eprintid: 10191148
rev_number: 10
eprint_status: archive
userid: 699
dir: disk0/10/19/11/48
datestamp: 2024-04-22 10:56:35
lastmod: 2025-02-11 07:10:05
status_changed: 2024-04-22 10:56:35
type: book_section
metadata_visibility: show
sword_depositor: 699
creators_name: Khan, Abbas
creators_name: Asad, Muhammad
creators_name: Zolotarev, Alexander
creators_name: Roney, Caroline
creators_name: Mathur, Anthony
creators_name: Benning, Martin
creators_name: Slabaugh, Gregory
title: Misclassification Loss for Segmentation of the Aortic Vessel Tree
ispublished: pub
divisions: UCL
divisions: B04
divisions: C05
divisions: F48
note: This version is the author-accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
abstract: 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.
date: 2024-01-01
date_type: published
publisher: Springer Nature Switzerland
official_url: https://doi.org/10.1007/978-3-031-53241-2_6
oa_status: green
full_text_type: other
language: eng
primo: open
primo_central: open_green
verified: verified_manual
elements_id: 2253344
doi: 10.1007/978-3-031-53241-2_6
isbn_13: 9783031532405
lyricists_name: Benning, Martin
lyricists_id: MBENN44
actors_name: Benning, Martin
actors_name: Kaltenbacher, Brigitte G
actors_id: MBENN44
actors_id: BGKAL87
actors_role: owner
actors_role: impersonator
full_text_status: public
series: SEGA
volume: 14539
place_of_pub: Cham, Switzerland
pagerange: 67-79
book_title: Segmentation of the Aorta. Towards the Automatic Segmentation, Modeling, and Meshing of the Aortic Vessel Tree from Multicenter Acquisition: First Challenge
editors_name: Pepe, Antonio
editors_name: Melito, Gian Marco
editors_name: Egger, Jan
citation:        Khan, Abbas;    Asad, Muhammad;    Zolotarev, Alexander;    Roney, Caroline;    Mathur, Anthony;    Benning, Martin;    Slabaugh, Gregory;      (2024)    Misclassification Loss for Segmentation of the Aortic Vessel Tree.                    In: Pepe, Antonio and Melito, Gian Marco and Egger, Jan, (eds.) Segmentation of the Aorta. Towards the Automatic Segmentation, Modeling, and Meshing of the Aortic Vessel Tree from Multicenter Acquisition: First Challenge. (pp. 67-79).   Springer Nature Switzerland: Cham, Switzerland.       Green open access   
 
document_url: https://discovery.ucl.ac.uk/id/eprint/10191148/1/Benning_Misclassification_Loss.pdf