Scholarlink

The creation of a virtual patient relies on the fusion of data from various imaging modalities, with cone-beam computed tomography (CBCT) serving as the primary source for detailed volumetric information on bone and tooth structures. The foundational step in building this digital representation of the patient is called image segmentation, which is the process of isolating and defining specific anatomical structures from the imaging data. However, manual tissue segmentation performed by a dental professional is often labor-intensive, time-consuming, and technically demanding. This chapter describes how AI has addressed these issues, particularly in the form of deep learning algorithms, by means of techniques of automated tissue segmentation.

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

Automated Tissue Segmentation

  • 章节

  • 发表日期：

    2026年

查看全文
  • Mariana Balcewicz Pozza,
  • Ji Yong Han,
  • Thi Ngoc Trang Tran,
  • Rafik Akhmad,
  • Malek Abu-Gharbieh,
  • Andreas Dominik Schwitalla,
  • Florian Beuer,
  • Arthur Rodriguez Gonzalez Cortes

摘要

The creation of a virtual patient relies on the fusion of data from various imaging modalities, with cone-beam computed tomography (CBCT) serving as the primary source for detailed volumetric information on bone and tooth structures. The foundational step in building this digital representation of the patient is called image segmentation, which is the process of isolating and defining specific anatomical structures from the imaging data. However, manual tissue segmentation performed by a dental professional is often labor-intensive, time-consuming, and technically demanding. This chapter describes how AI has addressed these issues, particularly in the form of deep learning algorithms, by means of techniques of automated tissue segmentation.