8 June 2006 in NMR in Biomedicine
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. Copyright © 2006 John Wiley & Sons, Ltd.
31 December 2002 in Magnetic Resonance in Medicine
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. Magn Reson Med 49:29–36, 2003.
1 September 2004 in Journal of Magnetic Resonance
1 May 2004 in Artificial Intelligence in Medicine
1 March 2003 in European Radiology
1 November 2002 in Radiology
To assess the utility of proton magnetic resonance (MR) spectroscopy in the clinical categorization of primitive neuroectodermal tumors (PNETs) in adults. In vivo proton MR spectroscopy was performed with an echo time of 136 msec in nine adults with PNET, and findings were retrospectively compared with spectroscopic findings of 22 meningiomas, 12 low-grade astrocytomas, eight anaplastic astrocytomas, 23 glioblastomas, and 21 metastases. Nine resonances were semiquantitatively evaluated. Statistical analysis was performed by using Kruskal-Wallis and Mann-Whitney U tests. The Hochberg correction was applied for multiple comparisons. Results were prospectively validated in 24 tumors of the six types included in the study. The resonances of choice for identifying PNET were alanine (P <.001) and glutamate and glutamine (P =.004), both decreased with respect to meningioma; choline increased with respect to low-grade (P <.001) and anaplastic astrocytoma (P =.055); and lipids at 1.30 ppm decreased and choline and other trimethyl-amine-containing compounds increased with respect to glioblastoma (P <.001 and P =.004, respectively) and metastasis (P <.001 and P =.021, respectively). We developed an algorithm for bilateral differential diagnosis between PNET and other tumor types. The leave-one-out method was used to test the five possible differential situations in the retrospective data set, with the following results: PNET versus meningioma, 31/23/5/3 (number of total/correct/unclassifiable/incorrect procedures); PNET versus low-grade astrocytoma, 21/19/2/0; PNET versus anaplastic astrocytoma, 17/6/9/2; PNET versus glioblastoma, 32/28/2/2; and PNET versus metastasis, 30/27/1/2. In total, 131 consecutive procedures produced 103 (79%) correct classifications and nine (7%) misclassifications. Twenty-five (78%) of 32 possible procedures in the prospective independent test set produced correct classifications and four (13%) produced incorrect classifications. In vivo proton MR spectroscopy provides useful information in clinical differentiation between PNETs and common brain tumors in adults.