Multitask deep learning model based on multimodal data for predicting prognosis of rectal cancer: a multicenter
Qiong Ma1,2, Runqi Meng3, Ruiting Li1,2
1Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, China.
BMC Medical Informatics and Decision Making
|June 5, 2025
Summary
A new deep learning model accurately predicts recurrence, metastasis, and survival in rectal cancer patients using MRI and clinical data. This tool aids in personalized treatment strategies and risk stratification.
Area of Science:
- Oncology
- Radiology
- Artificial Intelligence
Background:
- Accurate prognostic prediction is vital for personalized rectal cancer treatment.
- Developing advanced predictive models is essential for improving patient outcomes.
Purpose of the Study:
- To develop and validate a multitask deep learning model for predicting prognosis in rectal cancer patients.
- To assess the model's ability to predict recurrence/metastasis and disease-free survival (DFS).
Main Methods:
- A retrospective study of 321 rectal cancer patients undergoing total mesorectal excision.
- A multitask deep learning model integrating clinicopathologic data and multiparametric MRI (including DKI) was developed.
- Model performance was evaluated using ROC curves and C-index, without tumor segmentation.
Main Results:
- The model demonstrated strong predictive performance for recurrence/metastasis (AUCs: 0.885-0.797) and DFS (C-indices: 0.812-0.733) across training and testing sets.
- Patients were successfully stratified into distinct high- and low-risk groups (p < 0.05).
Conclusions:
- The multitask deep learning model effectively predicts recurrence/metastasis and survival in rectal cancer.
- The model shows potential as a tool for risk stratification and guiding individualized treatment decisions.
More Related Videos
Related Concept Videos
02:43Mouse Models of Cancer Study
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
02:43Mouse Models of Cancer Study
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
01:21Cancer Survival Analysis
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...