Improvement of mammographic mass characterization using spiculation measures and morphological features
Authors:
- Berkman SahinerBSBerkman Sahiner
- Heang‐Ping ChanHCHeang‐Ping Chan
- Nicholas PetrickNPNicholas Petrick
- Mark A. HelvieMHMark A. Helvie
- Lubomir M. HadjiiskiLHLubomir M. Hadjiiski
- 6 July 2001
- journal article
- Published by Wiley in Medical Physics
- Vol. 28 (7) , 1455-1465
Abstract
We are developing new computer vision techniques for characterization of breast masses on mammograms. We had previously developed a characterization method based on texture features. The goal of the present work was to improve our characterization method by making use of morphological features. Toward this goal, we have developed a fully automated, three‐stage segmentation method that includes clustering, active contour, and spiculation detection stages. After segmentation, morphological features describing the shape of the mass were extracted. Texture features were also extracted from a band of pixels surrounding the mass. Stepwise feature selection and linear discriminant analysis were employed in the morphological, texture, and combined feature spaces for classifier design. The classification accuracy was evaluated using the area under the receiver operating characteristic curve. A data set containing 249 films from 102 patients was used. When the leave‐one‐case‐out method was applied to partition the data set into trainers and testers, the average test for the task of classifying the mass on a single mammographic view was 0.83±0.02, 0.84±0.02, and 0.87±0.02 in the morphological, texture, and combined feature spaces, respectively. The improvement obtained by supplementing texture features with morphological features in classification was statistically significant For classifying a mass as malignant or benign, we combined the leave‐one‐case‐out discriminant scores from different views of a mass to obtain a summary score. In this task, the test value using the combined feature space was 0.91±0.02. Our results indicate that combining texture features with morphological features extracted from automatically segmented mass boundaries will be an effective approach for computer‐aided characterization of mammographic masses.Keywords
This publication has 42 references indexed in Scilit:
- Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture imagesIEEE Transactions on Medical Imaging, 1996
- Detection of stellate distortions in mammogramsIEEE Transactions on Medical Imaging, 1996
- Computer-aided diagnosis of breast cancer: Artificial neural network approach for optimized merging of mammographic featuresAcademic Radiology, 1995
- Computer-aided classification of mammographic masses and normal tissue: linear discriminant analysis in texture feature spacePhysics in Medicine & Biology, 1995
- Feature selection in the pattern classification problem of digital chest radiograph segmentationIEEE Transactions on Medical Imaging, 1995
- Application of shape analysis to mammographic calcificationsIEEE Transactions on Medical Imaging, 1994
- Mammographic feature analysisSeminars in Roentgenology, 1993
- Classifying mammographic lesions using computerized image analysisIEEE Transactions on Medical Imaging, 1993
- Generic neighborhood operatorsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992
- A Fast algorithm for active contours and curvature estimationCVGIP: Image Understanding, 1992