http://ivylabprev.kaist.ac.kr/image/demo/top_logo.gif

 

http://ivylabprev.kaist.ac.kr/image/demo/project_title.gif

 

 

http://ivylabprev.kaist.ac.kr/image/demo/project_profile.gif

 

 

http://ivylabprev.kaist.ac.kr/image/demo/profile_title.gif

Feature extraction from inter-view similarity of DBT projection views

http://ivylabprev.kaist.ac.kr/image/demo/profile_period.gif

2015 . 02 ~ current

 

 

 

http://ivylabprev.kaist.ac.kr/image/demo/project_overview.gif

 

 

1.  Introduction

l  Digital breast tomosynthesis (DBT) is designed to alleviate a tissue overlap problem occurred in Mammography which is the frequent cause of false positives (FPs)

l  However, few studies have been focused on utilizing information between DBT projection views  (PVs) as features for FP reduction

l  In this paper, mass features based on inter-view similarity in PVs are proposed to reduce the FPs

l  The proposed method has been developed under the following facts:

l  Because PVs are taken in different angles, FPs induced by the tissue overlap could be observed differently between PVs, while masses could appear similar (Please see Fig. 1 (b) and (e))

 

2.  Proposed Inter-view Similarity Features

A.    Proposed inter-view similarity measure

l  By utilizing the normalized cross-correlation (NCC), inter-view similarity between ROIs on i-th and j-th PVs for the given lesion candidate is measured as follows:

where wi: the ROI on i-th projection view,  fj : the subimage on j-th projection view, s and t: the range of summation taken over the region shared by wi and fj

Fig. 1. Examples of (a) a mass and (d) a FP with corresponding ROI sets (b) and (e) and inter-view similarities R (c) and (f), respectively. Note that the ROI sets are sampled from odd PVs

 

Fig. 2. Zigzag scanned values of averaged inter-view similarities

 

B.    Proposed inter-view similarity measure

l  To extract the different inter-view similarity pattern between masses FPs as shown in Fig. 1 and Fig. 2, following features are devised

Table 1. Summary of the proposed inter-view similarity based features

 

3.  Experiments

A.    Experimental setup

l  Dataset: 43 sets of mass ROIs and 306 sets of FPs are generated by automatic mass detection

l  Classifier: Support Vector Machine (SVM) with RBF kernel

l  Performance metric: area under the ROC curves (AUC)

l  50 independent runs of random partition into training and testing sets

 

B.    Experimental results

l  The proposed features show higher AUC with small number of feature dimensions

l  The concatenated feature (proposed+LBP) achieves an improved AUC. This indicates the proposed features have complementary information with existing features

 

Fig. 3. Comparisons of classification performances in terms of AUC

 

4.  Conclusions

l  In this paper, we proposed a new inter-view similarity based features for classifying masses and FPs, aiming to effectively utilize inter-view information in PVs

l  Experimental results show that the proposed features can improve the mass classification performance in PVs

 

 

http://ivylabprev.kaist.ac.kr/image/demo/project_researcher.gif

 

Contact Person: Prof. Yong Man Ro (ymro@kaist.ac.kr)

 

 

http://ivylabprev.kaist.ac.kr/image/demo/project_publication.gif

1.     Dae Hoe Kim, Seong Tae Kim, and Yong Man Ro, Feature extraction from inter-view similarity of DBT projection views, SPIE Medical imaging, 2015.