Machine Learning Analysis in Diffusion Kurtosis Imaging for Discriminating Pediatric Posterior Fossa Tumors: A...

Area of Science:

• Radiology and Imaging
• Oncology
• Pediatric Neuro-oncology

Background:

• Pediatric posterior fossa tumors (medulloblastoma, ependymoma, pilocytic astrocytoma) require accurate differentiation for treatment and prognosis.
• Diffusion kurtosis imaging (DKI) has not been previously explored for discriminating these pediatric tumors.
• Whole-tumor-based (VOI) segmentations may offer improved repeatability for diffusion measurements compared to region-of-interest (ROI) approaches.

Purpose of the Study:

• To compare the repeatability of DKI-derived diffusion measurements between ROI and VOI segmentation methods.
• To assess the accuracy of DKI in discriminating between pediatric posterior fossa tumor subtypes.
• To evaluate the utility of machine learning algorithms for tumor classification using DKI metrics.

Main Methods:

• Retrospective analysis of 34 pediatric patients with posterior fossa tumors who underwent preoperative DKI.
• Independent segmentation of tumors by two neuroradiologists using ROI and VOI methods.
• Statistical analysis (MANOVA, Bland-Altman plots) and Random Forest machine learning classification on DKI metrics, with SMOTE for dataset balancing.

Main Results:

• VOI-based DKI measurements demonstrated lower inter-observer variability compared to ROI-based measurements.
• DKI metrics significantly discriminated between tumor subtypes (Pillai's trace: p < 0.001).
• Machine learning classification achieved a 0.928 accuracy in predicting tumor histology on a balanced dataset.

Conclusions:

• VOI-based DKI measurements offer improved repeatability for analyzing pediatric posterior fossa tumors.
• Machine learning algorithms utilizing DKI metrics are effective for accurate discrimination of these tumor types.
• DKI combined with ML represents a promising non-invasive tool for pediatric PF tumor classification.