Carles Majós

A computer-based decision support system to assist radiologists in diagnosing and grading brain tumours has been developed by the multi-centre INTERPRET project. Spectra from a database of 1H single-voxel spectra of different types of brain tumours, acquired in vivo from 334 patients at four different centres, are clustered according to their pathology, using automated pattern recognition techniques and the results are presented as a two-dimensional scatterplot using an intuitive graphical user interface (GUI). Formal quality control procedures were performed to standardize the performance of the instruments and check each spectrum, and teams of expert neuroradiologists, neurosurgeons, neurologists and neuropathologists clinically validated each case. The prototype decision support system (DSS) successfully classified 89% of the cases in an independent test set of 91 cases of the most frequent tumour types (meningiomas, low-grade gliomas and high-grade malignant tumours--glioblastomas and metastases). It also helps to resolve diagnostic difficulty in borderline cases. When the prototype was tested by radiologists and other clinicians it was favourably received. Results of the preliminary clinical analysis of the added value of using the DSS for brain tumour diagnosis with MRS showed a small but significant improvement over MRI used alone. In the comparison of individual pathologies, PNETs were significantly better diagnosed with the DSS than with MRI alone.

BACKGROUND AND PURPOSE: Different TE can be used for obtaining MR spectra of brain tumors. The purpose of this study was to determine the influence of the TE used in brain tumor classification by comparing the performance of spectra obtained at two different TE (30 ms and 136 ms). METHODS: One hundred fifty-one studies of patients with brain tumors (37 meningiomas, 12 low grade astrocytomas, 16 anaplastic astrocytomas, 54 glioblastomas, and 32 metastases) were retrospectively selected from a series of 378 consecutive examinations of brain masses. Single voxel proton MR spectroscopy at TE 30 ms and 136 ms was performed with point-resolved spectroscopy in all cases. Fitted areas of nine resonances of interest were normalized to water. Tumors were classified into four groups (meningioma, low grade astrocytoma, anaplastic astrocytoma, and glioblastoma-metastases) by means of linear discriminant analysis. The performance of linear discriminant analysis at each TE was assessed by using the leave-one-out method. RESULTS: Tumor classification was slightly better at short TE (123 [81%] of 151 cases correctly classified) than at long TE (118 [78%] of 151 cases correctly classified). Meningioma was the only group that showed higher sensitivity and specificity at long TE. Improved results were obtained when both TE were considered simultaneously: the suggested diagnosis was correct in 105 (94%) of 112 cases when both TE agreed, whereas the correct diagnosis was suggested by at least one TE in 136 (90%) of 151 cases. CONCLUSION: Short TE provides slightly better tumor classification, and results improve when both TE are considered simultaneously. Meningioma was the only tumor group in which long TE performed better than short TE.

Automated pattern recognition techniques are needed to help radiologists categorize MRS data of brain tumors according to histological type and grade. A major question is whether a computer program "trained" on spectra from one hospital will be able to classify those from another, particularly if the acquisition protocol is different. A subset of 144 histopathologically validated brain tumor spectra in the INTERPRET database, obtained from three of the collaborating centers, was grouped into meningiomas, low-grade astrocytomas, and "aggressive tumors" (glioblastomas and metastases). Spectra from two centers formed the training set (94 spectra) while the third acted as the test set (50 spectra). Linear discriminant analysis successfully classified 48/50 in the test set; the remaining two were atypical cases. When the training and test sets were combined, 133 of the 144 spectra were correctly classified using the leave-one-out procedure. These spectra had been obtained using different sequences (STEAM and PRESS), different echo times (20, 30, 31, and 32 ms), different repetition times (1600 and 2000 ms), and different manufacturers' instruments (GE and Philips). Pattern recognition algorithms are less sensitive to acquisition parameters than had been expected.