Tissue segmentation plays a crucial role in many medical imaging applications by automatically locating the regions of interest. Typically supervised learning based segmentation methods require a large set of accurately labeled training data. However, thel labeling process is tedious, time consuming and sometimes not necessary. We propose a robust logistic regression algorithm to handle label outliers such that doctors do not need to waste time on precisely labeling images for training set. To validate its effectiveness and efficiency, we conduct carefully designed experiments on cervigram image segmentation while there exist label outliers. Experimental results show that the proposed robust logistic regression algorithms achieve superior performance compared to previous methods, which validates the bene ts of the proposed algorithms.
.Papers
-
Mingchen Gao, Junzhou Huang, Xiaolei Huang, Shaoting Zhang, Dimitris Metaxas, "Simplified Labeling Process for Medical Image Segmentation", In Proc. of the 15th Annual International Conf. on Medical Image Computing and Computer Assisted Intervention, MICCAI'12, Nice, France, October 2012.
- Yang Yu, Junzhou Huang, Shaoting Zhang, Christophe Restif, Xiaolei Huang, Dimitris Metaxas, "Group Sparsity Based Classification for Cervigram Segmentation", In Proc. of IEEE Int'l Symposium on Biomedical Imaging: From Nano to Macro, ISBI’11, Chicago, Illinois, USA, March 2011.
- Shaoting Zhang, Junzhou Huang, Wei Wang, Xiaolei Huang, Dimitris Metaxas, ”Cervigram Image Segmentation Based On Reconstructive Sparse Representations”, Proc. of SPIE, Medical Imaging: Image Processing, San Diego, California, USA, February 2010. [SLIDES]
Sparse Representation
 |
Figure.
Sparse representation and Dictionary learning. |
Tissue Segmentation in Cervigrams
 |
Figure.
Cervigram image and segmentation |