Abdomen segmentation in 3D fetal ultrasound using CNN-powered deformable models
In this paper, voxel probability maps generated by a novel fovea fully convolutional network architecture (FovFCN) are used as additional feature images in the context of a segmentation approach based on deformable shape models. The method is applied to fetal 3D ultrasound image data aiming at a seg...
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Conference item |
| Publicado: |
Springer
2017
|
| _version_ | 1826258213943640064 |
|---|---|
| author | Schmidt-Richberg, A Brosch, T Schadewaldt, N Klinder, T Cavallaro, A Salim, I Roundhill, D Papageorghiou, A Lorenz, C |
| author_facet | Schmidt-Richberg, A Brosch, T Schadewaldt, N Klinder, T Cavallaro, A Salim, I Roundhill, D Papageorghiou, A Lorenz, C |
| author_sort | Schmidt-Richberg, A |
| collection | OXFORD |
| description | In this paper, voxel probability maps generated by a novel fovea fully convolutional network architecture (FovFCN) are used as additional feature images in the context of a segmentation approach based on deformable shape models. The method is applied to fetal 3D ultrasound image data aiming at a segmentation of the abdominal outline of the fetal torso. This is of interest, e.g., for measuring the fetal abdominal circumference, a standard biometric measure in prenatal screening. The method is trained on 126 3D ultrasound images and tested on 30 additional scans. The results show that the approach can successfully combine the advantages of FovFCNs and deformable shape models in the context of challenging image data, such as given by fetal ultrasound. With a mean error of 2.24 mm, the combination of model-based segmentation and neural networks outperforms the separate approaches. |
| first_indexed | 2024-03-06T18:30:27Z |
| format | Conference item |
| id | oxford-uuid:0973b23c-6f7d-4322-a6f8-e1201391bb12 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T18:30:27Z |
| publishDate | 2017 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:0973b23c-6f7d-4322-a6f8-e1201391bb122022-03-26T09:18:33ZAbdomen segmentation in 3D fetal ultrasound using CNN-powered deformable modelsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:0973b23c-6f7d-4322-a6f8-e1201391bb12Symplectic Elements at OxfordSpringer2017Schmidt-Richberg, ABrosch, TSchadewaldt, NKlinder, TCavallaro, ASalim, IRoundhill, DPapageorghiou, ALorenz, CIn this paper, voxel probability maps generated by a novel fovea fully convolutional network architecture (FovFCN) are used as additional feature images in the context of a segmentation approach based on deformable shape models. The method is applied to fetal 3D ultrasound image data aiming at a segmentation of the abdominal outline of the fetal torso. This is of interest, e.g., for measuring the fetal abdominal circumference, a standard biometric measure in prenatal screening. The method is trained on 126 3D ultrasound images and tested on 30 additional scans. The results show that the approach can successfully combine the advantages of FovFCNs and deformable shape models in the context of challenging image data, such as given by fetal ultrasound. With a mean error of 2.24 mm, the combination of model-based segmentation and neural networks outperforms the separate approaches. |
| spellingShingle | Schmidt-Richberg, A Brosch, T Schadewaldt, N Klinder, T Cavallaro, A Salim, I Roundhill, D Papageorghiou, A Lorenz, C Abdomen segmentation in 3D fetal ultrasound using CNN-powered deformable models |
| title | Abdomen segmentation in 3D fetal ultrasound using CNN-powered deformable models |
| title_full | Abdomen segmentation in 3D fetal ultrasound using CNN-powered deformable models |
| title_fullStr | Abdomen segmentation in 3D fetal ultrasound using CNN-powered deformable models |
| title_full_unstemmed | Abdomen segmentation in 3D fetal ultrasound using CNN-powered deformable models |
| title_short | Abdomen segmentation in 3D fetal ultrasound using CNN-powered deformable models |
| title_sort | abdomen segmentation in 3d fetal ultrasound using cnn powered deformable models |
| work_keys_str_mv | AT schmidtrichberga abdomensegmentationin3dfetalultrasoundusingcnnpowereddeformablemodels AT broscht abdomensegmentationin3dfetalultrasoundusingcnnpowereddeformablemodels AT schadewaldtn abdomensegmentationin3dfetalultrasoundusingcnnpowereddeformablemodels AT klindert abdomensegmentationin3dfetalultrasoundusingcnnpowereddeformablemodels AT cavallaroa abdomensegmentationin3dfetalultrasoundusingcnnpowereddeformablemodels AT salimi abdomensegmentationin3dfetalultrasoundusingcnnpowereddeformablemodels AT roundhilld abdomensegmentationin3dfetalultrasoundusingcnnpowereddeformablemodels AT papageorghioua abdomensegmentationin3dfetalultrasoundusingcnnpowereddeformablemodels AT lorenzc abdomensegmentationin3dfetalultrasoundusingcnnpowereddeformablemodels |