Synthesis-based Imaging-Differentiation Representation Learning for Multi-Sequence 3D/4D MRI

TL;DR

This paper introduces a sequence-to-sequence generation framework for multi-sequence MRI that efficiently learns imaging-differentiation representations, ranks sequence importance, and enhances clinical diagnosis tasks.

Contribution

It proposes a novel generative model capable of arbitrary 3D/4D MRI sequence synthesis, sequence importance ranking, and extraction of unique sequence information, improving clinical prediction performance.

Findings

Efficient and lightweight model with high-quality image generation.

Top-ranked sequences can replace full sequences without losing performance.

Enhanced clinical task accuracy using imaging-differentiation maps.

Abstract

Multi-sequence MRIs can be necessary for reliable diagnosis in clinical practice due to the complimentary information within sequences. However, redundant information exists across sequences, which interferes with mining efficient representations by modern machine learning or deep learning models. To handle various clinical scenarios, we propose a sequence-to-sequence generation framework (Seq2Seq) for imaging-differentiation representation learning. In this study, not only do we propose arbitrary 3D/4D sequence generation within one model to generate any specified target sequence, but also we are able to rank the importance of each sequence based on a new metric estimating the difficulty of a sequence being generated. Furthermore, we also exploit the generation inability of the model to extract regions that contain unique information for each sequence. We conduct extensive experiments using three datasets including a toy dataset of 20,000 simulated subjects, a brain MRI dataset of 1,251 subjects, and a breast MRI dataset of 2,101 subjects, to demonstrate that (1) our proposed Seq2Seq is efficient and lightweight for complex clinical datasets and can achieve excellent image quality; (2) top-ranking sequences can be used to replace complete sequences with non-inferior performance; (3) combining MRI with our imaging-differentiation map leads to better performance in clinical tasks such as glioblastoma MGMT promoter methylation status prediction and breast cancer pathological complete response status prediction. Our code is available at https://github.com/fiy2W/mri_seq2seq.