%L discovery10191148
%I Springer Nature Switzerland
%S SEGA
%O This version is the author-accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
%X Common pixel-based loss functions for image segmentation struggle with the fine-scale structures often found in the aortic vessel tree. In this paper, we propose a Misclassification Loss (MC loss) function, which can effectively suppress false positives and rescue the false negatives. A differentiable eXclusive OR (XOR) operation is implemented to identify these false predictions, which are then minimized through a cross-entropy loss. The proposed MC loss helps the network achieve better performance by focusing on these difficult regions. On the Segmentation of the Aorta SEG.A. 2023 challenge, our method achieves a Dice score of 0.93 and a Hausdorff Distance (HD) of 3.50 mm on a 5-fold split of 56 training subjects. We participated in the SEG.A. 2023 challenge, and the proposed method ranks among the top-six approaches in the validation phase-1. The pre-trained models, source code, and implementation will be made public.
%C Cham, Switzerland
%B Segmentation of the Aorta. Towards the Automatic Segmentation, Modeling, and Meshing of the Aortic Vessel Tree from Multicenter Acquisition: First Challenge
%A Abbas Khan
%A Muhammad Asad
%A Alexander Zolotarev
%A Caroline Roney
%A Anthony Mathur
%A Martin Benning
%A Gregory Slabaugh
%V 14539
%E Antonio Pepe
%E Gian Marco Melito
%E Jan Egger
%T Misclassification Loss for Segmentation of the Aortic Vessel Tree
%D 2024
%P 67-79