PuSH - Publication Server of Helmholtz Zentrum München

Daza, L. ; Schnabel, J.A.

DiENTeS: Dynamic ENTity segmentation with local-global transformers.

In: (Supervised and Semi-supervised Multi-structure Segmentation and Landmark Detection in Dental Data). Berlin [u.a.]: Springer, 2025. 21-29 (Lect. Notes Comput. Sc. ; 15571 LNCS)
DOI
Semantic segmentation is crucial for accurately identifying anatomical structures and pathological anomalies in medical images, playing a vital role in diagnostics, treatment planning, and disease progression monitoring. Despite significant advancements, the development of flexible and generalizable algorithms that can adapt to the diverse shapes, sizes, and textures of various anatomical regions remains challenging. In this work, we introduce the Dynamic ENTity Segmentation (DiENTeS) model, which leverages Local-global Transformers for 3D medical segmentation. Our model utilizes a transformer-based backbone to extract localized features and propagate them to form a comprehensive global representation. Additionally, we incorporate language features to guide the segmentation process, enabling the generation of specialized convolutional kernels for each category. This approach allows DiENTeS to tackle semantic segmentation as a class-agnostic entity segmentation problem. We validate our method using the ToothFairy2 Challenge, demonstrating its effectiveness in segmenting multiple structures in the maxillofacial region. We will make our code and models publicly available.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Conference contribution
Corresponding Author
Keywords Multimodal Segmentation ; Semantic Segmentation ; Toothfairy2 Challenge ; Vision Transformers
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Conference Title Supervised and Semi-supervised Multi-structure Segmentation and Landmark Detection in Dental Data
Journal Lecture Notes in Computer Science
Quellenangaben Volume: 15571 LNCS, Issue: , Pages: 21-29 Article Number: , Supplement: ,
Publisher Springer
Publishing Place Berlin [u.a.]
Non-patent literature Publications
Institute(s) Institute for Machine Learning in Biomed Imaging (IML)