Title | ||
---|---|---|
Computer-aided lesion diagnosis in automated 3-D breast ultrasound using coronal spiculation. |
Abstract | ||
---|---|---|
A computer-aided diagnosis (CAD) system for the classification of lesions as malignant or benign in automated 3-D breast ultrasound (ABUS) images, is presented. Lesions are automatically segmented when a seed point is provided, using dynamic programming in combination with a spiral scanning technique. A novel aspect of ABUS imaging is the presence of spiculation patterns in coronal planes perpendicular to the transducer. Spiculation patterns are characteristic for malignant lesions. Therefore, we compute spiculation features and combine them with features related to echotexture, echogenicity, shape, posterior acoustic behavior and margins. Classification experiments were performed using a support vector machine classifier and evaluation was done with leave-one-patient-out cross-validation. Receiver operator characteristic (ROC) analysis was used to determine performance of the system on a dataset of 201 lesions. We found that spiculation was among the most discriminative features. Using all features, the area under the ROC curve (A(z)) was 0.93, which was significantly higher than the performance without spiculation features (A(z)=0.90, p=0.02). On a subset of 88 cases, classification performance of CAD (A(z)=0.90) was comparable to the average performance of 10 readers (A(z)=0.87). |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/TMI.2012.2184549 | IEEE Trans. Med. Imaging |
Keywords | Field | DocType |
gynaecology,echogenicity,transducer,automated 3d breast ultrasound,biomedical electrodes,biomedical transducers,spiculation patterns,image segmentation,biomedical ultrasonics,spiral scanning technique,support vector machine classifier,lesion classification,lesion segmentation,image classification,observer study,spiculation,leave-one-patient-out cross-validation,receiver operator characteristic analysis,abus imaging,posterior acoustic behavior,coronal spiculation,computer-aided lesion diagnosis,tumours,automated 3-d breast ultrasound,dynamic programming,biological organs,support vector machines,echotexture,medical image processing,sensitivity analysis,computer-aided diagnosis (cad),roc analysis,three dimensional,observational study,cross validation,ultrasound,roc curve,design automation,cluster analysis,cancer,receiver operator characteristic,support vector machine,acoustics | Breast ultrasound,Computer vision,Coronal plane,Receiver operating characteristic,Support vector machine,Image segmentation,Echogenicity,Artificial intelligence,Contextual image classification,Discriminative model,Mathematics | Journal |
Volume | Issue | ISSN |
31 | 5 | 1558-254X |
Citations | PageRank | References |
11 | 0.74 | 3 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tao Tan | 1 | 46 | 10.25 |
Bram Platel | 2 | 245 | 21.42 |
Henkjan J. Huisman | 3 | 130 | 15.50 |
Clara I. Sánchez | 4 | 349 | 21.29 |
Roel Mus | 5 | 18 | 2.45 |
Nico Karssemeijer | 6 | 992 | 122.49 |