Active Sampling for MRI-based Sequential Decision Making

2025-05-07

AI Summary

To address the challenge of prolonged scan times hindering continuous multi-task diagnosis in point-of-care portable MRI, this paper proposes a k-space active sampling framework tailored for sequential pathological diagnosis. Methodologically, we formulate a multi-objective deep reinforcement learning model that jointly optimizes diagnostic performance for anterior cruciate ligament (ACL) tear detection and cartilage thinning quantification. We introduce a stepwise weighted reward mechanism and a k-space adaptive sampling strategy to enable dynamic, sequential sampling decisions under sparse reward conditions. Our key contribution lies in the first integration of active sampling with clinically sequential diagnostic tasks, establishing a joint reconstruction-diagnosis inference paradigm. Experiments demonstrate that our approach reduces k-space sampling by ~40% on average while maintaining diagnostic accuracy for both tasks comparable to full-sampling baselines. The implementation is publicly available.

Technology Category

• Machine Learning: Active Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Despite the superior diagnostic capability of Magnetic Resonance Imaging (MRI), its use as a Point-of-Care (PoC) device remains limited by high cost and complexity. To enable such a future by reducing the magnetic field strength, one key approach will be to improve sampling strategies. Previous work has shown that it is possible to make diagnostic decisions directly from k-space with fewer samples. Such work shows that single diagnostic decisions can be made, but if we aspire to see MRI as a true PoC, multiple and sequential decisions are necessary while minimizing the number of samples acquired. We present a novel multi-objective reinforcement learning framework enabling comprehensive, sequential, diagnostic evaluation from undersampled k-space data. Our approach during inference actively adapts to sequential decisions to optimally sample. To achieve this, we introduce a training methodology that identifies the samples that contribute the best to each diagnostic objective using a step-wise weighting reward function. We evaluate our approach in two sequential knee pathology assessment tasks: ACL sprain detection and cartilage thickness loss assessment. Our framework achieves diagnostic performance competitive with various policy-based benchmarks on disease detection, severity quantification, and overall sequential diagnosis, while substantially saving k-space samples. Our approach paves the way for the future of MRI as a comprehensive and affordable PoC device. Our code is publicly available at https://github.com/vios-s/MRI_Sequential_Active_Sampling

Problem

• Reducing MRI cost by improving k-space sampling strategies
• Enabling sequential diagnostic decisions from undersampled data
• Achieving PoC MRI via multi-objective reinforcement learning

Innovation

• Multi-objective reinforcement learning for MRI
• Active adaptation during inference for optimal sampling
• Step-wise weighting reward function for diagnostics