Automatic Detection of the Nasal Cavities and Paranasal Sinuses Using Deep Neural Networks
- Resource Type
- Conference
- Authors
- Laura, Cristina Oyarzun; Hofmann, Patrick; Drechsler, Klaus; Wesarg, Stefan
- Source
- 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) Biomedical Imaging (ISBI 2019), 2019 IEEE 16th International Symposium on. :1154-1157 Apr, 2019
- Subject
- Bioengineering
Cavity resonators
Bones
Periodic structures
Computed tomography
Three-dimensional displays
Training
Deep learning
Nasal cavity
Paranasal sinus
Organ detection
YOLO
- Language
- ISSN
- 1945-8452
The nasal cavity and paranasal sinuses present large interpa-tient variabilities. Additional circumstances like for example, concha bullosa or nasal septum deviations complicate their segmentation. As in other areas of the body a previous multi-structure detection could facilitate the segmentation task. In this paper an approach is proposed to individually detect all sinuses and the nasal cavity. For a better delimitation of their borders the use of an irregular polyhedron is proposed. For an accurate prediction the Darknet-19 deep neural network is used which combined with the You Only Look Once method has shown very promising results in other fields of computer vision. 57 CT scans were available of which 85% were used for training and the remaining 15% for validation.