The unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi-contrast MR images
Segmenting articular cartilage and meniscus from magnetic resonance (MR) images is an essential task for the assessment of knee pathology. Most of the previous classification-based works for cartilage and meniscus segmentation only rely on independent labellings by a classifier, but do not consider...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/98648 http://hdl.handle.net/10220/17476 |
| _version_ | 1811697140437614592 |
|---|---|
| author | Zhang, Kunlei Lu, Wenmiao Marziliano, Pina |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Zhang, Kunlei Lu, Wenmiao Marziliano, Pina |
| author_sort | Zhang, Kunlei |
| collection | NTU |
| description | Segmenting articular cartilage and meniscus from magnetic resonance (MR) images is an essential task for the assessment of knee pathology. Most of the previous classification-based works for cartilage and meniscus segmentation only rely on independent labellings by a classifier, but do not consider the spatial context interaction. The labels of most image voxels are actually dependent upon their neighbours. In this study, we present an automatic knee segmentation system working on multi-contrast MR images where a novel classification model unifying an extreme learning machine (ELM)-based association potential and a discriminative random field (DRF)-based interaction potential is proposed. The DRF model introduces spatial dependencies between neighbouring voxels to the independent ELM classification. We exploit a rich set of features From multi-contrast MR images to train the proposed classification model and perform the loopy belief propagation for the inference. The proposed model is evaluated on multi-contrast MR datasets acquired from 11 subjects with results outperforming the independent classifiers in terms of segmentation accuracy of both cartilages and menisci. |
| first_indexed | 2024-10-01T07:50:31Z |
| format | Journal Article |
| id | ntu-10356/98648 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:50:31Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/986482020-03-07T13:57:29Z The unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi-contrast MR images Zhang, Kunlei Lu, Wenmiao Marziliano, Pina School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering Segmenting articular cartilage and meniscus from magnetic resonance (MR) images is an essential task for the assessment of knee pathology. Most of the previous classification-based works for cartilage and meniscus segmentation only rely on independent labellings by a classifier, but do not consider the spatial context interaction. The labels of most image voxels are actually dependent upon their neighbours. In this study, we present an automatic knee segmentation system working on multi-contrast MR images where a novel classification model unifying an extreme learning machine (ELM)-based association potential and a discriminative random field (DRF)-based interaction potential is proposed. The DRF model introduces spatial dependencies between neighbouring voxels to the independent ELM classification. We exploit a rich set of features From multi-contrast MR images to train the proposed classification model and perform the loopy belief propagation for the inference. The proposed model is evaluated on multi-contrast MR datasets acquired from 11 subjects with results outperforming the independent classifiers in terms of segmentation accuracy of both cartilages and menisci. 2013-11-08T06:14:05Z 2019-12-06T19:58:05Z 2013-11-08T06:14:05Z 2019-12-06T19:58:05Z 2013 2013 Journal Article Zhang, K., Lu, W., & Marziliano, P. (2013). The unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi-contrast MR images. Machine vision and applications, 24(7), 1459-1472. https://hdl.handle.net/10356/98648 http://hdl.handle.net/10220/17476 10.1007/s00138-012-0466-9 en Machine vision and applications |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering Zhang, Kunlei Lu, Wenmiao Marziliano, Pina The unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi-contrast MR images |
| title | The unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi-contrast MR images |
| title_full | The unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi-contrast MR images |
| title_fullStr | The unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi-contrast MR images |
| title_full_unstemmed | The unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi-contrast MR images |
| title_short | The unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi-contrast MR images |
| title_sort | unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi contrast mr images |
| topic | DRNTU::Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/98648 http://hdl.handle.net/10220/17476 |
| work_keys_str_mv | AT zhangkunlei theunifiedextremelearningmachinesanddiscriminativerandomfieldsforautomatickneecartilageandmeniscussegmentationfrommulticontrastmrimages AT luwenmiao theunifiedextremelearningmachinesanddiscriminativerandomfieldsforautomatickneecartilageandmeniscussegmentationfrommulticontrastmrimages AT marzilianopina theunifiedextremelearningmachinesanddiscriminativerandomfieldsforautomatickneecartilageandmeniscussegmentationfrommulticontrastmrimages AT zhangkunlei unifiedextremelearningmachinesanddiscriminativerandomfieldsforautomatickneecartilageandmeniscussegmentationfrommulticontrastmrimages AT luwenmiao unifiedextremelearningmachinesanddiscriminativerandomfieldsforautomatickneecartilageandmeniscussegmentationfrommulticontrastmrimages AT marzilianopina unifiedextremelearningmachinesanddiscriminativerandomfieldsforautomatickneecartilageandmeniscussegmentationfrommulticontrastmrimages |