Adversarial and Perceptual Refinement for Compressed Sensing MRI Reconstruction
This work addresses the need for visually appealing and semantically interpretable MRI reconstructions for medical imaging analysis, representing an incremental advancement in loss function optimization.
The paper tackled the problem of blurry and detail-lacking reconstructed images in compressed sensing MRI by proposing a hybrid method that combines adversarial and perceptual loss functions with MSE loss, achieving significant improvements over state-of-the-art in a human observer study and a semantic interpretability score on a cardiac MRI dataset with 8-fold undersampling.
Deep learning approaches have shown promising performance for compressed sensing-based Magnetic Resonance Imaging. While deep neural networks trained with mean squared error (MSE) loss functions can achieve high peak signal to noise ratio, the reconstructed images are often blurry and lack sharp details, especially for higher undersampling rates. Recently, adversarial and perceptual loss functions have been shown to achieve more visually appealing results. However, it remains an open question how to (1) optimally combine these loss functions with the MSE loss function and (2) evaluate such a perceptual enhancement. In this work, we propose a hybrid method, in which a visual refinement component is learnt on top of an MSE loss-based reconstruction network. In addition, we introduce a semantic interpretability score, measuring the visibility of the region of interest in both ground truth and reconstructed images, which allows us to objectively quantify the usefulness of the image quality for image post-processing and analysis. Applied on a large cardiac MRI dataset simulated with 8-fold undersampling, we demonstrate significant improvements ($p<0.01$) over the state-of-the-art in both a human observer study and the semantic interpretability score.