Machine learning-based prediction of motor status in glioma patients using diffusion MRI metrics along the corticospinal tract

Conceptualisation and Implementation of a Competency-based Multidisciplinary Course for Medical Students in Neurosurgery

The field of medicine is quickly evolving and becoming increasingly more multidisciplinary and technologically demanding. Medical education, however, does not yet adequately reflect these developments and new challenges, which calls for a reform in the way aspiring medical professionals are taught and prepared for the workplace. The present article presents an attempt to address this shortcoming in the form of a newly conceptualized course for medical students with a focus on the current demands and trends in modern neurosurgery. Competency-based education is introduced as a conceptual framework comprising academic and operational competence as well as life-world becoming. This framework provides a sound educational foundation for future medical professionals, equipping them with the knowledge as well as skills needed to successfully navigate the medical field in the current day and age. Three competencies are identified that are central to day-to-day medical practice, namely digitalization, multidisciplinarity, and the impact of recent developments on the changing patient-practitioner relationship. These competencies are relevant for all medical disciplines, but are demonstrated here in a neurosurgical context and visualized using a real patient's case study. Students follow this sample patient's way through each step of the neurosurgical workflow, from planning to performing the procedure, and can see for themselves the importance and application of the aforementioned competencies based on this real-world example. Courses such as the one presented here may prepare medical students more adequately for their future work by combining theoretical and practical skills and critical reflection, thereby providing holistic and practical insights as well as a conceptual framework for their future careers.

Radiomic white matter parameters of functional integrity of the corticospinal tract in high-grade glioma

Tractography has become a widely available tool for the planning of neurosurgical operations as well as for neuroscientific research. The absence of patient interaction makes it easily applicable. However, it leaves uncertainty about the functional relevance of the identified bundles. We retrospectively analyzed the correlation of white matter markers with their clinical function in 24 right-handed patients who underwent first surgery for high-grade glioma. Morphological affection of the corticospinal tract (CST) and grade of paresis were assessed before surgery. Tractography was performed manually with MRTrix3 and automatically with TractSeg. Median and mean fractional anisotropy (FA) from manual tractography showed a significant correlation with CST affection (p = 0.008) and paresis (p = 0.015, p = 0.026). CST affection correlated further most with energy, and surface-volume ratio (p = 0.014) from radiomic analysis. Paresis correlated most with maximum 2D column diameter (p = 0.005), minor axis length (p = 0.006), and kurtosis (p = 0.008) from radiomic analysis. Streamline count yielded no significant correlations. In conclusion, mean or median FA can be used for the assessment of CST integrity in high-grade glioma. Also, several radiomic parameters are suited to describe tract integrity and may be used to quantitatively analyze white matter in the future.

Structural changes in corticospinal tract profiling via multishell diffusion models and their relation to overall survival in glioblastoma

PURPOSE

Advanced MR fiber tracking imaging reflects fiber bundle invasion by glioblastoma, particularly of the corticospinal tract (CST), which is more susceptible as the largest downstream fiber tracts. We aimed to investigate whether CST features can predict the overall survival of glioblastoma.

METHODS

In this prospective secondary analysis, 40 participants (mean age, 58 years; 16 male) pathologically diagnosed with glioblastoma were enrolled. Diffusion spectrum MRI was used for CST reconstruction. Fifty morphological and diffusion indicators (DTI, DKI, NODDI, MAP and Q-space) were used to characterize the CST. Optimal parameters capturing fiber bundle damage were obtained through various grouping methods. Eventually, the correlation with overall survival was determined by the hazard ratios (HRs) from various Cox proportional hazard model combinations.

RESULTS

Only intracellular volume fraction (ICVF) and non-Gaussianity (NG) values on the affected tumor level were significant in all four groups or stratified comparisons (all P < .05). During the median follow-up 698 days, only the ICVF on the affected tumor level was independently associated with overall survival, even after adjusting for all classic prognostic factors (HR [95 % CI]: 0.611 [0.403, 0.927], P = .021). Moreover, stratification by the ICVF on the affected tumor level successfully predicted risk (P < .01) and improved the C-index of the multivariate model (from 0.695 to 0.736).

