Automatic Segmentation of the Paranasal Sinus from Computer Tomography Images Using a Probabilistic Atlas and a Fully Convolutional Network
- Resource Type
- Conference
- Authors
- Iwamoto, Yutaro; Xiong, Kun; Kitamura, Takahiro; Han, Xian-Hua; Matsushiro, Naoki; Nishimura, Hiroshi; Chen, Yen-Wei
- Source
- 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) Engineering in Medicine and Biology Society (EMBC), 2019 41st Annual International Conference of the IEEE. :2789-2792 Jul, 2019
- Subject
- Bioengineering
Image segmentation
Computed tomography
Probabilistic logic
Three-dimensional displays
Active contours
Bones
Image color analysis
- Language
- ISSN
- 1558-4615
In this paper, we present an automatic approach to paranasal sinus segmentation in computed tomography (CT) images. The proposed method combines a probabilistic atlas and a fully convolutional network (FCN). The probabilistic atlas was used to automatically localize the paranasal sinus and determine its bounding box. The FCN was then used to automatically segment the paranasal sinus in the bounding box. Comparing our proposed method with the conventional FCN (without probabilistic atlas) and the state-of-the-art method using active contour with group similarity, the proposed method demonstrated an improvement in the paranasal sinus segmentation. The segmentation accuracy (Dice coefficient) was about 0.83 even for the case with unclear boundary.