Accurately segmenting breast tumors in ultrasound(US)images is a difficult problem due to their specular nature and appearance of sonographic tumors. The current paper presents a variant of the normalized cut (NCut) algorithm based on homogeneous patches (HP-NCut) for the segmentation of ultrasonic breast tumors.Methods:
A novel boundary-detection function is defined by combining texture and intensity information to find the fuzzy boundaries in USimages. Subsequently, based on the precalculated boundary map, an adaptive neighborhood according to image location referred to as a homogeneous patch (HP) is proposed. HPs are guaranteed to spread within the same tissue region; thus, the statistics of primary features within the HPs is more reliable in distinguishing the different tissues and benefits subsequent segmentation. Finally, the fuzzy distribution of textons within HPs is used as final image features, and the segmentation is obtained using the NCut framework.Results:
The HP-NCut algorithm was evaluated on a large dataset of 100 breast USimages (50 benign and 50 malignant). The mean Hausdorff distance measure, the mean minimum Euclidean distance measure and similarity measure achieved 7.1 pixels, 1.58 pixels, and 86.67%, respectively, for benign tumors while those achieved 10.57 pixels, 1.98 pixels, and 84.41%, respectively, for malignant tumors.Conclusions:
The HP-NCut algorithm provided the improvement in accuracy and robustness compared with state-of-the-art methods. A conclusion that the HP-NCut algorithm is suitable for ultrasonictumor segmentation problems can be drawn.
This research was supported by the grants from the National Basic Research Program of China (973 Program) (Grant No. 2010CB732501) and National Natural Science Funds of China (Grant Nos. 30900380, 30730036, and 60873102). The authors would like to thank the anonymous reviewers for their valuable comments.
I.A. Related work
I.B. Our contributions
II.A. Background of normalized cut
II.B. Overview of the proposed HP-NCut algorithm
II.C. Primary feature extraction
II.D. Boundary detection
II.D.1. Detection function
II.E. HP construction
II.E.1. Search window determination
II.E.2. Energy reassignment
II.E.3. HP determination
II.F. HP-Based feature extraction
II.G. Manual interaction
III. RESULTS AND DISCUSSIONS
III.A. Data acquisition
III.B. Validation methods
III.C. Qualitative results
III.D. Quantitative results
III.D.1. Boundary-based error metrics
III.D.2. Overlapping area error metrics
III.D.3. Experiment results
III.E. Influence of parameter choices
III.F. Robustness analysis
- Medical imaging
- Medical image segmentation
Data & Media loading...
Article metrics loading...
Full text loading...