CONCLUSIONS

This study demonstrates a relationship between NODDI-derived CST features, ICVF on the affected tumor level, and overall survival in glioblastoma. Independent of classical prognostic factors for glioblastoma, a lower ICVF on the affected tumor level might predict a lower overall survival.

Assessing Postoperative Motor Risk in Insular Low-Grade Gliomas Patients: The Potential Role of Presurgery MRI Corticospinal Tract Shape Measures

BACKGROUND

Insular low-grade gliomas (LGGs) are surgically challenging due to their proximity to critical structures like the corticospinal tract (CST).

PURPOSE

This study aims to determine if preoperative CST shape metrics correlate with postoperative motor complications in insular LGG patients.

STUDY TYPE

Retrospective.

POPULATION

42 patients (mean age 40.26 ± 10.21 years, 25 male) with insular LGGs.

FIELD STRENGTH/SEQUENCE

Imaging was performed using 3.0 Tesla MRI, incorporating T1-weighted magnetization-prepared rapid gradient-echo, T2-weighted space dark-fluid with spin echo (SE), and diffusional kurtosis imaging (DKI) with gradient echo sequences, all integrated with echo planar imaging.

ASSESSMENT

Shape metrics of the CST, including span, irregularity, radius, and irregularity of end regions (RER and IER, respectively), were compared between the affected and healthy hemispheres. Total end region radius (TRER) was determined as the sum of RER 1 and RER 2. The relationships between shape metrics and postoperative short-term (4 weeks) and long-term (>8 weeks) motor disturbances assessing by British Medical Research Council grading system, was analyzed using multivariable regression models.

STATISTICAL TESTING

Paired t-tests compared CST metrics between hemispheres. Logistic regression identified associations between these metrics and motor disturbances. The models were developed using all available data and there was no independent validation dataset. Significance was set at P < 0.05.

RESULTS

Short-term motor disturbance risk was significantly related to TRER (OR = 199.57). Long-term risk significantly correlated with IER 1 (OR = 59.84), confirmed as a significant marker with an AUC of 0.78. Furthermore, the CST on the affected side significantly had the greater irregularity, larger TRER and RER 1, and smaller span compared to the healthy side.

DATA CONCLUSION

Preoperative evaluation of TRER and IER 1 metrics in the CST may serve as a tool for assessing the risk of postoperative motor complications in insular LGG patients.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY: Stage 2.

Improved prediction of glioma-related aphasia by diffusion MRI metrics, machine learning, and automated fiber bundle segmentation

White matter impairments caused by gliomas can lead to functional disorders. In this study, we predicted aphasia in patients with gliomas infiltrating the language network using machine learning methods. We included 78 patients with left-hemispheric perisylvian gliomas. Aphasia was graded preoperatively using the Aachen aphasia test (AAT). Subsequently, we created bundle segmentations based on automatically generated tract orientation mappings using TractSeg. To prepare the input for the support vector machine (SVM), we first preselected aphasia-related fiber bundles based on the associations between relative tract volumes and AAT subtests. In addition, diffusion magnetic resonance imaging (dMRI)-based metrics [axial diffusivity (AD), apparent diffusion coefficient (ADC), fractional anisotropy (FA), and radial diffusivity (RD)] were extracted within the fiber bundles' masks with their mean, standard deviation, kurtosis, and skewness values. Our model consisted of random forest-based feature selection followed by an SVM. The best model performance achieved 81% accuracy (specificity = 85%, sensitivity = 73%, and AUC = 85%) using dMRI-based features, demographics, tumor WHO grade, tumor location, and relative tract volumes. The most effective features resulted from the arcuate fasciculus (AF), middle longitudinal fasciculus (MLF), and inferior fronto-occipital fasciculus (IFOF). The most effective dMRI-based metrics were FA, ADC, and AD. We achieved a prediction of aphasia using dMRI-based features and demonstrated that AF, IFOF, and MLF were the most important fiber bundles for predicting aphasia in this cohort.