Automated analysis of contrast enhancement in breast MRI lesions using mean shift clustering for ROI selection

@article{citeulike:1606701, abstract = {To evaluate a new method for automated determination of a region of interest (ROI) for the analysis of contrast enhancement in breast MRI.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.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).Mean shift clustering followed by automated selection of the most suspicious cluster resulted in accurate ROIs in breast MRI lesions. J. Magn. Reson. Imaging 2007;26:606-614. {\copyright} 2007 Wiley-Liss, Inc.}, address = {Radboud University Medical Centre, Department of Radiology, Nijmegen, The Netherlands; Ikazia Hospital, Department of Radiology, Rotterdam, The Netherlands}, author = {Stoutjesdijk, Mark J. and Veltman, Jeroen and Huisman, Henkjan and Karssemeijer, Nico and Barentsz, Jelle O. and Blickman, Johan G. and Boetes, Carla }, citeulike-article-id = {1606701}, doi = {10.1002/jmri.21026}, journal = {Journal of Magnetic Resonance Imaging}, keywords = {breast, cancer, dce-mri, mean-shift, mri, segmentation}, number = {3}, pages = {606--614}, posted-at = {2007-08-30 07:39:24}, priority = {5}, title = {Automated analysis of contrast enhancement in breast MRI lesions using mean shift clustering for ROI selection}, url = {http://dx.doi.org/10.1002/jmri.21026}, volume = {26}, year = {2007} }

TY - JOUR ID - citeulike:1606701 L3 - citeulike-article-id:1606701 TI - Automated analysis of contrast enhancement in breast MRI lesions using mean shift clustering for ROI selection JF - Journal of Magnetic Resonance Imaging VL - 26 IS - 3 SP - 606 EP - 614 AD - Radboud University Medical Centre, Department of Radiology, Nijmegen, The Netherlands; Ikazia Hospital, Department of Radiology, Rotterdam, The Netherlands N2 - To evaluate a new method for automated determination of a region of interest (ROI) for the analysis of contrast enhancement in breast MRI.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.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).Mean shift clustering followed by automated selection of the most suspicious cluster resulted in accurate ROIs in breast MRI lesions. J. Magn. Reson. Imaging 2007;26:606-614. © 2007 Wiley-Liss, Inc. KW - breast KW - cancer KW - dce-mri KW - mean-shift KW - mri KW - segmentation AU - Stoutjesdijk, Mark AU - Veltman, Jeroen AU - Huisman, Henkjan AU - Karssemeijer, Nico AU - Barentsz, Jelle AU - Blickman, Johan AU - Boetes, Carla PY - 2007/// UR - http://dx.doi.org/10.1002/jmri.21026 ER -