PURPOSE: To evaluate a new method for automated determination of a region of interest (ROI) for the analysis of contrast enhancement in breast MRI. MATERIALS AND METHODS: Mean shift multidimensional clustering (MS-MDC) was employed to divide 92 lesions into several spatially contiguous clusters each, based on multiple enhancement parameters. The ROIs were defined as the clusters with the highest probability of malignancy. The performance of enhancement analysis within these ROIs was estimated using the area under the receiver operator characteristic curve (AUC), and compared against a radiologist's final assessment and a classifier using histogram analysis (HA). For HA, the first, second, and third quartiles were evaluated. RESULTS: MS-MDC resulted in AUC = 0.88 with a 95% confidence interval (CI) of 0.81-0.95. The AUC for the radiologist's assessment was 0.93 (95%CI = 0.87-0.97). Best HA performance was found using the first quartile, with AUC = 0.79 (95%CI = 0.69-0.88). There was no significant difference between MS-MDC and the radiologist (P = 0.40). The improvement of MS-MDC over HA was significant (P = 0.018). CONCLUSION: Mean shift clustering followed by automated selection of the most suspicious cluster resulted in accurate ROIs in breast MRI lesions. (c) 2007 Wiley-Liss, Inc.
PURPOSE: To evaluate a new method for automated determination of a region of interest (ROI) for the analysis of contrast enhancement in breast MRI. MATERIALS AND METHODS: Mean shift multidimensional clustering (MS-MDC) was employed to divide 92 lesions into several spatially contiguous clusters each, based on multiple enhancement parameters. The ROIs were defined as the clusters with the highest probability of malignancy. The performance of enhancement analysis within these ROIs was estimated using the area under the receiver operator characteristic curve (AUC), and compared against a radiologist's final assessment and a classifier using histogram analysis (HA). For HA, the first, second, and third quartiles were evaluated. RESULTS: MS-MDC resulted in AUC = 0.88 with a 95% confidence interval (CI) of 0.81-0.95. The AUC for the radiologist's assessment was 0.93 (95%CI = 0.87-0.97). Best HA performance was found using the first quartile, with AUC = 0.79 (95%CI = 0.69-0.88). There was no significant difference between MS-MDC and the radiologist (P = 0.40). The improvement of MS-MDC over HA was significant (P = 0.018). CONCLUSION: Mean shift clustering followed by automated selection of the most suspicious cluster resulted in accurate ROIs in breast MRI lesions. (c) 2007 Wiley-Liss, Inc.