Naslov
Using the Polar Transform for Efficient Deep Learning-Based Aorta Segmentation in CTA Images

Autori
Bencevic, Marin ; Habijan, Marija ; Galic, Irena ; Babin, Danilo

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
International Symposium on Electronics in Marine (ELMAR) / - : Institute of Electrical and Electronics Engineers (IEEE), 2022, 191-194

Skup
64th International Symposium ELMAR-2022

Mjesto i datum
Zadar, Hrvatska, 12.09.2022. - 14.09.2022

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Convolutional neural network ; medical image processing ; medical image segmentation ; semantic segmentation

Sažetak
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.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA