An Explainable Deep Framework: Towards Task-Specific Fusion for Multi-to-One MRI Synthesis

TL;DR

This paper introduces an explainable deep learning framework for multi-to-one MRI synthesis that adaptively fuses input sequences and provides interpretability, improving synthesis quality and reliability.

Contribution

It proposes a novel task-specific, explainable neural network that visualizes input contributions and refines areas during MRI synthesis, enhancing practicality and interpretability.

Findings

Outperforms state-of-the-art methods on BraTS2021 dataset

Provides visual explanations of input sequence contributions

Achieves higher synthesis accuracy and reliability

Abstract

Multi-sequence MRI is valuable in clinical settings for reliable diagnosis and treatment prognosis, but some sequences may be unusable or missing for various reasons. To address this issue, MRI synthesis is a potential solution. Recent deep learning-based methods have achieved good performance in combining multiple available sequences for missing sequence synthesis. Despite their success, these methods lack the ability to quantify the contributions of different input sequences and estimate the quality of generated images, making it hard to be practical. Hence, we propose an explainable task-specific synthesis network, which adapts weights automatically for specific sequence generation tasks and provides interpretability and reliability from two sides: (1) visualize the contribution of each input sequence in the fusion stage by a trainable task-specific weighted average module; (2) highlight the area the network tried to refine during synthesizing by a task-specific attention module. We conduct experiments on the BraTS2021 dataset of 1251 subjects, and results on arbitrary sequence synthesis indicate that the proposed method achieves better performance than the state-of-the-art methods. Our code is available at \url{https://github.com/fiy2W/mri_seq2seq}.