3D cephalometric landmark detection by multiple stage deep reinforcement learning

Abstract

The lengthy time needed for manual landmarking has delayed the widespread adoption of three-dimensional (3D) cephalometry. We here propose an automatic 3D cephalometric annotation system based on multi-stage deep reinforcement learning (DRL) and volume-rendered imaging. This system considers geometrical characteristics of landmarks and simulates the sequential decision process underlying human professional landmarking patterns. It consists mainly of constructing an appropriate two-dimensional cutaway or 3D model view, then implementing single-stage DRL with gradient-based boundary estimation or multi-stage DRL to dictate the 3D coordinates of target landmarks. This system clearly shows sufficient detection accuracy and stability for direct clinical applications, with a low level of detection error and low inter-individual variation (1.96 ± 0.78 mm). Our system, moreover, requires no additional steps of segmentation and 3D mesh-object construction for landmark detection. We believe these system features will enable fast-track cephalometric analysis and planning and expect it to achieve greater accuracy as larger CT datasets become available for training and testing.

Three-Dimensional Postoperative Results Prediction for Orthognathic Surgery through Deep Learning-Based Alignment Network

“…Deep learning studies are also being conducted for the diagnosis and planning of dentofacial dysmorphosis [ 21 , 22 , 23 , 24 ]. However, most adhere to the classic method using points, planes, and angles [ 21 , 22 , 23 ].…”

“…Deep learning studies are also being conducted for the diagnosis and planning of dentofacial dysmorphosis [ 21 , 22 , 23 , 24 ]. However, most adhere to the classic method using points, planes, and angles [ 21 , 22 , 23 ]. Among these, Xiao et al estimated reference bony-shape models for orthognathic surgical planning using 3D point-cloud deep learning [ 24 ].…”

“…It can reduce the labor of experts while detecting image information that may be missed by humans. Deep learning research related to the diagnosis and planning of dentofacial dysmorphosis is being actively conducted [ 21 , 22 , 23 ]. However, most have focused only on finding reference points, planes, and angles using conventional methods [ 21 , 22 , 23 ].…”

“…Deep learning research related to the diagnosis and planning of dentofacial dysmorphosis is being actively conducted [ 21 , 22 , 23 ]. However, most have focused only on finding reference points, planes, and angles using conventional methods [ 21 , 22 , 23 ]. This may have been due to their failure to grasp the true nature of DNNs.…”

Use of Advanced Artificial Intelligence in Forensic Medicine, Forensic Anthropology and Clinical Anatomy

“…Automatized 3D cephalometric landmark annotation [41][42][43][44][45][46][47][48][49][50][51][52][53][54][55][56][57][58]…”