Correlative feature analysis of FFDM images

Yading Yuan; Maryellen L. Giger; Hui Li; Charlene Sennett

doi:10.1117/12.770524

Translator Disclaimer

17 March 2008 Correlative feature analysis of FFDM images

Yading Yuan, Maryellen L. Giger, Hui Li, Charlene Sennett

Author Affiliations +

Proceedings Volume 6915, Medical Imaging 2008: Computer-Aided Diagnosis; 69151L (2008) https://doi.org/10.1117/12.770524
Event: Medical Imaging, 2008, San Diego, California, United States

Abstract

Identifying the corresponding image pair of a lesion is an essential step for combining information from different views of the lesion to improve the diagnostic ability of both radiologists and CAD systems. Because of the non-rigidity of the breasts and the 2D projective property of mammograms, this task is not trivial. In this study, we present a computerized framework that differentiates the corresponding images from different views of a lesion from non-corresponding ones. A dual-stage segmentation method, which employs an initial radial gradient index(RGI) based segmentation and an active contour model, was initially applied to extract mass lesions from the surrounding tissues. Then various lesion features were automatically extracted from each of the two views of each lesion to quantify the characteristics of margin, shape, size, texture and context of the lesion, as well as its distance to nipple. We employed a two-step method to select an effective subset of features, and combined it with a BANN to obtain a discriminant score, which yielded an estimate of the probability that the two images are of the same physical lesion. ROC analysis was used to evaluate the performance of the individual features and the selected feature subset in the task of distinguishing between corresponding and non-corresponding pairs. By using a FFDM database with 124 corresponding image pairs and 35 non-corresponding pairs, the distance feature yielded an AUC (area under the ROC curve) of 0.8 with leave-one-out evaluation by lesion, and the feature subset, which includes distance feature, lesion size and lesion contrast, yielded an AUC of 0.86. The improvement by using multiple features was statistically significant as compared to single feature performance. (p<0.001)

Citation Download Citation

Yading Yuan, Maryellen L. Giger, Hui Li, and Charlene Sennett "Correlative feature analysis of FFDM images", Proc. SPIE 6915, Medical Imaging 2008: Computer-Aided Diagnosis, 69151L (17 March 2008); https://doi.org/10.1117/12.770524

ACCESS THE FULL ARTICLE