Task-driven assessment of experimental designs in diffusion MRI: a computational framework

TL;DR

This paper introduces a task-driven computational framework for evaluating diffusion MRI experimental designs by directly measuring their performance on specific clinical tasks, rather than traditional parameter estimation metrics.

Contribution

It presents a novel simulation-based assessment method that predicts task performance, validated against clinical data, and outperforms traditional evaluation approaches.

Findings

Validated pipeline predictions with clinical ROC/AUC data.

Demonstrated superiority over traditional assessment methods.

Showed generalizability to other MRI applications.

Abstract

This paper proposes a task-driven computational framework for assessing diffusion MRI experimental designs which, rather than relying on parameter-estimation metrics, directly measures quantitative task performance. Traditional computational experimental design (CED) methods may be ill-suited to experimental tasks, such as clinical classification, where outcome does not depend on parameter-estimation accuracy or precision alone. Current assessment metrics evaluate experiments' ability to faithfully recover microstructural parameters rather than their task performance. The method we propose addresses this shortcoming. For a given MRI experimental design, experiments are simulated start-to-finish and task performance is computed from ROC curves and associated summary metrics (e.g. AUC). Two experiments were performed: first, a validation of the pipeline's task performance predictions against clinical results, comparing in-silico predictions to real-world ROC/AUC; and second, a demonstration of the pipeline's advantages over traditional CED approaches, using two simulated clinical classification tasks. Comparison with clinical datasets validates our method's predictions of (a) the qualitative form of ROC curves, (b) the relative task performance of different experimental designs, and (c) the absolute performance of each experimental design. Furthermore, we show that our method outperforms traditional task-agnostic assessment methods, enabling improved, more useful experimental design. Compared to current approaches, such task-driven assessment is more likely to identify experimental designs that perform well in practice. Our method is not limited to diffusion MRI; the pipeline generalises to any task-based quantitative MRI application, and provides the foundation for developing future task-driven end-to end CED frameworks.