Leveraging Point Transformers for Detecting Anatomical Landmarks in Digital Dentistry

Leveraging Point Transformers for Detecting Anatomical Landmarks in Digital Dentistry

Stať ve sborníku v databázi WoS či Scopus

The increasing availability of intraoral scanning devices has heightened their importance in modern clinical orthodontics. Clinicians utilize advanced Computer-Aided Design techniques to create patient-specific treatment plans that include laboriously identifying crucial landmarks such as cusps, mesial-distal locations, facial axis points, and tooth-gingiva boundaries. Detecting such landmarks automatically presents challenges, including limited dataset sizes, significant anatomical variability among subjects, and the geometric nature of the data. We present our experiments from the 3DTeethLand Grand Challenge at MICCAI 2024. Our method leverages recent advancements in point cloud learning through transformer architectures. We designed a Point Transformer v3 inspired module to capture meaningful geometric and anatomical features, which are processed by a lightweight decoder to predict per-point distances, further processed by graph-based non-minima suppression. We report promising results and discuss insights on learned feature interpretability.

The increasing availability of intraoral scanning devices has heightened their importance in modern clinical orthodontics. Clinicians utilize advanced Computer-Aided Design techniques to create patient-specific treatment plans that include laboriously identifying crucial landmarks such as cusps, mesial-distal locations, facial axis points, and tooth-gingiva boundaries. Detecting such landmarks automatically presents challenges, including limited dataset sizes, significant anatomical variability among subjects, and the geometric nature of the data. We present our experiments from the 3DTeethLand Grand Challenge at MICCAI 2024. Our method leverages recent advancements in point cloud learning through transformer architectures. We designed a Point Transformer v3 inspired module to capture meaningful geometric and anatomical features, which are processed by a lightweight decoder to predict per-point distances, further processed by graph-based non-minima suppression. We report promising results and discuss insights on learned feature interpretability.

3D dental landmark detection | 3D medical shape analysis | 3DTeethLand MICCAI 2024 challenge

3D dental landmark detection | 3D medical shape analysis | 3DTeethLand MICCAI 2024 challenge

KUBÍK, T.; KODYM, O.; ŠILLING, P.; TRÁVNÍČKOVÁ, K.; MOJŽIŠ, T.; MATULA, J.

2026

01.01.2025

Springer Science and Business Media Deutschland GmbH

9783031889769

Lecture Notes in Computer Science

Lecture Notes in Computer Science

15571 LNCS

Švýcarská konfederace

216

228

13

https://link.springer.com/chapter/10.1007/978-3-031-88977-6_20?getft_integrator=scopus