Multi-modal Contrastive Learning for Tumor-specific Missing Modality Synthesis

TL;DR

This paper introduces a novel multi-modal contrastive learning framework for synthesizing missing MRI modalities, focusing on tumor regions, and simultaneously improving segmentation accuracy.

Contribution

It proposes a new generative model that combines contrastive learning, entropy-based feature selection, and joint segmentation to enhance tumor-specific MRI synthesis.

Findings

Outperformed existing methods in Brain MR Image Synthesis challenge

Generated high-quality tumor region images

Improved downstream segmentation performance

Abstract

Multi-modal magnetic resonance imaging (MRI) is essential for providing complementary information about brain anatomy and pathology, leading to more accurate diagnoses. However, obtaining high-quality multi-modal MRI in a clinical setting is difficult due to factors such as time constraints, high costs, and patient movement artifacts. To overcome this difficulty, there is increasing interest in developing generative models that can synthesize missing target modality images from the available source ones. Therefore, our team, PLAVE, design a generative model for missing MRI that integrates multi-modal contrastive learning with a focus on critical tumor regions. Specifically, we integrate multi-modal contrastive learning, tailored for multiple source modalities, and enhance its effectiveness by selecting features based on entropy during the contrastive learning process. Additionally, our network not only generates the missing target modality images but also predicts segmentation outputs, simultaneously. This approach improves the generator's capability to precisely generate tumor regions, ultimately improving performance in downstream segmentation tasks. By leveraging a combination of contrastive, segmentation, and additional self-representation losses, our model effectively reflects target-specific information and generate high-quality target images. Consequently, our results in the Brain MR Image Synthesis challenge demonstrate that the proposed model excelled in generating the missing modality.