Survival Analysis for Multimode Ablation Using Self-Adapted Deep Learning Network Based on Multisource Features

Novel multimode thermal therapy by freezing before radio-frequency heating has achieved a desirable therapeutic effect in liver cancer. Compared with surgical resection, ablation treatment has a relatively high risk of tumor recurrence. To monitor tumor progression after ablation, we developed a novel survival analysis framework for survival prediction and efficacy assessment. We extracted preoperative and postoperative MRI radiomics features and vision transformer-based deep learning features. We also combined the immune features extracted from peripheral blood immune responses using flow cytometry and routine blood tests before and after treatment. We selected features using random survival forest and improved the deep Cox mixture (DCM) for survival analysis. To properly accommodate multitype input features, we proposed a self-adapted fully connected layer for locally and globally representing features. We evaluated the method using our clinical dataset. Of note, the immune features rank the highest feature importance and contribute significantly to the prediction accuracy. The results showed a promising C $^{\mathit{td}}$ -index of 0. 885 $\pm$ 0. 040 and an integrated Brier score of 0. 041 $\pm$ 0. 014, which outperformed state-of-the-art method combinations of survival prediction. For each patient, individual survival probability was accurately predicted over time, which provided clinicians with trustable prognosis suggestions.

Authors

• Ziqi Zhao
• Wentao Li Tsinghua University
• Ping Liu Center for Frontier AI Research, IHPC, A*STAR, Singapore
• Aili Zhang
• Jianqi Sun
• Lisa X. Xu

Keywords

• Feature extraction
• Tumors
• Immune system
• Deep learning
• Predictive models
• Radiomics
• Biomedical imaging
• Survival Analysis
• Prediction Accuracy
• Random Forest
• Input Features
• Feature Learning
• Survival Probability
• Predictor Of Survival
• Individual Survival
• Deep Features
• Individual Probability
• Routine Blood Tests
• Immune Characteristics
• Prediction Framework
• Radio Frequency Heating
• Preoperative Characteristics
• Radiomic Features
• Brier Score
• Peripheral Immune Response
• Deep Learning Features
• Vision Transformer
• Low-risk Group
• Convolutional Neural Network
• Survival Prediction Model
• Complex Nonlinear Relationships
• Risk Score
• Combination Of Features
• Overall Survival
• Prediction Model
• Radiofrequency Ablation
• immune feature
• multimode ablation
• Humans
• Liver Neoplasms
• Magnetic Resonance Imaging
• Female
• Male
• Ablation Techniques
• Middle Aged