AAD-DCE: An Aggregated Multimodal Attention Mechanism for Early and Late Dynamic Contrast Enhanced Prostate MRI Synthesis

TL;DR

This paper introduces AAD-DCE, a novel GAN-based model with an aggregated attention discriminator for synthesizing early and late DCE-MRI images from multimodal inputs, improving accuracy over existing methods.

Contribution

The paper presents a new multimodal attention GAN architecture for DCE-MRI synthesis that outperforms previous approaches and emphasizes the role of attention ensembling.

Findings

Outperforms existing DCE-MRI synthesis methods in PSNR, SSIM, and MAE.

Employs multimodal inputs including T2W, ADC, and T1 pre-contrast.

Demonstrates the effectiveness of aggregated attention discriminators in image synthesis.

Abstract

Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) is a medical imaging technique that plays a crucial role in the detailed visualization and identification of tissue perfusion in abnormal lesions and radiological suggestions for biopsy. However, DCE-MRI involves the administration of a Gadolinium based (Gad) contrast agent, which is associated with a risk of toxicity in the body. Previous deep learning approaches that synthesize DCE-MR images employ unimodal non-contrast or low-dose contrast MRI images lacking focus on the local perfusion information within the anatomy of interest. We propose AAD-DCE, a generative adversarial network (GAN) with an aggregated attention discriminator module consisting of global and local discriminators. The discriminators provide a spatial embedded attention map to drive the generator to synthesize early and late response DCE-MRI images. Our method employs multimodal inputs - T2 weighted (T2W), Apparent Diffusion Coefficient (ADC), and T1 pre-contrast for image synthesis. Extensive comparative and ablation studies on the ProstateX dataset show that our model (i) is agnostic to various generator benchmarks and (ii) outperforms other DCE-MRI synthesis approaches with improvement margins of +0.64 dB PSNR, +0.0518 SSIM, -0.015 MAE for early response and +0.1 dB PSNR, +0.0424 SSIM, -0.021 MAE for late response, and (ii) emphasize the importance of attention ensembling. Our code is available at https://github.com/bhartidivya/AAD-DCE.