Using the polar transform for efficient deep learning-based aorta segmentation in CTA images
| Autor: | Marin Bencevic, Marija Habijan, Irena Galic, Danilo Babin |
|---|---|
| Přispěvatelé: | Mustra, M, Zovko-Cihlar, B, Vukovic, J |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
medical image segmentation Technology and Engineering Computer and information sciences [FOS] Computer Vision and Pattern Recognition (cs.CV) Image and Video Processing (eess.IV) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Computer Science - Computer Vision and Pattern Recognition Electrical engineering [FOS] Convolutional neural network Electrical Engineering and Systems Science - Image and Video Processing electronic engineering medical image processing semantic segmentation information engineering Computer Science::Computer Vision and Pattern Recognition FOS: Electrical engineering electronic engineering information engineering |
| Zdroj: | 2022 International Symposium ELMAR, proceedings |
| ISSN: | 1334-2630 |
| Popis: | Medical image segmentation often requires segmenting multiple elliptical objects on a single image. This includes, among other tasks, segmenting vessels such as the aorta in axial CTA slices. In this paper, we present a general approach to improving the semantic segmentation performance of neural networks in these tasks and validate our approach on the task of aorta segmentation. We use a cascade of two neural networks, where one performs a rough segmentation based on the U-Net architecture and the other performs the final segmentation on polar image transformations of the input. Connected component analysis of the rough segmentation is used to construct the polar transformations, and predictions on multiple transformations of the same image are fused using hysteresis thresholding. We show that this method improves aorta segmentation performance without requiring complex neural network architectures. In addition, we show that our approach improves robustness and pixel-level recall while achieving segmentation performance in line with the state of the art. Accepted to 64th International Symposium ELMAR-2022, Zadar, Croatia |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|