Multi-Task Diffusion Approach For Prediction of Glioma Tumor Progression

2025-09-13

AI Summary

Glioma progression prediction is challenging due to sparse, irregular, and incomplete longitudinal MRI acquisitions in clinical follow-up. This paper proposes a multi-task diffusion framework enabling pixel-wise evolutionary forecasting at arbitrary time points—jointly generating future FLAIR images and probabilistic evolution maps based on signed distance fields (SDFs). Key innovations include: (1) a time-agnostic multi-task diffusion backbone; (2) a pre-trained deformation module to model irregular temporal intervals; (3) a radiotherapy-weighted focal loss integrating dose maps to emphasize learning in critical regions; and (4) synergistic integration of SDF representation, deformation field modeling, and targeted data augmentation for missing-modality imputation and synthetic follow-up sequence generation. Using only two early scans, the method produces flexible temporal risk maps, significantly improving prediction stability and accuracy under sparse-data conditions on both public and private datasets.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multimodal Learning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Glioma, an aggressive brain malignancy characterized by rapid progression and its poor prognosis, poses significant challenges for accurate evolution prediction. These challenges are exacerbated by sparse, irregularly acquired longitudinal MRI data in clinical practice, where incomplete follow-up sequences create data imbalances and make reliable modeling difficult. In this paper, we present a multitask diffusion framework for time-agnostic, pixel-wise prediction of glioma progression. The model simultaneously generates future FLAIR sequences at any chosen time point and estimates spatial probabilistic tumor evolution maps derived using signed distance fields (SDFs), allowing uncertainty quantification. To capture temporal dynamics of tumor evolution across arbitrary intervals, we integrate a pretrained deformation module that models inter-scan changes using deformation fields. Regarding the common clinical limitation of data scarcity, we implement a targeted augmentation pipeline that synthesizes complete sequences of three follow-up scans and imputes missing MRI modalities from available patient studies, improving the stability and accuracy of predictive models. Based on merely two follow-up scans at earlier timepoints, our framework produces flexible time-depending probability maps, enabling clinicians to interrogate tumor progression risks at any future temporal milestone. We further introduce a radiotherapy-weighted focal loss term that leverages radiation dose maps, as these highlight regions of greater clinical importance during model training. The proposed method was trained on a public dataset and evaluated on an internal private dataset, achieving promising results in both cases

Problem

• Predicting glioma progression using sparse longitudinal MRI data
• Generating future FLAIR sequences and tumor evolution maps
• Addressing data scarcity through targeted augmentation techniques

Innovation

• Multitask diffusion framework for glioma progression
• Pretrained deformation module for temporal dynamics
• Targeted augmentation pipeline for data scarcity