Abdomen segmentation in 3D fetal ultrasound using CNN-powered deformable models

Conference item

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.

Authors: Schmidt-Richberg, A; Brosch, T; Schadewaldt, N; Klinder, T; Cavallaro, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer
• Host title: International Workshop on Fetal and Infant Image Analysis/International Workshop on Ophthalmic Medical Image Analysis (FIFI 2017/OMIA 2017)
• Journal: International Workshop on Fetal and Infant Image Analysis/International Workshop on Ophthalmic Medical Image Analysis (FIFI 2017/OMIA 2017)
• Publication date: 2017-09-09
• Acceptance date: 2017-05-16
• DOI: 10.1007/978-3-319-67561-9_6
• EISSN: 1611-3349
• ISSN: 0302-9743
• ISBN: 9783319675602