Vesal S, Ravikumar N, Ellmann S, Maier A (2018)
Publication Type: Conference contribution
Publication year: 2018
Publisher: Springer Berlin Heidelberg
Pages Range: 257-262
Conference Proceedings Title: Informatik aktuell
Event location: Erlangen, DEU
DOI: 10.1007/978-3-662-56537-7_68
Accurate segmentation of breast lesions is a crucial step in evaluating the characteristics of tumors. However, this is a challenging task, since breast lesions have sophisticated shape, topological structure, and variation in the intensity distribution. In this paper, we evaluated the performance of three unsupervised algorithms for the task of breast Magnetic Resonance (MRI) lesion segmentation, namely, Gaussian Mixture Model clustering, K-means clustering and a markercontrolled Watershed transformation based method. All methods were applied on breast MRI slices following selection of regions of interest (ROIs) by an expert radiologist and evaluated on 106 subject’s images, which include 59 malignant and 47 benign lesions. Segmentation accuracy was evaluated by comparing our results with ground truth masks, using the Dice similarity coefficient (DSC), Jaccard index (JI), Hausdorff distance and precision-recall metrics. The results indicate that the marker-controlled Watershed transformation outperformed all other algorithms investigated.
APA:
Vesal, S., Ravikumar, N., Ellmann, S., & Maier, A. (2018). Comparative analysis of unsupervised algorithms for breast MRI lesion segmentation. In Heinz Handels, Thomas Tolxdorff, Thomas M. Deserno, Klaus H. Maier-Hein, Andreas Maier, Christoph Palm (Eds.), Informatik aktuell (pp. 257-262). Erlangen, DEU: Springer Berlin Heidelberg.
MLA:
Vesal, Sulaiman, et al. "Comparative analysis of unsupervised algorithms for breast MRI lesion segmentation." Proceedings of the Workshop on Bildverarbeitung fur die Medizin, 2018, Erlangen, DEU Ed. Heinz Handels, Thomas Tolxdorff, Thomas M. Deserno, Klaus H. Maier-Hein, Andreas Maier, Christoph Palm, Springer Berlin Heidelberg, 2018. 257-262.
BibTeX: Download