The Diagnostic Value of MRI-Based Texture Analysis in Discrimination of Tumors Located in Posterior Fossa: A Preliminary Study

• Published in: Frontiers in neuroscience Vol. 13; p. 1113
• Main Authors: Zhang, Yang, Chen, Chaoyue, Tian, Zerong, Feng, Ridong, Cheng, Yangfan, Xu, Jianguo
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 23.10.2019; Frontiers Media S.A
• Subjects: Brain cancer; brain metastatic tumor; Brain tumors; Entropy; hemangioblastoma; Lymphoma; Magnetic resonance imaging; Medical imaging; Medulloblastoma; Metastases; Metastasis; Nervous system; Neuroscience; Neurosurgery; NMR; Nuclear magnetic resonance; Pediatrics; posterior fossa tumors; Studies; texture analysis; Tumors; China; brain metastatic tumor; magnetic resonance imaging; hemangioblastoma; posterior fossa tumors; medulloblastoma; texture analysis
• ISSN: 1662-4548; 1662-453X; 1662-453X
• DOI: 10.3389/fnins.2019.01113

To investigate the diagnostic value of MRI-based texture analysis in discriminating common posterior fossa tumors, including medulloblastoma, brain metastatic tumor, and hemangioblastoma. A total number of 185 patients were enrolled in the current study: 63 of them were diagnosed with medulloblastoma, 56 were diagnosed with brain metastatic tumor, and 66 were diagnosed with hemangioblastoma. Texture features were extracted from contrast-enhanced T1-weighted (T1C) images and fluid-attenuation inversion recovery (FLAIR) images within two matrixes. Mann-Whitney test was conducted to identify whether texture features were significantly different among subtypes of tumors. Logistic regression analysis was performed to assess if they could be taken as independent predictors and to establish the integrated models. Receiver operating characteristic analysis was conducted to evaluate their performances in discrimination. There were texture features from both T1C images and FLAIR images found to be significantly different among the three types of tumors. The integrated model represented that the promising diagnostic performance of texture analysis depended on a series of features rather than a single feature. Moreover, the predictive model that combined texture features and clinical feature implied feasible performance in prediction with an accuracy of 0.80. MRI-based texture analysis could potentially be served as a radiological method in discrimination of common tumors located in posterior fossa.