Premium
B‐spline active rays segmentation of microcalcifications in mammography
Author(s) -
Arikidis Nikolaos S.,
Skiadopoulos Spyros,
Karahaliou Anna,
Likaki Eleni,
Panayiotakis George,
Costaridou Lena
Publication year - 2008
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.2991286
Subject(s) - microcalcification , segmentation , artificial intelligence , pattern recognition (psychology) , mammography , computer science , active contour model , receiver operating characteristic , computer vision , mathematics , image segmentation , medicine , cancer , machine learning , breast cancer
Accurate segmentation of microcalcifications in mammography is crucial for the quantification of morphologic properties by features incorporated in computer‐aided diagnosis schemes. A novel segmentation method is proposed implementing active rays (polar‐transformed active contours) on B‐spline wavelet representation to identify microcalcification contour point estimates in a coarse‐to‐fine strategy at two levels of analysis. An iterative region growing method is used to delineate the final microcalcification contour curve, with pixel aggregation constrained by the microcalcification contour point estimates. A radial gradient‐based method was also implemented for comparative purposes. The methods were tested on a dataset consisting of 149 mainly pleomorphic microcalcification clusters originating from 130 mammograms of the DDSM database. Segmentation accuracy of both methods was evaluated by three radiologists, based on a five‐point rating scale. The radiologists’ average accuracy ratings were 3.96 ± 0.77 , 3.97 ± 0.80 , and 3.83 ± 0.89 for the proposed method, and 2.91 ± 0.86 , 2.10 ± 0.94 , and 2.56 ± 0.76 for the radial gradient‐based method, respectively, while the differences in accuracy ratings between the two segmentation methods were statistically significant (Wilcoxon signed‐ranks test, p < 0.05 ). The effect of the two segmentation methods in the classification of benign from malignant microcalcification clusters was also investigated. A least square minimum distance classifier was employed based on cluster features reflecting three morphological properties of individual microcalcifications (area, length, and relative contrast). Classification performance was evaluated by means of the area under ROC curve ( A z ) . The area and length morphologic features demonstrated a statistically significant (Mann‐Whitney U‐test, p < 0.05 ) higher patient‐based classification performance when extracted from microcalcifications segmented by the proposed method ( 0.82 ± 0.06 and 0.86 ± 0.05 , respectively), as compared to segmentation by the radial gradient‐based method ( 0.71 ± 0.08 and 0.75 ± 0.08 ). The proposed method demonstrates improved segmentation accuracy, fulfilling human visual criteria, and enhances the ability of morphologic features to characterize microcalcification clusters.