EUVIMEDEUVIMED entdecken
Crossref

S 3 R: Shape and Semantics-Based Selective Regularization for Explainable Continual Segmentation Across Multiple Sites

Jingyang Zhang, Ran Gu, Peng Xue, Mianxin Liu, Hao Zheng, Yefeng Zheng, Lei Ma, Guotai Wang, Lixu Gu

IEEE Transactions on Medical Imaging · 2023

DOI: 10.1109/tmi.2023.3260974 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2023. Verfasst von Jingyang Zhang und 8 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Optic Disk. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Key Research and Development Program, 863 National Research Fund, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In clinical practice, it is desirable for medical image segmentation models to be able to continually learn on a sequential data stream from multiple sites, rather than a consolidated dataset, due to storage cost and privacy restrictions. However, when learning on a new site, existing methods struggle with a weak memorizability for previous sites with complex shape and semantic information, and a poor explainability for the memory consolidation process. In this work, we propose a novel Shape and Semantics-based Selective Regularization ( [Formula: see text]) method for explainable cross-site continual segmentation to maintain both shape and semantic knowledge of previously learned sites. Specifically, [Formula: see text] method adopts a selective regularization scheme to penalize changes of parameters with high Joint Shape and Semantics-based Importance (JSSI) weights, which are estimated based on the parameter sensitivity to shape properties and reliable semantics of the segmentation object. This helps to prevent the related shape and semantic knowledge from being forgotten. Moreover, we propose an Importance Activation Mapping (IAM) method for memory interpretation, which indicates the spatial support for important parameters to visualize the memorized content. We have extensively evaluated our method on prostate segmentation and optic cup and disc segmentation tasks. Our method outperforms other comparison methods in reducing model forgetting and increasing explainability. Our code is available at https://github.com/jingyzhang/S3R.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedOptic DiskMaleHumansSemanticsMachine LearningProstate

Förderung

  • National Key Research and Development Program
  • 863 National Research Fund
  • National Natural Science Foundation of China

Zitieren

APA

Zhang, J., Gu, R., Xue, P., Liu, M., Zheng, H., Zheng, Y., Ma, L., Wang, G., & Gu, L. (2023). S 3 R: Shape and Semantics-Based Selective Regularization for Explainable Continual Segmentation Across Multiple Sites. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2023.3260974

Vancouver

Zhang J, Gu R, Xue P, Liu M, Zheng H, Zheng Y, et al. S 3 R: Shape and Semantics-Based Selective Regularization for Explainable Continual Segmentation Across Multiple Sites. IEEE Transactions on Medical Imaging. 2023. doi:10.1109/tmi.2023.3260974

BibTeX
@article{Zhang2023,
  author = {Zhang, Jingyang and Gu, Ran and Xue, Peng and Liu, Mianxin and Zheng, Hao and Zheng, Yefeng and Ma, Lei and Wang, Guotai and Gu, Lixu},
  title = {S 3 R: Shape and Semantics-Based Selective Regularization for Explainable Continual Segmentation Across Multiple Sites},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2023},
  doi = {10.1109/tmi.2023.3260974}
}
Kostenlos starten →