Utilizing Multi-Agent Reinforcement Learning with Encoder-Decoder Architecture Agents to Identify Optimal Resection Location in Glioblastoma Multiforme Patients

2025-12-07

AI Summary

Glioblastoma (GBM), a highly heterogeneous and lethal brain tumor with a dismal 5.1% five-year survival rate, lacks end-to-end AI-driven diagnostic and therapeutic support. To address this gap, we propose the first sequential-decision AI system specifically designed for GBM management. Our method comprises: (i) a lightweight, four-stage multimodal classification framework enabling precise imaging-driven diagnosis; and (ii) a novel feedback-loop-based multi-agent reinforcement learning architecture that integrates diffusion models with spatiotemporal Vision Transformers to generate dynamic preoperative–intraoperative representations, coupled with Proximal Policy Optimization (PPO) for personalized resection planning. The approach reduces computational overhead by 22.3×, accelerates tumor progression inference by 113 hours, improves segmentation Dice score by 2.9%, and is projected to increase patient survival by 0.9%—potentially saving approximately 2,250 lives annually.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Multiagent Systems: Adversarial Agents
• Computer Vision: Diffusion Models for Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Currently, there is a noticeable lack of AI in the medical field to support doctors in treating heterogenous brain tumors such as Glioblastoma Multiforme (GBM), the deadliest human cancer in the world with a five-year survival rate of just 5.1%. This project develops an AI system offering the only end-to-end solution by aiding doctors with both diagnosis and treatment planning. In the diagnosis phase, a sequential decision-making framework consisting of 4 classification models (Convolutional Neural Networks and Support Vector Machine) are used. Each model progressively classifies the patient's brain into increasingly specific categories, with the final step being named diagnosis. For treatment planning, an RL system consisting of 3 generative models is used. First, the resection model (diffusion model) analyzes the diagnosed GBM MRI and predicts a possible resection outcome. Second, the radiotherapy model (Spatio-Temporal Vision Transformer) generates an MRI of the brain's progression after a user-defined number of weeks. Third, the chemotherapy model (Diffusion Model) produces the post-treatment MRI. A survival rate calculator (Convolutional Neural Network) then checks if the generated post treatment MRI has a survival rate within 15% of the user defined target. If not, a feedback loop using proximal policy optimization iterates over this system until an optimal resection location is identified. When compared to existing solutions, this project found 3 key findings: (1) Using a sequential decision-making framework consisting of 4 small diagnostic models reduced computing costs by 22.28x, (2) Transformers regression capabilities decreased tumor progression inference time by 113 hours, and (3) Applying Augmentations resembling Real-life situations improved overall DICE scores by 2.9%. These results project to increase survival rates by 0.9%, potentially saving approximately 2,250 lives.

Problem

• Develops an AI system to assist in diagnosing and planning treatment for Glioblastoma Multiforme.
• Uses reinforcement learning to identify optimal brain tumor resection locations for improved outcomes.
• Aims to increase survival rates by optimizing surgical and therapeutic planning through AI models.

Innovation

• Multi-Agent Reinforcement Learning with encoder-decoder agents for optimal GBM resection
• Sequential decision-making framework of four classification models for efficient diagnosis
• Generative models including diffusion and transformer for treatment planning and feedback