Problem
Research questions and friction points this paper is trying to address.
Survival Analysis
Non-Small Cell Lung Cancer
FDG-PET/CT
Overall Survival
Time-driven Prediction
Time-driven Survival Analysis from FDG-PET/CT in Non-Small Cell Lung Cancer
🤖 AI Summary
This study proposes a deep regression framework based on medical imaging for continuous-time prediction of overall survival in non-small cell lung cancer patients, aiming to support prognostic assessment and personalized treatment. The method uniquely incorporates time as a continuous variable within an imaging-based survival analysis model, dynamically integrating image embeddings extracted by ResNet-50 from FDG-PET/CT scans with clinical scalar features. To enhance interpretability and performance, the framework employs saliency heatmaps and a multimodal ensemble strategy. Experimental results demonstrate an AUC of 0.788, representing a 4.3% improvement over baseline models, and effective stratification of high- and low-risk patients. Notably, saliency heatmaps confirm that the model’s predictions are grounded in tumor regions, underscoring its clinical interpretability and biological plausibility.
📝 Abstract
Purpose: Automated medical image-based prediction of clinical outcomes, such as overall survival (OS), has great potential in improving patient prognostics and personalized treatment planning. We developed a deep regression framework using tissue-wise FDG-PET/CT projections as input, along with a temporal input representing a scalar time horizon (in days) to predict OS in patients with Non-Small Cell Lung Cancer (NSCLC).
Methods: The proposed framework employed a ResNet-50 backbone to process input images and generate corresponding image embeddings. The embeddings were then combined with temporal data to produce OS probabilities as a function of time, effectively parameterizing the predictions based on time. The overall framework was developed using the U-CAN cohort (n = 556) and evaluated by comparing with a baseline method on the test set (n = 292). The baseline utilized the ResNet-50 architecture, processing only the images as input and providing OS predictions at pre-specified intervals, such as 2- or 5-year.
Results: The incorporation of temporal data with image embeddings demonstrated an advantage in predicting OS, outperforming the baseline method with an improvement in AUC of 4.3%. The proposed model using clinical + IDP features achieved strong performance, and an ensemble of imaging and clinical + IDP models achieved the best overall performance (0.788), highlighting the complementary value of multimodal inputs. The proposed method also enabled risk stratification of patients into distinct categories (high vs low risk). Heat maps from the saliency analysis highlighted tumor regions as key structures for the prediction.
Conclusion: Our method provided an automated framework for predicting OS as a function of time and demonstrates the potential of combining imaging and tabular data for improved survival prediction.
Innovation
Methods, ideas, or system contributions that make the work stand out.
time-driven survival analysis
deep regression framework
FDG-PET/CT
multimodal fusion
continuous-time prediction
🔎 Similar Papers
No similar papers found.
