Automatic Graph Cut Segmentation of Lesions in CT Using Mean Shift Superpixels
This paper presents a new, automatic method of accurately extracting lesions from CT data. It first determines, at each voxel, a five-dimensional (5D) feature vector that contains intensity, shape index, and 3D spatial location. Then, nonparametric mean shift clustering forms superpixels from these...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2010-01-01
|
| Series: | International Journal of Biomedical Imaging |
| Online Access: | http://dx.doi.org/10.1155/2010/983963 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832567654278234112 |
|---|---|
| author | Xujiong Ye Gareth Beddoe Greg Slabaugh |
| author_facet | Xujiong Ye Gareth Beddoe Greg Slabaugh |
| author_sort | Xujiong Ye |
| collection | DOAJ |
| description | This paper presents a new, automatic method of accurately extracting lesions from CT data. It first determines, at each voxel, a five-dimensional (5D) feature vector that contains intensity, shape index, and 3D spatial location. Then, nonparametric mean shift clustering forms superpixels from these 5D features, resulting in an oversegmentation of the image. Finally, a graph cut algorithm groups the superpixels using a novel energy formulation that incorporates shape, intensity, and spatial features. The mean shift superpixels increase the robustness of the result while reducing the computation time. We assume that the lesion is part spherical, resulting in high shape index values in a part of the lesion. From these spherical subregions, foreground and background seeds for the graph cut segmentation can be automatically obtained. The proposed method has been evaluated on a clinical CT dataset. Visual inspection on different types of lesions (lung nodules and colonic polyps), as well as a quantitative evaluation on 101 solid and 80 GGO nodules, both demonstrate the potential of the proposed method. The joint spatial-intensity-shape features provide a powerful cue for successful segmentation of lesions adjacent to structures of similar intensity but different shape, as well as lesions exhibiting partial volume effect. |
| format | Article |
| id | doaj-art-696ce7d0917a4539a17bc2fb84c7f710 |
| institution | Kabale University |
| issn | 1687-4188 1687-4196 |
| language | English |
| publishDate | 2010-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Biomedical Imaging |
| spelling | doaj-art-696ce7d0917a4539a17bc2fb84c7f7102025-02-03T01:00:55ZengWileyInternational Journal of Biomedical Imaging1687-41881687-41962010-01-01201010.1155/2010/983963983963Automatic Graph Cut Segmentation of Lesions in CT Using Mean Shift SuperpixelsXujiong Ye0Gareth Beddoe1Greg Slabaugh2R&D Department, Medicsight PLC, 66 Hammersmith Road, London W14 8UD, UKR&D Department, Medicsight PLC, 66 Hammersmith Road, London W14 8UD, UKR&D Department, Medicsight PLC, 66 Hammersmith Road, London W14 8UD, UKThis paper presents a new, automatic method of accurately extracting lesions from CT data. It first determines, at each voxel, a five-dimensional (5D) feature vector that contains intensity, shape index, and 3D spatial location. Then, nonparametric mean shift clustering forms superpixels from these 5D features, resulting in an oversegmentation of the image. Finally, a graph cut algorithm groups the superpixels using a novel energy formulation that incorporates shape, intensity, and spatial features. The mean shift superpixels increase the robustness of the result while reducing the computation time. We assume that the lesion is part spherical, resulting in high shape index values in a part of the lesion. From these spherical subregions, foreground and background seeds for the graph cut segmentation can be automatically obtained. The proposed method has been evaluated on a clinical CT dataset. Visual inspection on different types of lesions (lung nodules and colonic polyps), as well as a quantitative evaluation on 101 solid and 80 GGO nodules, both demonstrate the potential of the proposed method. The joint spatial-intensity-shape features provide a powerful cue for successful segmentation of lesions adjacent to structures of similar intensity but different shape, as well as lesions exhibiting partial volume effect.http://dx.doi.org/10.1155/2010/983963 |
| spellingShingle | Xujiong Ye Gareth Beddoe Greg Slabaugh Automatic Graph Cut Segmentation of Lesions in CT Using Mean Shift Superpixels International Journal of Biomedical Imaging |
| title | Automatic Graph Cut Segmentation of Lesions in CT Using Mean Shift Superpixels |
| title_full | Automatic Graph Cut Segmentation of Lesions in CT Using Mean Shift Superpixels |
| title_fullStr | Automatic Graph Cut Segmentation of Lesions in CT Using Mean Shift Superpixels |
| title_full_unstemmed | Automatic Graph Cut Segmentation of Lesions in CT Using Mean Shift Superpixels |
| title_short | Automatic Graph Cut Segmentation of Lesions in CT Using Mean Shift Superpixels |
| title_sort | automatic graph cut segmentation of lesions in ct using mean shift superpixels |
| url | http://dx.doi.org/10.1155/2010/983963 |
| work_keys_str_mv | AT xujiongye automaticgraphcutsegmentationoflesionsinctusingmeanshiftsuperpixels AT garethbeddoe automaticgraphcutsegmentationoflesionsinctusingmeanshiftsuperpixels AT gregslabaugh automaticgraphcutsegmentationoflesionsinctusingmeanshiftsuperpixels |