Unsupervised segmentation of MRI knees using Image Partition Forests
Nowadays many people are affected by arthritis, a condition of the joints with limited prevention measures, but with various options of treatment the most radical of which is surgical. In order for surgery to be successful, it relies on careful analysis of patient–based models generated from medical...
| Main Authors: | , |
|---|---|
| Format: | Conference item |
| Published: |
Society of Photo-Optical Instrumentation Engineers (SPIE)
2016
|
| _version_ | 1826256412702932992 |
|---|---|
| author | Marcan, M Voiculescu, I |
| author_facet | Marcan, M Voiculescu, I |
| author_sort | Marcan, M |
| collection | OXFORD |
| description | Nowadays many people are affected by arthritis, a condition of the joints with limited prevention measures, but with various options of treatment the most radical of which is surgical. In order for surgery to be successful, it relies on careful analysis of patient–based models generated from medical images, usually by manual segmentation. In this work we show how to automate the segmentation of a crucial and complex joint – the knee. To achieve this goal we rely on our novel way of representing a 3D voxel volume as a hierarchical structure of partitions which we have named Image Partition Forest (IPF). The IPF contains several partition layers of increasing coarseness, with partitions nested across layers in the form of adjacency graphs. On the basis of a set of properties (size, mean intensity, coordinates) of each node in the IPF we classify nodes into different features. Values indicating whether or not any particular node belongs to the femur or tibia are assigned through node filtering and node– based region growing. So far we have evaluated our method on 15 MRI knee scans. Our unsupervised segmentation compared against a hand–segmented gold standard has achieved an average Dice similarity coefficient of 0.87 for both femur and tibia, and an average symmetric surface distance of 3.77 mm for femur and 1.52 mm for tibia. The paper also discusses ways to introduce stricter morphological and spatial conditioning in the bone labelling process. |
| first_indexed | 2024-03-06T18:01:52Z |
| format | Conference item |
| id | oxford-uuid:000d2073-9081-4a5b-b238-021cc7178e49 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T18:01:52Z |
| publishDate | 2016 |
| publisher | Society of Photo-Optical Instrumentation Engineers (SPIE) |
| record_format | dspace |
| spelling | oxford-uuid:000d2073-9081-4a5b-b238-021cc7178e492022-03-26T08:27:36ZUnsupervised segmentation of MRI knees using Image Partition ForestsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:000d2073-9081-4a5b-b238-021cc7178e49Symplectic Elements at OxfordSociety of Photo-Optical Instrumentation Engineers (SPIE)2016Marcan, MVoiculescu, INowadays many people are affected by arthritis, a condition of the joints with limited prevention measures, but with various options of treatment the most radical of which is surgical. In order for surgery to be successful, it relies on careful analysis of patient–based models generated from medical images, usually by manual segmentation. In this work we show how to automate the segmentation of a crucial and complex joint – the knee. To achieve this goal we rely on our novel way of representing a 3D voxel volume as a hierarchical structure of partitions which we have named Image Partition Forest (IPF). The IPF contains several partition layers of increasing coarseness, with partitions nested across layers in the form of adjacency graphs. On the basis of a set of properties (size, mean intensity, coordinates) of each node in the IPF we classify nodes into different features. Values indicating whether or not any particular node belongs to the femur or tibia are assigned through node filtering and node– based region growing. So far we have evaluated our method on 15 MRI knee scans. Our unsupervised segmentation compared against a hand–segmented gold standard has achieved an average Dice similarity coefficient of 0.87 for both femur and tibia, and an average symmetric surface distance of 3.77 mm for femur and 1.52 mm for tibia. The paper also discusses ways to introduce stricter morphological and spatial conditioning in the bone labelling process. |
| spellingShingle | Marcan, M Voiculescu, I Unsupervised segmentation of MRI knees using Image Partition Forests |
| title | Unsupervised segmentation of MRI knees using Image Partition Forests |
| title_full | Unsupervised segmentation of MRI knees using Image Partition Forests |
| title_fullStr | Unsupervised segmentation of MRI knees using Image Partition Forests |
| title_full_unstemmed | Unsupervised segmentation of MRI knees using Image Partition Forests |
| title_short | Unsupervised segmentation of MRI knees using Image Partition Forests |
| title_sort | unsupervised segmentation of mri knees using image partition forests |
| work_keys_str_mv | AT marcanm unsupervisedsegmentationofmrikneesusingimagepartitionforests AT voiculescui unsupervisedsegmentationofmrikneesusingimagepartitionforests |