肝胆胰肿瘤复发风险预测及治疗策略推荐方法
By combining clinical, radiomics, and pathological data, and utilizing a multi-task learning model to simultaneously predict the recurrence risk and treatment efficacy of hepatobiliary and pancreatic tumors, the problem of the disconnect between prognostic assessment and treatment decision-making is solved, enabling the generation of personalized diagnosis and treatment reports and improving the precision of hepatobiliary and pancreatic tumor treatment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- TONGJI HOSPITAL ATTACHED TO TONGJI MEDICAL COLLEGE HUAZHONG SCI TECH
- Filing Date
- 2026-06-22
- Publication Date
- 2026-07-17
AI Technical Summary
The lack of an intrinsic data-driven link between existing hepatobiliary and pancreatic tumor risk prediction models and individualized treatment options leads to a disconnect between prognostic assessment and treatment decision-making, limiting the accuracy and scientific rigor of developing optimal individualized treatment strategies in clinical practice.
By acquiring patients' clinical data, medical imaging data, and postoperative pathological data, radiomics features are extracted and combined with pathological data. A multi-task learning model is used to simultaneously output the recurrence risk level and the expected efficacy index of individualized treatment plans for multiple treatment options, generating an individualized diagnosis and treatment report.
It significantly improves the accuracy and robustness of predicting the risk of recurrence after hepatobiliary and pancreatic tumor surgery, establishes an intrinsic data-driven bridge between prognostic assessment and treatment decision-making, and promotes the scientific and precise nature of individualized diagnosis and treatment models.
Smart Images
Figure CN122417433A_ABST