Post-concussive mTBI in Student Athletes: MRI Features and Machine Learning.

Purpose: To determine and characterize the radiomics features from structural MRI (MPRAGE) and Diffusion Tensor Imaging (DTI) associated with the presence of mild traumatic brain injuries on student athletes with post-concussive syndrome (PCS). Material and Methods: 122 student athletes (65 M, 57 F), median (IQR) age 18.8 (15-20) years, with a mixed level of play and sports activities, with a known history of concussion and clinical PCS, and 27 (15 M, 12 F), median (IQR) age 20 (19, 21) years, concussion free athlete subjects were MRI imaged in a clinical MR machine. MPRAGE and DTI-FA and DTI-ADC images were used to extract radiomic features from white and gray matter regions within the entire brain (2 ROI) and the eight main lobes of the brain (16 ROI) for a total of 18 analyzed regions. Radiomic features were divided into five different data sets used to train and cross-validate five different filter-based Support Vector Machines. The top selected features of the top model were described. Furthermore, the test predictions of the top four models were ensembled into a single average prediction. The average prediction was evaluated for the association to the number of concussions and time from injury. Results: Ninety-one PCS subjects passed inclusion criteria (91 Cases, 27 controls). The average prediction of the top four models had a sensitivity of 0.80, 95% CI: [0.71, 0.88] and specificity of 0.74 95%CI [0.54, 0.89] for distinguishing subjects from controls. The white matter features were strongly associated with mTBI, while the whole-brain analysis of gray matter showed the worst association. The predictive index was significantly associated with the number of concussions (p < 0.0001) and associated with the time from injury (p < 0.01). Conclusion: MRI Radiomic features are associated with a history of mTBI and they were successfully used to build a predictive machine learning model for mTBI for subjects with PCS associated with a history of one or more concussions.

Más allá del tensor de difusión: experiencia preliminar en tractografía HARDI-CSD y super-resolución en 1. 5T / Beyond the diffusion tensor model: preliminary experience inHARDI tractography-CSD and super-resolution 1. 5T

Introduction: For more than a decade the diffusion tensor imaging model has been widely used in order to resolve and represent the intracranial white-matter microanatomy. Howeverthere are numerous studies that have successfully demonstrated the limitations associated with DTI in trying to define crossing-fibre regions. Various models have been developed with the intention of overcoming these limitations. This is why our study focuses on the description and preliminary experience in the use of tractography based on high-angular-resolution-diffusion imaging (HARDI) using the constrained spherical deconvolution (CSD) technique. Methods: The data was acquired on a Philips Achieva 1.5T resonator using a diffusion weighted single-shot echoplanar sequence along 32 directions with a b-value of 1000s/mm2. The images were processed using FSL v5.0 and MRtrix v0.2.10 software. Results: We achieved tensor free high-angular-resolution-diffusion tractographic images that better represented the white-matter micro-architecture than those obtained from the tensor model. Additionally, it was possible to generate track-density images (TDI) with a final resolution more than 500 times that of the acquired data.

Introducción: Desde hace más de una década que el modelo de tensor de difusión ha sido ampliamente utilizado con el fin de resolver y representar la microanatomía de la sustancia blanca intra-cerebral. Sin embargo, no son pocos los estudios que han logrado demostrar las grandes desventajas que el modelo presenta al tratar de definir regiones de entrecruzamiento de fibras. Diversos modelos han sido desarrollados para ofrecer una solución consistente, capaz de representar dichas regiones con mayor grado de correlación anatómica. Es por ello que nuestro estudio se enfoca en la descripción y experiencia preliminar en el uso de tractografía basada en imágenes de difusión de alta resolución angular (HARDI) usando el modelo de deconvolución esférica restringida (CSD). Métodos: La adquisición se realizó en un resonador Philips Achieva 1.5T mediante secuencia de difusión single-shot echo-planar de 32 direcciones con un b-value de 1.000s/mm² procesamiento de las imágenes se realizó mediante software FSL v5.0 y MRtrix v0.2.10. Resultados: Se lograron tractografías libres de tensor de difusión de alta resolución angular que representan la micro-arquitectura de la sustancia blanca de mejor manera que con las generadas a partir del modelo de tensor. Adicionalmente, se logró generar imágenes de densidad tractográfica (TDI) con una resolución final de más de 500 veces a la de adquisición.