Fully-Automated Identification of Imaging Biomarkers for Post-Operative Cerebellar Mutism Syndrome Using Longitudinal Paediatric MRI

Abstract

Post-operative cerebellar mutism syndrome (POPCMS) in children is a post-surgical complication which occurs following the resection of tumors within the brain stem and cerebellum. High resolution brain magnetic resonance (MR) images acquired at multiple time points across a patient's treatment allow the quantification of localized changes caused by the progression of this syndrome. However, MR images are not necessarily acquired at regular intervals throughout treatment and are often not volumetric. This restricts the analysis to 2D space and causes difficulty in intra-and inter-subject comparison. To address these challenges, we have developed an automated image processing and analysis pipeline. Multi-slice 2D MR image slices are interpolated in space and time to produce a 4D volumetric MR image dataset providing a longitudinal representation of the cerebellum and brain stem at specific time points across treatment. The deformations within the brain over time are represented using a novel metric known as the Jacobian of deformations determinant. This metric, together with the changing grey-level intensity of areas within the brain over time, are analyzed using machine learning techniques in order to identify biomarkers that correspond with the development of POPCMS following tumor resection. This study makes use of a fully automated approach which is not hypothesis-driven. As a result, we were able to automatically detect six potential biomarkers that are related to the development of POPCMS following tumor resection in the posterior fossa.

The Research Trends of Post-operative Pediatric Cerebellar Mutism Syndrome: A Bibliometric Analysis (1999-2022)

“…Speech and language may not return to normal, and other de cits of cognitive, affective, and motor function often persist". The reported incidence of ppCMS ranges from 17.5-32.1% [9][10][11][12][13][14].…”

“…Speech and language may not return to normal, and other de cits of cognitive, affective, and motor function often persist". The reported incidence of ppCMS ranges from 17.5-32.1% [9][10][11][12][13][14].Lewison, G. astutely likened bibliometrics to scienti c papers in the same way epidemiology is to patients [15]. On one hand, bibliometrics offers both quantitative and qualitative insights into the interconnections among various elements such as countries, institutions, journals, authors, papers, keywords, and more [16,17].…”

Diffusion Tensor Imaging Connectomics Reveals Preoperative Neural Connectivity Changes in Children with Postsurgical Posterior Fossa Syndrome

“…DTI is a powerful noninvasive image technique that allows in vivo noninvasive investigation of the neural architecture of the brain. Recently, the application of automatic image analysis and machine learning in longitudinal pediatric MRI datasets has been explored as well …”

“…Recently, the application of automatic image analysis and machine learning in longitudinal pediatric MRI datasets has been explored as well. 13 While conventional neuroimaging is limited to the description of morphological changes in PFS patients, more advanced neuroimaging approaches, such as structural connectomics, can reveal more global connectivity changes. The connectome is a comprehensive map of the structural and functional interregional connections within the brain with connectometry enabling the study of the local connectome changes.…”

Mining multi-site clinical data to develop machine learning MRI biomarkers: application to neonatal hypoxic ischemic encephalopathy

“…Accuracy is measured by comparing the predicted outcome (assuming unknown during prediction) with the actually known outcome [29]. The promise has been shown in brain tumors [30–32], Alzheimer’s Disease (AD) [33–36], neuroscience [37, 38], stroke [39], epilepsy [40], psychiatric disorders [41–43], traumatic brain injury (TBI) [44, 45], pediatric brain tumor [46], etc. HIE poses 3 unique challenges to ML: (i) lack of data: public data exists for hundreds of patients with brain tumors [47, 48], AD [49, 50], etc.…”