Scholarlink

Robust 3D segmentation of primary and permanent teeth in cone-beam CT (CBCT) is critical for pediatric and orthodontic care. We propose a fully automatic deep-learning pipeline built on the self-configuring nnU-Net v2 framework, tailored for high-fidelity dental shape modeling. Our approach learns fine-scale tooth geometries directly from volumetric data, eliminating manual tuning. On a pediatric CBCT cohort (369 training, 93 validation, 55 test scans), our model attains a mean Dice score of 0.87 across 55 dental and supporting anatomical structures. Key components include adaptive preprocessing (isotropic resampling, automatic craniofacial cropping, intensity normalization), on-the-fly 3D augmentations, and lightweight postprocessing to remove spurious segment. The resulting segmentations are consistent and clinically actionable, supporting advanced 3D morphometric analysis and digital treatment planning. By extending state-of-the-art volumetric segmentation to mixed dentition CBCT data, our work facilitates integration of AI-driven geometric learning into routine pediatric dentistry workflows.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Self-configuring 3D Segmentation of Pediatric Dentition

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Enzo Tulissi,
  • Alban Gaydamour,
  • Juan C. Prieto,
  • Claudia Mattos,
  • Renata R. Rosa,
  • Sara Tinawi,
  • Dylan J. Keener,
  • Aron Aliaga Del Castillo,
  • Eduardo Caleme,
  • Brent Larson,
  • Antonio C. de Oliveira Ruellas,
  • Luis E. Arriola-Guillén,
  • Jonas Bianchi,
  • Heesoo Oh,
  • Marcela Lima Gurgel,
  • Erika Benavides,
  • Fabiana Soki,
  • Yalil A. Rodríguez-Cárdenas,
  • Gustavo A. Ruíz-Mora,
  • Bruno M. R. Braga,
  • Ana B. Teodoro,
  • Selene Barone,
  • Martin Styner,
  • Roberto Bespalez-Neto,
  • Lucia H. Cevidanes

摘要

Robust 3D segmentation of primary and permanent teeth in cone-beam CT (CBCT) is critical for pediatric and orthodontic care. We propose a fully automatic deep-learning pipeline built on the self-configuring nnU-Net v2 framework, tailored for high-fidelity dental shape modeling. Our approach learns fine-scale tooth geometries directly from volumetric data, eliminating manual tuning. On a pediatric CBCT cohort (369 training, 93 validation, 55 test scans), our model attains a mean Dice score of 0.87 across 55 dental and supporting anatomical structures. Key components include adaptive preprocessing (isotropic resampling, automatic craniofacial cropping, intensity normalization), on-the-fly 3D augmentations, and lightweight postprocessing to remove spurious segment. The resulting segmentations are consistent and clinically actionable, supporting advanced 3D morphometric analysis and digital treatment planning. By extending state-of-the-art volumetric segmentation to mixed dentition CBCT data, our work facilitates integration of AI-driven geometric learning into routine pediatric dentistry workflows.