SelfCoLearn: Self-Supervised Collaborative Learning for Accelerating Dynamic MR Imaging

Abstract

Lately, deep learning technology has been extensively investigated for accelerating dynamic magnetic resonance (MR) imaging, with encouraging progresses achieved. However, without fully sampled reference data for training, the current approaches may have limited abilities in recovering fine details or structures. To address this challenge, this paper proposes a self-supervised collaborative learning framework (SelfCoLearn) for accurate dynamic MR image reconstruction from undersampled k-space data directly. The proposed SelfCoLearn is equipped with three important components, namely, dual-network collaborative learning, reunderampling data augmentation and a special-designed co-training loss. The framework is flexible and can be integrated into various model-based iterative un-rolled networks. The proposed method has been evaluated on an in vivo dataset and was compared to four state-of-the-art methods. The results show that the proposed method possesses strong capabilities in capturing essential and inherent representations for direct reconstructions from the undersampled k-space data and thus enables high-quality and fast dynamic MR imaging.

Knowledge‐driven deep learning for fast MR imaging: Undersampled MR image reconstruction from supervised to un‐supervised learning

“…Several studies have investigated self-supervised learning for MRI reconstruction. [197][198][199][200][201][202][203][204][205][206][207][208][209][210][211][212] For instance, Yaman et al 197 introduced a self-supervised approach (SSDU) in which the acquired undersampled data indices are divided into a set of k-space positions used in the network's DC layer during training, and a set of k-space positions used within the loss function. This is a classic work in self-supervised MRI reconstruction, offering valuable insights for subsequent self-supervised learning methods.…”

“…Several studies have investigated self‐supervised learning for MRI reconstruction 197–212 . For instance, Yaman et al 197 introduced a self‐supervised approach (SSDU) in which the acquired undersampled data indices are divided into a set of k‐space positions used in the network's DC layer during training, and a set of k‐space positions used within the loss function.…”

Machine learning for automatic Alzheimer’s disease detection: addressing domain shift issues for building robust models

“…Computer-aided diagnosis systems are highly desired to help physicians achieve fast and accurate neuroimaging data analysis. ML techniques have had great success in different fields in recent decades, including medical and neuroimaging fields [25][26][27], and the ability and accuracy of largescale complicated data analyses have been significantly improved due to recent developments in DL techniques [21,[28][29][30][31]. Essential obstacles, however, still prevent the direct and efficient application of DL algorithms in the clinical setting because there are few labeled medical datasets because annotating medical datasets is a labor-intensive, costly, and time-consuming procedure that requires neurologists, neuroradiologists, and other experts [5].…”

“…For example, amyloid-PET imaging is expensive and not affordable by all participants. As a result, combining sparse or missing datasets is a critical challenge in multi-modal data analysis that needs to be investigated further [29,66].…”

AI in MRI: Computational Frameworks for a Faster, Optimized, and Automated Imaging Workflow

“…Here, several papers introduce techniques for developing DL models while facing data-related challenges. Zou et al [ 48 ] introduce a new framework for dynamic MRI reconstruction without ground truth data, namely self-supervised collaborative learning (SelcCoLearn). This framework splits the undersampled k-space measurements into two datasets and uses them as inputs for two neural networks.…”