EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

False-Positive Scar Control in Scribble-Supervised LGE-CMR Segmentation Using an Asymmetric Intensity Prior

Xin Lan, Xinchen Xie, Jinwei Dong, Chenming Zhao, Qitong Zhang, Wangbin Ding, Shimei Fu

Journal of Cardiovascular Development and Disease · 17.11.2026 · 13 (11) · 605

DOI: 10.3390/jcdd13110605 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Cardiovascular Development and Disease, online erschienen am 17.11.2026. Verfasst von Xin Lan und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fujian Medical University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Scribble-supervised LGE-CMR segmentation can overestimate myocardial scar.

Methods

We introduced an asymmetric intensity prior that penalizes predicted scar darker than a scribble-derived reference. We evaluated 36 patient-disjoint test cases using reference myocardium-guided crops and performed separate reference-free central-crop and automatic-myocardial-wall analyses. The main prior-specific comparison matched the 2.5D backbone with and without the prior across three seeds.

Results

On the pre-cropped images, mean Dice increased from 0.5328±0.0108 to 0.5472±0.0060, while recall fell from 0.6924 to 0.6399. The predicted-to-reference scar ratio fell from 1.6796±0.1834 to 1.4039±0.1389, and absolute scar-volume error fell from 21.09±5.27 to 14.08±2.47 mL on the common crop grid. However, restriction to the reference myocardial wall increased absolute percent-LV-scar error from 5.55±1.14 to 6.58±0.99 percentage points. With additional healthy-myocardium background points (seed 2022), the matched prior model reduced Pred/GT from 1.5789 to 1.1500 but Dice fell from 0.5441 to 0.5366. With one fixed-rule reference-free central crop and retraining (seed 2022), Dice was 0.4892 without and 0.5047 with the prior. In a paired automatic-wall analysis, the prior did not improve three-seed wall-restricted burden error (6.14 versus 8.16 percentage points).

Conclusions

The prior reduced full-output overestimation on the pre-cropped images, but did not improve intramyocardial burden agreement or retain a Dice advantage in the single-seed healthy-background sensitivity analysis. Its effects depend on localization and wall quality and require independent prospective reference-free evaluation.

Förderung

  • Fujian Medical University

Zitieren

APA

Lan, X., Xie, X., Dong, J., Zhao, C., Zhang, Q., Ding, W., & Fu, S. (2026). False-Positive Scar Control in Scribble-Supervised LGE-CMR Segmentation Using an Asymmetric Intensity Prior. Journal of Cardiovascular Development and Disease, 13(11), 605. https://doi.org/10.3390/jcdd13110605

Vancouver

Lan X, Xie X, Dong J, Zhao C, Zhang Q, Ding W, et al. False-Positive Scar Control in Scribble-Supervised LGE-CMR Segmentation Using an Asymmetric Intensity Prior. Journal of Cardiovascular Development and Disease. 2026;13(11):605. doi:10.3390/jcdd13110605

BibTeX
@article{Lan2026,
  author = {Lan, Xin and Xie, Xinchen and Dong, Jinwei and Zhao, Chenming and Zhang, Qitong and Ding, Wangbin and Fu, Shimei},
  title = {False-Positive Scar Control in Scribble-Supervised LGE-CMR Segmentation Using an Asymmetric Intensity Prior},
  journal = {Journal of Cardiovascular Development and Disease},
  year = {2026},
  volume = {13},
  number = {11},
  pages = {605},
  doi = {10.3390/jcdd13110605}
}
Kostenlos starten →