Purpose: To develop and evaluate a method for an automatic detection of brain metastases in MR images.
Materials and methods: Nineteen patients were scanned using a 1.5 Tesla MR scanner. Two radiologists and a radiation oncologist marked the location of the brain metastases. The training group consisted of eight patients harboring 20 metastases. First, three-dimensional (3D) tumor-appearance templates were cross-correlated with MR brain images to evaluate their similarity, and a correlation threshold was established for metastasis candidates. Afterward, a method to reduce false positive rate (FPR) was applied: each detected object was segmented and its degree of anisotropy (DA) was obtained, removing the elongated structures with a DA above the optimal value from the receiver operating characteristic curve. Finally, the method was statistically validated in two groups: 11 patients with 42 brain metastases and 11 patients without metastases.
Results: The method led to a sensitivity of 80% and an FPR per slice of 0.023 and 2.75 per patient in the training group. In the first validation group, a sensitivity of 88.10% and an FPR per slice of 0.05 corresponding to 6.91 false positives per patient were obtained. DA implementation decreased 3.5 times FPR compared with templates alone. It improved the radiologist's performance in metastases less than 10 mm from 89-93% to 100%. In the second validation group the FPR was 0.04 per slice and 5.18 per patient.
Conclusion: This method demonstrates that 3D template matching applying DA technique has high sensitivity and low FPR for detecting brain metastases in MR images. J. Magn. Reson. Imaging 2016;44:642-652.
Keywords: brain metastasis; computer-aided detection; degree of anisotropy; magnetic resonance imaging; template matching.
© 2016 International Society for Magnetic Resonance in Medicine.