Chapter title |
Learning Distance Transform for Boundary Detection and Deformable Segmentation in CT Prostate Images
|
---|---|
Chapter number | 12 |
Book title |
Machine Learning in Medical Imaging
|
Published in |
Machine learning in medical imaging. MLMI (Workshop), September 2014
|
DOI | 10.1007/978-3-319-10581-9_12 |
Pubmed ID | |
Book ISBNs |
978-3-31-910580-2, 978-3-31-910581-9
|
Authors |
Yaozong Gao, Li Wang, Yeqin Shao, Dinggang Shen |
Editors |
Guorong Wu, Daoqiang Zhang, Luping Zhou |
Abstract |
Segmenting the prostate from CT images is a critical step in the radio-therapy planning for prostate cancer. The segmentation accuracy could largely affect the efficacy of radiation treatment. However, due to the touching boundaries with the bladder and the rectum, the prostate boundary is often ambiguous and hard to recognize, which leads to inconsistent manual delineations across different clinicians. In this paper, we propose a learning-based approach for boundary detection and deformable segmentation of the prostate. Our proposed method aims to learn a boundary distance transform, which maps an intensity image into a boundary distance map. To enforce the spatial consistency on the learned distance transform, we combine our approach with the auto-context model for iteratively refining the estimated distance map. After the refinement, the prostate boundaries can be readily detected by finding the valley in the distance map. In addition, the estimated distance map can also be used as a new external force for guiding the deformable segmentation. Specifically, to automatically segment the prostate, we integrate the estimated boundary distance map into a level set formulation. Experimental results on 73 CT planning images show that the proposed distance transform is more effective than the traditional classification-based method for driving the deformable segmentation. Also, our method can achieve more consistent segmentations than human raters, and more accurate results than the existing methods under comparison. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 15 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Other | 3 | 20% |
Student > Master | 3 | 20% |
Student > Ph. D. Student | 2 | 13% |
Researcher | 2 | 13% |
Student > Doctoral Student | 1 | 7% |
Other | 0 | 0% |
Unknown | 4 | 27% |
Readers by discipline | Count | As % |
---|---|---|
Engineering | 6 | 40% |
Computer Science | 2 | 13% |
Medicine and Dentistry | 2 | 13% |
Biochemistry, Genetics and Molecular Biology | 1 | 7% |
Unknown | 4 | 27% |