Premium
Computerized characterization of breast masses on three‐dimensional ultrasound volumes
Author(s) -
Sahiner Berkman,
Chan HeangPing,
Roubidoux Marilyn A.,
Helvie Mark A.,
Hadjiiski Lubomir M.,
Ramachandran Aditya,
Paramagul Chintana,
LeCarpentier Gerald L.,
Nees Alexis,
Blane Caroline
Publication year - 2004
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 - 10.1118/1.1649531
Subject(s) - initialization , artificial intelligence , breast ultrasound , segmentation , active contour model , linear discriminant analysis , pattern recognition (psychology) , receiver operating characteristic , computer science , computer aided diagnosis , ultrasound , robustness (evolution) , mammography , image segmentation , breast imaging , mathematics , radiology , breast cancer , medicine , machine learning , biochemistry , chemistry , cancer , gene , programming language
We are developing computer vision techniques for the characterization of breast masses as malignant or benign on radiologic examinations. In this study, we investigated the computerized characterization of breast masses on three‐dimensional (3‐D) ultrasound (US) volumetric images. We developed 2‐D and 3‐D active contour models for automated segmentation of the mass volumes. The effect of the initialization method of the active contour on the robustness of the iterative segmentation method was studied by varying the contour used for its initialization. For a given segmentation, texture and morphological features were automatically extracted from the segmented masses and their margins. Stepwise discriminant analysis with the leave‐one‐out method was used to select effective features for the classification task and to combine these features into a malignancy score. The classification accuracy was evaluated using the area A zunder the receiver operating characteristic (ROC) curve, as well as the partial area index A z( 0.9 ), defined as the relative area under the ROC curve above a sensitivity threshold of 0.9. For the purpose of comparison with the computer classifier, four experienced breast radiologists provided malignancy ratings for the 3‐D US masses. Our dataset consisted of 3‐D US volumes of 102 biopsied masses (46 benign, 56 malignant). The classifiers based on 2‐D and 3‐D segmentation methods achieved test A zvalues of 0.87±0.03 and 0.92±0.03, respectively. The difference in the A zvalues of the two computer classifiers did not achieve statistical significance. The A zvalues of the four radiologists ranged between 0.84 and 0.92. The difference between the computer's A zvalue and that of any of the four radiologists did not achieve statistical significance either. However, the computer's A z( 0.9 )value was significantly higher than that of three of the four radiologists. Our results indicate that an automated and effective computer classifier can be designed for differentiating malignant and benign breast masses on 3‐D US volumes. The accuracy of the classifier designed in this study was similar to that of experienced breast radiologists.