The aim of this study was to examine the potential utility of a self-paced saccadic eye movement as a marker of post-concussion syndrome (PCS) and monitoring the recovery from PCS. Fifty-nine persistently symptomatic participants with at least two concussions performed the self-paced saccade (SPS) task. We evaluated the relationships between the number of SPSs and 1) number of self-reported concussion symptoms, and 2) integrity of major white matter (WM) tracts (as measured by fractional anisotropy [FA] and mean diffusivity) that are directly or indirectly involved in saccadic eye movements and often affected by concussion. These tracts included the uncinate fasciculus (UF), cingulum (Cg) and its three subcomponents (subgenual, retrosplenial, and parahippocampal), superior longitudinal fasciculus, and corpus callosum. Mediation analyses were carried out to examine whether specific WM tracts (left UF and left subgenual Cg) mediated the relationship between the number of SPSs and 1) interval from last concussion or 2) total number of self-reported symptoms. The number of SPSs was negatively correlated with the total number of self-reported symptoms (r = -0.419, p = 0.026). The number of SPSs were positively correlated with FA of left UF and left Cg (r = 0.421, p = 0.013 and r = 0.452, p = 0.008; respectively). FA of the subgenual subcomponent of the left Cg partially mediated the relationship between the total number of symptoms and the number of SPSs, while FA of the left UF mediated the relationship between interval from last concussion and the number of SPSs. In conclusion, SPS testing as a fast and objective assessment may reflect symptom burden in patients with PCS. In addition, since the number of SPSs is associated with the integrity of some WM tracts, it may be useful as a diagnostic biomarker in patients with PCS.

No abstract

No abstract

We present a new Adaptive Error Correction Net (AEC-Net) to formulate the estimation of Cobb anges from spinal X-rays as a high-precision regression task. Our AEC-Net introduces two novel innovations. (1) The AEC-Net contains two networks calculating landmarks and Cobb angles separately, which robustly solve the disadvantage of ambiguity in X-rays since these networks focus on more features. It effectively handles the nonlinear relationship between input images and quantitative outputs, while explicitly capturing the intrinsic features of input images. (2) Based on the two estimated angles, the AEC-Net proposed a new loss function to calculate the final Cobb angles. The optimization of the loss function is based on a high-precision calculation method. The deep learning structure is used to complete this optimization, which achieves higher accuracy and efficiency. We validate our method with the spinal X-rays dataset of 581 subjects with signs of scoliosis at varying extents. The proposed method achieves high accuracy and robustness on the Cobb angle estimations. Comparing to the exsiting conventional methods suffering from tremendous variability and low reliability caused by high ambiguity and variability around boundaries of the vertebrae, the AEC-Net obtain Cobb angles accurately and robustly, which indicates its great potential in clinical use. The highly accurate Cobb angles produced by our framework can be used by clinicians for comprehensive scoliosis assessment, and possibly be further extended to other clinical applications. INDEX TERMS AEC-Net, Cobb angle estimation, deep learning, direct estimation, high-precision calculation. LIANSHENG WANG, photograph and biography not available at the time of publication.

No abstract