Title |
Fast segmentation of anterior segment optical coherence tomography images using graph cut
|
---|---|
Published in |
Eye and Vision, January 2015
|
DOI | 10.1186/s40662-015-0011-9 |
Pubmed ID | |
Authors |
Dominic Williams, Yalin Zheng, Fangjun Bao, Ahmed Elsheikh |
Abstract |
Optical coherence tomography (OCT) is a non-invasive imaging system that can be used to obtain images of the anterior segment. Automatic segmentation of these images will enable them to be used to construct patient specific biomechanical models of the human eye. These models could be used to help with treatment planning and diagnosis of patients. A novel graph cut technique using regional and shape terms was developed. It was evaluated by segmenting 39 OCT images of the anterior segment. The results of this were compared with manual segmentation and a previously reported level set segmentation technique. Three different comparison techniques were used: Dice's similarity coefficient (DSC), mean unsigned surface positioning error (MSPE), and 95% Hausdorff distance (HD). A paired t-test was used to compare the results of different segmentation techniques. When comparison with manual segmentation was performed, a mean DSC value of 0.943 ± 0.020 was achieved, outperforming other previously published techniques. A substantial reduction in processing time was also achieved using this method. We have developed a new segmentation technique that is both fast and accurate. This has the potential to be used to aid diagnostics and treatment planning. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 26 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 8 | 31% |
Researcher | 5 | 19% |
Student > Master | 3 | 12% |
Student > Bachelor | 2 | 8% |
Other | 1 | 4% |
Other | 0 | 0% |
Unknown | 7 | 27% |
Readers by discipline | Count | As % |
---|---|---|
Engineering | 6 | 23% |
Physics and Astronomy | 5 | 19% |
Agricultural and Biological Sciences | 2 | 8% |
Business, Management and Accounting | 2 | 8% |
Medicine and Dentistry | 2 | 8% |
Other | 3 | 12% |
Unknown | 6 | 23% |