Assessing preoperative risk of STR in skull meningiomas using MR radiomics and machine learning

Abstract

Our aim is to predict possible gross total and subtotal resections of skull meningiomas from pre-treatment T1 post contrast MR-images using radiomics and machine learning in a representative patient cohort. We analyse the accuracy of our model predictions depending on the tumor location within the skull and the postoperative tumor volume. In this retrospective, IRB-approved study, image segmentation of the contrast enhancing parts of the tumor was semi-automatically performed using the 3D Slicer open-source software platform. Imaging data were split into training data and independent test data at random. We extracted a total of 107 radiomic features by hand-delineated regions of interest on T1 post contrast MR images. Feature preselection and model construction were performed with eight different machine learning algorithms. Each model was estimated 100 times on new training data and then tested on a previously unknown, independent test data set to avoid possible overfitting. Our cohort included 138 patients. A gross total resection of the meningioma was performed in 107 cases and a subtotal resection in the remaining 31 cases. Using the training data, the mean area under the curve (AUC), mean accuracy, mean kappa, mean sensitivity and mean specificity were 0.901, 0.875, 0.629, 0.675 and 0.933 respectively. We obtained very similar results with the independent test data: mean AUC = 0.900, mean accuracy = 0.881, mean kappa = 0.644, mean sensitivity = 0.692 and mean specificity = 0.936. Thus, our model exposes good and stable predictive performance with both training and test data. Our radiomics approach shows that with machine learning algorithms and comparatively few explanatory factors such as the location of the tumor within the skull as well as its shape, it is possible to make accurate predictions about whether a meningioma can be completely resected by surgery. Complete resections and resections with larger postoperative tumor volumes can be predicted with very high accuracy. However, cases with very small postoperative tumor volumes are comparatively difficult to predict correctly.

Impact of Shape Irregularity in Medial Sphenoid Wing Meningiomas on Postoperative Cranial Nerve Functioning, Proliferation, and Progression-Free Survival

“…(3) Irregularly shaped MSWMs are significantly more challenging to operate and are at an increased risk of subtotal resection compared with regularly shaped MSWMS. This finding has been described by Musigmann et al [ 43 ], who performed a retrospective review using radiomics and machine learning to assess the preoperative risk of subtotal resection in skull meningiomas. Skull-base meningiomas or posterior fossa meningiomas with an irregular shape are at an increased risk of incomplete resection.…”

Use Test of Automated Machine Learning in Cancer Diagnostics

“…Krähling et al developed an MRI-based radiomics model to predict mitotic cycles in intracranial meningiomas before surgery [3]. In Musigmann et al, it was shown that ML algorithms can predict possible total and subtotal resections of skull meningiomas using pre-treatment T1 post-contrast MR images [4].…”

A magnetic resonance imaging based radiomics model to predict mitosis cycles in intracranial meningioma

“…Concerning meningiomas, a few previous studies have explored the utility of radiomics for the prediction of recurrence in surgically treated meningiomas 14 . Previous studies have already shown that statements regarding the probability of complete surgical resectability of meningiomas can be made by radiomics-based analysis of MRI images 15 . Furthermore, there are research approaches that evaluate semantic features such as heterogeneity of the tumour tissue, external shape or the mass effect caused by the tumour using radiomics-based analysis for meningioma grading 16 .…”