Identifying quantitative imaging features of posterior fossa syndrome in longitudinal MRI

Abstract

Abstract. Up to 25% of children who undergo brain tumor resection surgery in the posterior fossa develop posterior fossa syndrome (PFS). This syndrome is characterized by mutism and disturbance in speech. Our hypothesis is that there is a correlation between PFS and the occurrence of hypertrophic olivary degeneration (HOD) in structures within the posterior fossa, known as the inferior olivary nuclei (ION). HOD is exhibited as an increase in size and intensity of the ION on an MR image. Longitudinal MRI datasets of 28 patients were acquired consisting of pre-, intra-, and postoperative scans. A semiautomated segmentation process was used to segment the ION on each MR image. A full set of imaging features describing the first-and second-order statistics and size of the ION were extracted for each image. Feature selection techniques were used to identify the most relevant features among the MRI features, demographics, and data based on neuroradiological assessment. A support vector machine was used to analyze the discriminative features selected by a generative k-nearest neighbor algorithm. The results indicate the presence of hyperintensity in the left ION as the most diagnostically relevant feature, providing a statistically significant improvement in the classification of patients (p ¼ 0.01) when using this feature alone. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

CT radiomics to predict high‐risk intraductal papillary mucinous neoplasms of the pancreas

“…The performance of models designed with different combinations of features was evaluated with a tenfold cross‐validation technique. For small datasets, hold‐out validation is not feasible, and in such circumstances, cross‐validation is an effective choice . In tenfold cross‐validation, observations are randomly divided into ten groups.…”

“…For small datasets, hold-out validation is not feasible, and in such circumstances, crossvalidation is an effective choice. 36 In tenfold cross-validation, observations are randomly divided into ten groups. Each of the groups is used exactly once as the test set while the others are used for training (i.e., to select the important features and to design the predictive model with the selected features).…”

Post-operative pediatric cerebellar mutism syndrome and its association with hypertrophic olivary degeneration

“…We performed independent qualitative and quantitative analyses of the ION. The results of the quantitative analysis has been published earlier focusing on the technical aspect of the analysis (18). In this article we aim to combine the results of the analyses and discuss their clinical relevance.…”

“…The quantitative analysis of the MR imaging was performed in collaboration with The Centre for Vision, Speech and Signal Processing at the University of Surrey, UK. A detailed account of the analysis methodology and outcome has been published in an earlier article (18). In order to analyze the changes in the left and right ION with respect to their original state pre-operatively it was required to assess their state in the pre-operative scan, as well as on at least two post-operative scans.…”

“…This process involved selecting the subset of features listed in Table 1 prior to classification of the patients into POPCMS and non-POPCMS. The techniques used were random subset feature selection (RSFS), sequential forward selection (SFS) and sequential floating forward selection (SFFS) to obtain the most relevant subsets (18,(22)(23)(24). These algorithms were carried out 100 times each to obtain the average relevance scores.…”