Fully automatic lesion segmentation in breast MRI using mean-shift and graph-cuts on a region adjacency graph

• Published in: Journal of magnetic resonance imaging Vol. 39; no. 4; pp. 795 - 804
• Main Authors: McClymont, Darryl, Mehnert, Andrew, Trakic, Adnan, Kennedy, Dominic, Crozier, Stuart
• Format: Journal Article
• Language: English
• Published: United States Blackwell Publishing Ltd 01.04.2014; Wiley Subscription Services, Inc
• Subjects: Adult; Aged, 80 and over; Algorithms; Artificial Intelligence; automated segmentation; breast MRI; Breast Neoplasms - pathology; CONTRAST; ENHANCEMENT; Equipment Design; Equipment Failure Analysis; Female; FRAMEWORK; graph-cuts; Humans; image analysis; Image Enhancement - instrumentation; Image Enhancement - methods; Image Interpretation, Computer-Assisted - instrumentation; Image Interpretation, Computer-Assisted - methods; IMAGE SEGMENTATION; Magnetic resonance imaging; Magnetic Resonance Imaging - instrumentation; Magnetic Resonance Imaging - methods; Male; mean-shift; Middle Aged; Pattern Recognition, Automated - methods; Reproducibility of Results; SELECTION; Sensitivity and Specificity; suspicious lesion; Young Adult
• ISSN: 1053-1807; 1522-2586; 1522-2586
• DOI: 10.1002/jmri.24229

Purpose To present and evaluate a fully automatic method for segmentation (i.e., detection and delineation) of suspicious tissue in breast MRI. Materials and Methods The method, based on mean‐shift clustering and graph‐cuts on a region adjacency graph, was developed and its parameters tuned using multimodal (T1, T2, DCE‐MRI) clinical breast MRI data from 35 subjects (training data). It was then tested using two data sets. Test set 1 comprises data for 85 subjects (93 lesions) acquired using the same protocol and scanner system used to acquire the training data. Test set 2 comprises data for eight subjects (nine lesions) acquired using a similar protocol but a different vendor's scanner system. Each lesion was manually delineated in three‐dimensions by an experienced breast radiographer to establish segmentation ground truth. The regions of interest identified by the method were compared with the ground truth and the detection and delineation accuracies quantitatively evaluated. Results One hundred percent of the lesions were detected with a mean of 4.5 ± 1.2 false positives per subject. This false‐positive rate is nearly 50% better than previously reported for a fully automatic breast lesion detection system. The median Dice coefficient for Test set 1 was 0.76 (interquartile range, 0.17), and 0.75 (interquartile range, 0.16) for Test set 2. Conclusion The results demonstrate the efficacy and accuracy of the proposed method as well as its potential for direct application across different MRI systems. It is (to the authors' knowledge) the first fully automatic method for breast lesion detection and delineation in breast MRI. J. Magn. Reson. Imaging 2014;39:795–804. © 2013 Wiley Periodicals, Inc.