Dewey Blake E, Remedios Samuel W, Sanjayan Muraleetharan, Rjeily Nicole Bou, Lee Alexandra Zambriczki, Wyche Chelsea, Duncan Safiya, Prince Jerry L, Calabresi Peter A, Fitzgerald Kathryn C, Mowry Ellen M
From the Department of Neurology (B.E.D., M.S., N.B.R., A.Z.L., C.W., S.D., P.A.C., K.C.F., E.M.M.), Johns Hopkins University, Baltimore, Maryland
Department of Computer Science (S.W.R.), Johns Hopkins University, Baltimore, Maryland.
AJNR Am J Neuroradiol. 2025 Apr 2;46(4):823-831. doi: 10.3174/ajnr.A8526.
Measurement of the mean upper cervical cord area (MUCCA) is an important biomarker in the study of neurodegeneration. However, dedicated high-resolution (HR) scans of the cervical spinal cord are rare in standard-of-care imaging due to timing and clinical usability. Most clinical cervical spinal cord imaging is sagittally acquired in 2D with thick slices and anisotropic voxels. As a solution, previous work describes HR T1-weighted brain imaging for measuring the upper cord area, but this is still not common in clinical care.
We propose using a zero-shot super-resolution technique, synthetic multi-orientation resolution enhancement (SMORE), already validated in the brain, to enhance the resolution of 2D-acquired scans for upper cord area calculations. To incorporate super-resolution in spinal cord analysis, we validate SMORE against HR research imaging and in a real-world longitudinal data analysis.
Super-resolved (SR) images reconstructed by using SMORE showed significantly greater similarity to the ground truth than low-resolution (LR) images across all tested resolutions ( < .001 for all resolutions in peak signal-to-noise ratio [PSNR] and mean structural similarity [MSSIM]). MUCCA results from SR scans demonstrate excellent correlation with HR scans ( > 0.973 for all resolutions) compared with LR scans. Additionally, SR scans are consistent between resolutions ( > 0.969), an essential factor in longitudinal analysis. Compared with clinical outcomes such as walking speed or disease severity, MUCCA values from LR scans have significantly lower correlations than those from HR scans. SR results have no significant difference. In a longitudinal real-world data set, we show that these SR volumes can be used in conjunction with T1-weighted brain scans to show a significant rate of atrophy (-0.790, = .020 versus -0.438, = .301 with LR).
Super-resolution is a valuable tool for enabling large-scale studies of cord atrophy, as LR images acquired in clinical practice are common and available.
测量上颈髓平均面积（MUCCA）是神经退行性变研究中的一项重要生物标志物。然而，由于时间安排和临床实用性，在标准护理成像中，专门针对颈髓的高分辨率（HR）扫描很少见。大多数临床颈髓成像采用二维矢状面厚层扫描，体素呈各向异性。作为一种解决方案，先前的研究描述了利用HR T1加权脑成像来测量上颈髓面积，但这在临床护理中仍不常见。
我们提出使用一种零样本超分辨率技术，即已在脑部验证的合成多方向分辨率增强（SMORE）技术，来提高二维采集扫描的分辨率，以计算上颈髓面积。为了将超分辨率纳入脊髓分析，我们针对HR研究成像以及在真实世界纵向数据分析中对SMORE进行了验证。
在所有测试分辨率下，使用SMORE重建的超分辨率（SR）图像与真实图像的相似度显著高于低分辨率（LR）图像（在峰值信噪比[PSNR]和平均结构相似性[MSSIM]方面，所有分辨率下的P值均<0.001）。与LR扫描相比，SR扫描得出的MUCCA结果与HR扫描具有极好的相关性（所有分辨率下均>0.973）。此外，SR扫描在不同分辨率之间具有一致性（>0.969），这是纵向分析中的一个关键因素。与步行速度或疾病严重程度等临床结果相比，LR扫描得出的MUCCA值与HR扫描得出的值相比，相关性显著更低。SR结果无显著差异。在一个真实世界纵向数据集中，我们表明这些SR体积数据可与T1加权脑扫描结合使用，以显示显著的萎缩率（-0.790，P = 0.020，而LR为-0.438，P = 0.301）。
超分辨率是开展脊髓萎缩大规模研究的一项有价值的工具，因为临床实践中获取的LR图像很常见且可得。
