Find in Library

<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="normal">B</mi><mn>0</mn></msub></semantics></math></inline-formula> field inhomogeneity is a long-lasting issue for Cardiac MRI (CMR) in high-field (3T and above) scanners. The inhomogeneous <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="normal">B</mi><mn>0</mn></msub></semantics></math></inline-formula> fields can lead to corrupted image quality, prolonged scan time, and false diagnosis. <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="normal">B</mi><mn>0</mn></msub></semantics></math></inline-formula> shimming is the most straightforward way to improve the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="normal">B</mi><mn>0</mn></msub></semantics></math></inline-formula> homogeneity. However, today’s standard cardiac shimming protocol requires manual selection of a shim volume, which often falsely includes regions with large <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="normal">B</mi><mn>0</mn></msub></semantics></math></inline-formula> deviation (e.g., liver, fat, and chest wall). The flawed shim field compromises the reliability of high-field CMR protocols, which significantly reduces the scan efficiency and hinders its wider clinical adoption. This study aims to develop a dual-channel deep learning model that can reliably contour the cardiac region for <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="normal">B</mi><mn>0</mn></msub></semantics></math></inline-formula> shim without human interaction and under variable imaging protocols. By utilizing both the magnitude and phase information, the model achieved a high segmentation accuracy in the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="normal">B</mi><mn>0</mn></msub></semantics></math></inline-formula> field maps compared to the conventional single-channel methods (Dice score: 2D-mag = 0.866, 3D-mag = 0.907, and 3D-mag-phase = 0.938, all <i>p</i> < 0.05). Furthermore, it shows better generalizability against the common variations in MRI imaging parameters and enables significantly improved <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="normal">B</mi><mn>0</mn></msub></semantics></math></inline-formula> shim compared to the standard method (SD(<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="normal">B</mi><mn>0</mn></msub></semantics></math></inline-formula>Shim): Proposed = 15 ± 11% vs. Standard = 6 ± 12%, <i>p</i> < 0.05). The proposed autonomous model can boost the reliability of cardiac shimming at 3T and serve as the foundation for more reliable and efficient high-field CMR imaging in clinical routines.