nature Communications, 2021
18.Genome-wide Discovery of a Novel Gene-expression Signature for the Identification of Lymph Node Metastasis in Esophageal Squamous Cell Carcinoma, Annals of Surgery, 2019
19.Long-read RNA Sequencing Identifies Alternative Splice Variants in Hepatocellular Carcinoma and Tumor-specific Isoforms, Hepatology, 2019
20.DeepCC: A Novel Deep Learning-based Framework for Cancer Molecular Subtype Classification, Oncogenesis, 2019
21.A Genome-wide Transcriptomic Approach Identifies a Novel Gene Expression Signature for the Detection of Lymph Node Metastasis in Patients with Early-stage Gastric Cancer, EBioMedicine, 2019
22.RNAMethyPro: A Biologically Conserved Signature of N6-methyladenosine Regulators for Predicting Survival at Pan-cancer Level, NPJ Precision Oncology, 2019
23.Gene Expression Signature in Surgical Tissues and Endoscopic Biopsies Identifies High-risk T1 Colorectal Cancers, Gastroenterology, 2019
24.Genome-wide Discovery and Identification of a Novel miRNA Signature for Recurrence Prediction in Stage II and III Colorectal Cancer, Clinical Cancer Research, 2018
25.A microRNA signature associated with metastasis of T1 colorectal cancers to lymph nodes, Gastroenterology, 2018