Lung cancer has higher heterogeneity and malignancy than other malignant tumors, and there is always a risk of recurrence and metastasis throughout the entire treatment cycle of lung cancer, especially postoperative recurrence and metastasis in surgical patients, which has always been a clinical difficulty. How to achieve the best decision-making in the whole cycle management of invasive lung cancer is very urgent, and it is necessary to form an intelligent full-life-cycle decision-making intelligent system, especially a perioperative diagnostic and treatment decision-making system. Through standardized preoperative assessment and intelligent standardization, under the premise of tumor radical treatment, it is possible to minimize surgical trauma. Through precise surgery and intraoperative re-evaluation, it is possible to achieve R0 radical resection of tumors and surgical plans that protect functional organs, and digital diagnosis and treatment can bring safe and effective postoperative recovery strategies for patients.
For postoperative recurrence of lung cancer and systemic treatment of advanced lung cancer, comprehensive treatment based on local and systemic treatment on the basis of MDT should be achieved. Intelligent management and dynamic monitoring throughout the entire life cycle will bring the best survival time and quality of life for patients. There is still a considerable proportion of postoperative recurrence and metastasis of lung cancer. After treatment for advanced lung cancer, there is still a risk of local progression, and how to achieve dynamic monitoring of postoperative recurrence and metastasis and effective monitoring of the window period of advanced lung cancer is currently a very important clinical focus. How to achieve preoperative immuno-neoadjuvant therapy and postoperative precise targeted therapy, and effectively achieve dynamic monitoring of ctDNA and minimal residual disease (MRD), will be the top priority in the decision support system for lung cancer diagnosis and treatment.
Based on the multitask generative artificial intelligence model oriented towards diagnosis and treatment, technological innovation enhances the early detection, precise assessment, prognosis prediction, and personalized treatment capabilities for lung cancer. The main unique advantages are as follows:
1. Lung Cancer High-Risk Intelligent Early Warning System, utilizing big data analysis and artificial intelligence technology to achieve early identification and monitoring of high-risk populations for lung cancer; research on precise assessment technology for lung cancer surgical intervention and indications, by in-depth analysis of patients' pathophysiological characteristics and disease progression patterns, providing a scientific basis for the formulation of surgical treatment plans;
2. Research on multimodal lung cancer postoperative metastasis and recurrence prediction models based on clinical imaging and multi-omics, integrating imaging features with genetic and proteomic multi-omics data to construct more accurate predictive models to assist doctors in judging the risk of postoperative metastasis and recurrence in patients;
3. Research on lung cancer systemic intervention (immunotherapy and targeted therapy) drug recommendation models, using machine learning algorithms to analyze patients' genotypes, clinical information, and drug response data, achieving personalized drug selection and recommendation, and improving treatment effectiveness;
4. Integration and system development of precision diagnosis and treatment decision support technologies for the entire life cycle of lung cancer, covering the entire diagnostic and treatment process from early warning, precise assessment, postoperative prediction to personalized treatment recommendation, providing clinical doctors with comprehensive and intelligent decision support, aiming to improve the efficiency of lung cancer diagnosis and treatment and extend the survival period of patients.
Understand the principles and applications of multi-omics data to construct accurate predictive models of lung cancer postoperative metastasis and recurrence.
Develop proficiency in laboratory techniques, such as Big Data Analysis and Artificial Intelligence Technology
Gain experience in clinical trial design and analysis
Cultivate skills in scientific writing and grant preparation
Research ares:
Mechanisms of lung cancer occurrence, development, and metastasis.
Mechanisms of esophageal cancer invasion and metastasis.
Minimally invasive diagnostic and therapeutic technologies for thoracic diseases.
Mechanisms of resistance to targeted drugs in lung cancer.
Projects:
1. Multi-omics data to construct accurate predictive models of lung cancer postoperative metastasis and recurrence.
2. Mechanisms of resistance to targeted drugs in lung cancer.
3. Minimally invasive diagnostic and therapeutic technologies for thoracic cancer
Researcher fellows:
Applicants should have an advanced degree (M.Sc. M.D. Ph.D. or equivalent) in a biomedical discipline with some prior research experience. Candidates must demonstrate an ability to work independently and contribute to team projects. Proficiency in English is essential.
Doctors:
Candidates must hold an M.D. degree with clinical experience, preferably in oncology or internal medicine. Research experience is not mandatory but is a strong advantage. Applicants must be fluent in English.
Postdocs:
Postdoctoral fellows should have a Ph.D. in biomedicine or an M.D. with clinical training in medicine, or the equivalent of education, training and experience. Candidates should be fluent in English.
Duration: 8 weeks
Daily Training Schedule (Example):
Monday:
9:00-10:30 Laboratory meeting
11:00-12:00 Technical training
14:00-17:00 Experimental work
Tuesday:
9:00-12:00 Research experiments
14:00-15:30 Journal club
16:00-17:00 Data analysis
Wednesday:
9:00-12:00 Clinical correlation meeting
14:00-17:00 Laboratory work
Thursday:
9:00-12:00 Research experiments
14:00-15:30 Scientific writing workshop
16:00-17:00 Individual mentoring
Friday:
9:00-10:30 Progress presentation
11:00-12:00 Group discussion
14:00-17:00 Laboratory work
Assessment Methods:
Submission of a final research report summarizing lab work and findings
Practical assessments during wet lab sessions
Certificates provided upon successful completion of the program
Explain how participants can provide feedback about the training experience.
Feedback for Participants:
Participants can submit anonymous feedback via an online form at the end of the program. One-on-one feedback sessions will also be scheduled midway through the program.
The program is free of charge.
Program Coordinator: TENG Xiao
Email: tengxiao@zju.edu.cn
Phone: +86 138 6818 6104