SSPC: A new topological metric for deep learning based anatomical reconstruction evaluation

5 pages•Published: December 17, 2024

Lhoussein Axel Mabrouk, Fabrice Bertrand, François Boux de Casson and Clément Daviller

Abstract

Computer-assisted surgery relies on precise labeling of patient anatomy using 3D images. Major part of this process is nowadays performed by deep-learning (DL) algorithms. However, the evaluation of automated segmentations using conventional metrics like Dice coefficient or Hausdorff distance has limitations, especially when assessing non-significant errors at the mesh level. To overcome this, we propose a novel metric (SSPC) focusing on significant surface disparities to enhance evaluation accuracy.

Keyphrases: 3d modeling, deep learning, image processing, total shoulder arthroplasty

In: Joshua W Giles and Aziliz Guezou-Philippe (editors). Proceedings of The 24th Annual Meeting of the International Society for Computer Assisted Orthopaedic Surgery, vol 7, pages 155-159.

Links:	https://easychair.org/publications/paper/QtCb
	https://doi.org/10.29007/dl41

BibTeX entry

@inproceedings{CAOS2024:SSPC_new_topological_metric,
  author    = {Lhoussein Axel Mabrouk and Fabrice Bertrand and François Boux de Casson and Clément Daviller},
  title     = {SSPC: A new topological metric for deep learning based anatomical reconstruction evaluation},
  booktitle = {Proceedings of The 24th Annual Meeting of the International Society for Computer Assisted Orthopaedic Surgery},
  editor    = {Joshua W Giles and Aziliz Guezou-Philippe},
  series    = {EPiC Series in Health Sciences},
  volume    = {7},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-5305},
  url       = {/publications/paper/QtCb},
  doi       = {10.29007/dl41},
  pages     = {155-159},
  year      = {2024}}

Download PDF Open PDF in browser