Automated Orientation and Registration of Cone-Beam Computed Tomography Scans

被引：7

作者：

Anchling, Luc ^{[1
,2
]}

Hutin, Nathan ^{[1
,2
]}

Huang, Yanjie ^{[1
]}

Barone, Selene ^{[1
,5
]}

Roberts, Sophie ^{[8
]}

Miranda, Felicia ^{[1
,7
]}

Gurgel, Marcela ^{[1
]}

Al Turkestani, Najla ^{[1
,6
]}

Tinawi, Sara ^{[1
]}

Bianchi, Jonas ^{[1
,4
]}

Yatabe, Marilia ^{[1
]}

Ruellas, Antonio ^{[9
]}

Prieto, Juan Carlos ^{[3
]}

Cevidanes, Lucia ^{[1
]}

机构：

[1] Univ Michigan, Ann Arbor, MI 48109 USA

[2] CPE Lyon, Lyon, France

[3] Univ N Carolina, Chapel Hill, NC 27515 USA

[4] Univ Pacific, San Francisco, CA USA

[5] Magna Graecia Univ Catanzaro, Catanzaro, Italy

[6] King Abdulaziz Univ, Jeddah, Saudi Arabia

[7] Univ Sao Paulo, Bauru Dent Sch, Bauru, SP, Brazil

[8] Univ Melbourne, Dept Orthodont, Melbourne, Vic, Australia

[9] Fed Univ Rio Janeiro, Rio De Janeiro, Brazil

来源：

CLINICAL IMAGE-BASED PROCEDURES, FAIRNESS OF AI IN MEDICAL IMAGING, AND ETHICAL AND PHILOSOPHICAL ISSUES IN MEDICAL IMAGING, CLIP 2023, FAIMI 2023, EPIMI 2023 | 2023年 / 14242卷

关键词：

Deep Learning; Standardized Orientation; Medical Image Registration; 3D CBCT scans; Image Processing;

D O I：

10.1007/978-3-031-45249-9_5

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

Automated clinical decision support systems rely on accurate analysis of three-dimensional (3D) medical and dental images to assist clinicians in diagnosis, treatment planning, intervention, and assessment of growth and treatment effects. However, analyzing longitudinal 3D images requires standardized orientation and registration, which can be laborious and error-prone tasks dependent on structures of reference for registration. This paper proposes two novel tools to automatically perform the orientation and registration of 3D Cone-Beam Computed Tomography (CBCT) scans with high accuracy (<3. and <2mm of angular and linear errors when compared to expert clinicians). These tools have undergone rigorous testing, and are currently being evaluated by clinicians who utilize the 3D Slicer open-source platform. Our work aims to reduce the sources of error in the 3D medical image analysis workflow by automating these operations. These methods combine conventional image processing approaches and Artificial Intelligence (AI) based models trained and tested on de-identified CBCT volumetric images. Our results showed robust performance for standardized and reproducible image orientation and registration that provide a more complete understanding of individual patient facial growth and response to orthopedic treatment in less than 5 min.

引用

页码：43 / 58

页数：16