SIMPLE: Simultaneous Multi-Plane Self-Supervised Learning for Isotropic MRI Restoration from Anisotropic Data

2024-08-23

arXiv.org

AI Summary

MRI’s anisotropic acquisition yields spatially non-uniform resolution, limiting diagnostic accuracy and reliable 3D quantitative analysis. To address this, we propose the first end-to-end, physically consistent 3D isotropic super-resolution method tailored to real clinical data—requiring no simulated downsampling or paired isotropic ground truth. Our approach employs a multi-planar (axial/coronal/sagittal) co-supervised learning framework, augmented by a cross-plane alignment consistency loss, a 3D feature-decoupled reconstruction network, and a Kernel Inception Distance (KID)-driven quality assessment module. Evaluated on brain and abdominal clinical datasets, our method significantly outperforms state-of-the-art approaches: KID improves by 32%, and radiologist scoring increases by 1.8 points (on a 5-point scale). The resulting isotropic volumes enable more accurate volumetric quantification and enhanced 3D surgical planning.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Multimodal Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Magnetic resonance imaging (MRI) is crucial in diagnosing various abdominal conditions and anomalies. Traditional MRI scans often yield anisotropic data due to technical constraints, resulting in varying resolutions across spatial dimensions, which limits diagnostic accuracy and volumetric analysis. Super-resolution (SR) techniques aim to address these limitations by reconstructing isotropic high-resolution images from anisotropic data. However, current SR methods often depend on indirect mappings and scarce 3D isotropic data for training, primarily focusing on two-dimensional enhancements rather than achieving genuine three-dimensional isotropy. We introduce ``SIMPLE,'' a Simultaneous Multi-Plane Self-Supervised Learning approach for isotropic MRI restoration from anisotropic data. Our method leverages existing anisotropic clinical data acquired in different planes, bypassing the need for simulated downsampling processes. By considering the inherent three-dimensional nature of MRI data, SIMPLE ensures realistic isotropic data generation rather than solely improving through-plane slices. This approach's flexibility allows it to be extended to multiple contrast types and acquisition methods commonly used in clinical settings. Our experiments on two distinct datasets (brain and abdomen) show that SIMPLE outperforms state-of-the-art methods both quantitatively using the Kernel Inception Distance (KID), semi-quantitatively through radiologist evaluations, and qualitatively through Fourier domain analysis. The generated isotropic volume facilitates more accurate volumetric analysis and 3D reconstructions, promising significant improvements in clinical diagnostic capabilities.

Problem

• Restores isotropic MRI from anisotropic data
• Eliminates need for scarce 3D training data
• Improves diagnostic accuracy via 3D reconstruction

Innovation

• Simultaneous Multi-Plane Self-Supervised Learning
• Leverages existing anisotropic clinical data
• Ensures realistic 3D isotropic data generation