Justification Automatic brain tumor classification by MRS has been under development for more than a decade. Nonetheless, to our knowledge, there are no published evaluations of predictive models with unseen cases that are subsequently acquired in different centers. The multicenter eTUMOUR project (2004)(2005)(2006)(2007)(2008)(2009), which builds upon previous expertise from the INTERPRET project (2000INTERPRET project ( -2002 has allowed such an evaluation to take place. Materials and Methods A total of 253 pairwise classifiers for glioblastoma, meningioma, metastasis, and low-grade glial diagnosis were inferred based on 211 SV short TE INTERPRET MR spectra obtained at 1.5 T (PRESS or STEAM, 20-32 ms) and automatically pre-processed. Afterwards, the classifiers were tested with 97 spectra, which were subsequently compiled during eTUMOUR. ResultsIn our results based on subsequently acquired spectra, accuracies of around 90% were achieved for most of the pairwise discrimination problems. The exception was for the glioblastoma versus metastasis discrimination, which was below 78%. A more clear definition of metastases may be obtained by other approaches, such as MRSI + MRI. Conclusions The prediction of the tumor type of in-vivo MRS is possible using classifiers developed from previously acquired data, in different hospitals with different instrumentation under the same acquisition protocols. This methodology may find application for assisting in the diagnosis of new brain tumor cases and for the quality control of multicenter MRS databases.

Purpose To determine if preoperative vascular heterogeneity of glioblastoma is predictive of overall survival of patients undergoing standard-of-care treatment by using an unsupervised multiparametric perfusion-based habitat-discovery algorithm. Materials and Methods Preoperative magnetic resonance (MR) imaging including dynamic susceptibility-weighted contrast material-enhanced perfusion studies in 50 consecutive patients with glioblastoma were retrieved. Perfusion parameters of glioblastoma were analyzed and used to automatically draw four reproducible habitats that describe the tumor vascular heterogeneity: high-angiogenic and low-angiogenic regions of the enhancing tumor, potentially tumor-infiltrated peripheral edema, and vasogenic edema. Kaplan-Meier and Cox proportional hazard analyses were conducted to assess the prognostic potential of the hemodynamic tissue signature to predict patient survival. Results Cox regression analysis yielded a significant correlation between patients' survival and maximum relative cerebral blood volume (rCBV) and maximum relative cerebral blood flow (rCBF) in high-angiogenic and low-angiogenic habitats (P < .01, false discovery rate-corrected P < .05). Moreover, rCBF in the potentially tumor-infiltrated peripheral edema habitat was also significantly correlated (P < .05, false discovery rate-corrected P < .05). Kaplan-Meier analysis demonstrated significant differences between the observed survival of populations divided according to the median of the rCBV or rCBF at the high-angiogenic and low-angiogenic habitats (log-rank test P < .05, false discovery rate-corrected P < .05), with an average survival increase of 230 days. Conclusion Preoperative perfusion heterogeneity contains relevant information about overall survival in patients who undergo standard-of-care treatment. The hemodynamic tissue signature method automatically describes this heterogeneity, providing a set of vascular habitats with high prognostic capabilities. RSNA, 2018.

ElsevierVicente Robledo, J.; Fuster Garcia, E.; Tortajada Velert, S.; García Gómez, JM.; Davies, N.; Natarajan, K.; Wilson, M.... (2013) Integration. Linear Discriminant Analysis was applied to this data to produce diagnostic classifiers. An evaluation of the diagnostic accuracy was performed based on resampling to measure the Balanced Accuracy Rate (BAR). Results:The accuracy of the diagnostic classifiers for discriminating the three tumour types was found to be high (BAR 0.98) when a combination of TE was used. The combination of both TE significantly improved the classification performance (p < 0.01, Tukeyʼs test) compared with the use of one TE alone. 3Other tumour types were classified accurately as glial or primitive neuroectodermal (BAR 1.00). 12 cases failed the inclusion criteria for QC mainly due to poor SNR. Conclusions Classification and evaluation 9The diagnostic classification problem of discriminating between EPEN, PILOA and MED, the three most common pediatric tumour types, is addressed in this study. Since EPEN and PILOA tumours can be found in brain locations other than the PF whereas MED are found only in the PF, training was undertaken twice, once using the tumour cases located in the PF and then with those in any brain location. Classifiers were designed and evaluated using features from Short-TE and Long-TE alone and a combination of both TEs, ShortTE+Long-TE. Our results were compared with those in previous studies [27][28][29][30].Based on the results of previous studies [15,20,26,29 Results Spectral featuresSeveral key features allow visual discrimination of PILOA, EPEN and MED. Figures 1 and 2 show the Short-TE and Long-TE mean spectra of the tumour types. Minimum differences are found between the mean spectra of the tumours in the PF and those in any location. All tumour spectra display an increase in Cho peak (3.2ppm) with respect to Cr peak (3.0ppm). NAA (2.0ppm) presents a less prominent peak in MED and EPEN compared with 10 PILOA. Elevation of macromolecules and lipids (0.9ppm and 1.3ppm) is observed in Short-TE. Regarding Long-TE, the inverted peak of Lac at 1.3ppm is distinguished in PILOA and EPEN but not in MED. Tables 2 and 3 show the metabolite concentrations estimated with TARQUIN in Short-TE and Long-TE for the three tumour types found in any brain location. The Kruskal-Wallis test for the analysis of the variance (α=0.05) was applied to determine the significant differences in metabolite concentrations of PILOA, EPEN and MED. Both Cho components, Glycerophosphocholine (GPC) and Phosphocholine (PCh) (p≤0.01) showed significant differences. Cr and Tau concentrations were significantly different in both TEs (p≤0.01). Univariate metabolite comparisonDifferences in the mI concentrations (p≤0.01) were significant in Short-TE.Macromolecules and lipids at 0.9, 1.3 and 2.0ppm (p≤0.05, p≤0.01 and p≤0.01, respectively) exhibited statistical differences in Short-TE MRS. Classification DiscussionThis is the first study of MRS as a non-invasive diagnostic aid in childhood brain tumo...

No abstract