Abstract
We applied machine learning algorithms for differentiation of posterior fossa tumors using apparent diffusion coefficient (ADC) histogram analysis and structural MRI findings. A total of 256 patients with intra-axial posterior fossa tumors were identified, of whom 248 were included in machine learning analysis, with at least 6 representative subjects per each tumor pathology. The ADC histograms of solid components of tumors, structural MRI findings, and patients' age were applied to construct decision models using Classification and Regression Tree analysis. We also compared different machine learning classification algorithms (i.e., naïve Bayes, random forest, neural networks, support vector machine with linear and polynomial kernel) for dichotomized differentiation of the 5 most common tumors in our cohort: metastasis (n = 65), hemangioblastoma (n = 44), pilocytic astrocytoma (n = 43), ependymoma (n = 27), and medulloblastoma (n = 26). The decision tree model could differentiate seven tumor histopathologies with terminal nodes yielding up to 90% accurate classification rates. In receiver operating characteristics (ROC) analysis, the decision tree model achieved greater area under the curve (AUC) for differentiation of pilocytic astrocytoma (p = 0.020); and atypical teratoid/rhabdoid tumor ATRT (p = 0.001) from other types of neoplasms compared to the official clinical report. However, neuroradiologists' interpretations had greater accuracy in differentiating metastases (p = 0.001). Among different machine learning algorithms, random forest models yielded the highest accuracy in dichotomized classification of the 5 most common tumor types; and in multiclass differentiation of all tumor types random forest yielded an averaged AUC of 0.961 in training datasets, and 0.873 in validation samples. Our study demonstrates the potential application of machine learning algorithms and decision trees for accurate differentiation of brain tumors based on pretreatment MRI. Using easy to apply and understandable imaging metrics, the proposed decision tree model can help radiologists with differentiation of posterior fossa tumors, especially in tumors with similar qualitative imaging characteristics. In particular, our decision tree model provided more accurate differentiation of pilocytic astrocytomas from ATRT than by neuroradiologists in clinical reads.
Highlights
The current standard of care for patients presenting with posterior fossa tumors is maximal safe resection of tumor, decompression to eliminate mass effect, and radiochemotherapy
Patients with metastasis and hemangioblastomas were older than those with anaplastic astrocytoma, low-grade glioma, and glioblastoma multiforme. (B) On post hoc analysis, metastases, hemangioblastomas, and lymphomas had larger diameter of peritumoral Fluid Attenuated Inversion Recovery (FLAIR) hyperintensity compared to medulloblastoma, pilocytic astrocytomas, ependymomas, low-grade glioma, ATRT, and subependymomas—likely since latter tumors tend to be intraventricular with virtually no peritumoral edema
The peritumoral FLAIR hyperintensity surrounding metastases, and hemangioblastomas was larger in diameter compared to anaplastic astrocytoma, and glioblastoma multiforme. (C) On post hoc analysis of tumor volumes, pilocytic astrocytomas, medulloblastomas, and ATRTs had larger size compared to metastases
Summary
The current standard of care for patients presenting with posterior fossa tumors is maximal safe resection of tumor, decompression to eliminate mass effect, and radiochemotherapy. While histopathological evaluation is currently the gold standard for brain tumors diagnosis, there is growing body of evidence that combination of quantitative imagining and machine learning algorithms can help with non-invasive differentiation of brain neoplasms based on pre-treatment MRI [1, 2]. Recent studies demonstrate the added value of quantitative diffusion analysis in differentiation of posterior fossa tumors, besides conventional structural MRI findings such as peritumoral edema, enhancement pattern, location, or extension through the foramina of Luschka/Magendie [8,9,10]. Prior studies were limited by restricting their analysis pool to select tumor types, analyzing few ADC quantitative metrics (e.g., ADC means, median, or minimum), or only evaluating ADC values on a single slice, not accounting for tumor heterogeneity [11, 12]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
