Alert button
Picture for Tongyao Wang

Tongyao Wang

Alert button

Self-Supervised Deep Equilibrium Models for Inverse Problems with Theoretical Guarantees

Oct 07, 2022
Weijie Gan, Chunwei Ying, Parna Eshraghi, Tongyao Wang, Cihat Eldeniz, Yuyang Hu, Jiaming Liu, Yasheng Chen, Hongyu An, Ulugbek S. Kamilov

Figure 1 for Self-Supervised Deep Equilibrium Models for Inverse Problems with Theoretical Guarantees
Figure 2 for Self-Supervised Deep Equilibrium Models for Inverse Problems with Theoretical Guarantees
Figure 3 for Self-Supervised Deep Equilibrium Models for Inverse Problems with Theoretical Guarantees
Figure 4 for Self-Supervised Deep Equilibrium Models for Inverse Problems with Theoretical Guarantees

Deep equilibrium models (DEQ) have emerged as a powerful alternative to deep unfolding (DU) for image reconstruction. DEQ models-implicit neural networks with effectively infinite number of layers-were shown to achieve state-of-the-art image reconstruction without the memory complexity associated with DU. While the performance of DEQ has been widely investigated, the existing work has primarily focused on the settings where groundtruth data is available for training. We present self-supervised deep equilibrium model (SelfDEQ) as the first self-supervised reconstruction framework for training model-based implicit networks from undersampled and noisy MRI measurements. Our theoretical results show that SelfDEQ can compensate for unbalanced sampling across multiple acquisitions and match the performance of fully supervised DEQ. Our numerical results on in-vivo MRI data show that SelfDEQ leads to state-of-the-art performance using only undersampled and noisy training data.

Viaarxiv icon

SPICE: Self-Supervised Learning for MRI with Automatic Coil Sensitivity Estimation

Oct 05, 2022
Yuyang Hu, Weijie Gan, Chunwei Ying, Tongyao Wang, Cihat Eldeniz, Jiaming Liu, Yasheng Chen, Hongyu An, Ulugbek S. Kamilov

Figure 1 for SPICE: Self-Supervised Learning for MRI with Automatic Coil Sensitivity Estimation
Figure 2 for SPICE: Self-Supervised Learning for MRI with Automatic Coil Sensitivity Estimation
Figure 3 for SPICE: Self-Supervised Learning for MRI with Automatic Coil Sensitivity Estimation
Figure 4 for SPICE: Self-Supervised Learning for MRI with Automatic Coil Sensitivity Estimation

Deep model-based architectures (DMBAs) integrating physical measurement models and learned image regularizers are widely used in parallel magnetic resonance imaging (PMRI). Traditional DMBAs for PMRI rely on pre-estimated coil sensitivity maps (CSMs) as a component of the measurement model. However, estimation of accurate CSMs is a challenging problem when measurements are highly undersampled. Additionally, traditional training of DMBAs requires high-quality groundtruth images, limiting their use in applications where groundtruth is difficult to obtain. This paper addresses these issues by presenting SPICE as a new method that integrates self-supervised learning and automatic coil sensitivity estimation. Instead of using pre-estimated CSMs, SPICE simultaneously reconstructs accurate MR images and estimates high-quality CSMs. SPICE also enables learning from undersampled noisy measurements without any groundtruth. We validate SPICE on experimentally collected data, showing that it can achieve state-of-the-art performance in highly accelerated data acquisition settings (up to 10x).

Viaarxiv icon