Suppr超能文献

从颞骨 CT 成像中自动提取解剖测量值。

Automated Extraction of Anatomical Measurements From Temporal Bone CT Imaging.

机构信息

Department of Otolaryngology-Head and Neck Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.

Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, USA.

出版信息

Otolaryngol Head Neck Surg. 2022 Oct;167(4):731-738. doi: 10.1177/01945998221076801. Epub 2022 Feb 8.

Abstract

OBJECTIVE

Proposed methods of minimally invasive and robot-assisted procedures within the temporal bone require measurements of surgically relevant distances and angles, which often require time-consuming manual segmentation of preoperative imaging. This study aims to describe an automatic segmentation and measurement extraction pipeline of temporal bone cone-beam computed tomography (CT) scans.

STUDY DESIGN

Descriptive study of temporal bone measurements.

SETTING

Academic institution.

METHODS

A propagation template composed of 16 temporal bone CT scans was formed with relevant anatomical structures and landmarks manually segmented. Next, 52 temporal bone CT scans were autonomously segmented using deformable registration techniques from the Advanced Normalization Tools Python package. Anatomical measurements were extracted via in-house Python algorithms. Extracted measurements were compared to ground truth values from manual segmentations.

RESULTS

Paired test analyses showed no statistical difference between measurements using this pipeline and ground truth measurements from manually segmented images. Mean (SD) malleus manubrium length was 4.39 (0.34) mm. Mean (SD) incus short and long processes were 2.91 (0.18) mm and 3.53 (0.38) mm, respectively. The mean (SD) maximal diameter of the incus long process was 0.74 (0.17) mm. The first and second facial nerve genus had mean (SD) angles of 68.6 (6.7) degrees and 111.1 (5.3) degrees, respectively. The facial recess had a mean (SD) span of 3.21 (0.46) mm. Mean (SD) minimum distance between the external auditory canal and tegmen was 3.79 (1.05) mm.

CONCLUSIONS

This is the first study to automatically extract relevant temporal bone anatomical measurements from CT scans using segmentation propagation. Measurements from these models can streamline preoperative planning, improve future segmentation techniques, and help develop future image-guided or robot-assisted systems for temporal bone procedures.

摘要

目的

提出的经颞骨微创和机器人辅助手术方法需要测量手术相关的距离和角度,这通常需要对术前影像进行耗时的手动分割。本研究旨在描述一种自动分割和提取颞骨锥形束 CT(CBCT)扫描的颞骨测量值的管道。

研究设计

颞骨测量的描述性研究。

设置

学术机构。

方法

使用手动分割的相关解剖结构和地标形成由 16 个颞骨 CT 扫描组成的传播模板。接下来,使用来自 Advanced Normalization Tools Python 包的变形配准技术自动分割 52 个颞骨 CT 扫描。通过内部 Python 算法提取解剖测量值。提取的测量值与手动分割的真实值进行比较。

结果

配对 t 检验分析显示,使用该管道的测量值与手动分割图像的真实值之间无统计学差异。锤骨柄长度的平均值(标准差)为 4.39(0.34)mm。砧骨短和长突的平均值(标准差)分别为 2.91(0.18)mm 和 3.53(0.38)mm。砧骨长突的最大直径平均值(标准差)为 0.74(0.17)mm。面神经第一和第二支的平均值(标准差)角度分别为 68.6(6.7)度和 111.1(5.3)度。面神经隐窝的平均跨度(标准差)为 3.21(0.46)mm。外耳道口与鼓室盖之间的最小距离平均值(标准差)为 3.79(1.05)mm。

结论

这是第一项使用分割传播自动从 CT 扫描中提取相关颞骨解剖测量值的研究。这些模型的测量值可以简化术前计划,改进未来的分割技术,并有助于开发未来的颞骨手术图像引导或机器人辅助系统。

相似文献

1
Automated Extraction of Anatomical Measurements From Temporal Bone CT Imaging.
Otolaryngol Head Neck Surg. 2022 Oct;167(4):731-738. doi: 10.1177/01945998221076801. Epub 2022 Feb 8.
2
Automated Registration-Based Temporal Bone Computed Tomography Segmentation for Applications in Neurotologic Surgery.
Otolaryngol Head Neck Surg. 2022 Jul;167(1):133-140. doi: 10.1177/01945998211044982. Epub 2021 Sep 7.
3
A Self-Configuring Deep Learning Network for Segmentation of Temporal Bone Anatomy in Cone-Beam CT Imaging.
Otolaryngol Head Neck Surg. 2023 Oct;169(4):988-998. doi: 10.1002/ohn.317. Epub 2023 Mar 8.
4
Statistical Shape Model of the Temporal Bone Using Segmentation Propagation.
Otol Neurotol. 2022 Jul 1;43(6):e679-e687. doi: 10.1097/MAO.0000000000003554.
5
PWD-3DNet: A Deep Learning-Based Fully-Automated Segmentation of Multiple Structures on Temporal Bone CT Scans.
IEEE Trans Image Process. 2021;30:739-753. doi: 10.1109/TIP.2020.3038363. Epub 2020 Dec 4.
6
Atlas-based segmentation of temporal bone surface structures.
Int J Comput Assist Radiol Surg. 2019 Aug;14(8):1267-1273. doi: 10.1007/s11548-019-01978-2. Epub 2019 Apr 25.
7
Fully automated segmentation in temporal bone CT with neural network: a preliminary assessment study.
BMC Med Imaging. 2021 Nov 9;21(1):166. doi: 10.1186/s12880-021-00698-x.
8
Variability in Manual Segmentation of Temporal Bone Structures in Cone Beam CT Images.
Otol Neurotol. 2024 Mar 1;45(3):e137-e141. doi: 10.1097/MAO.0000000000004119. Epub 2024 Feb 7.
9
Fully automated preoperative segmentation of temporal bone structures from clinical CT scans.
Sci Rep. 2021 Jan 8;11(1):116. doi: 10.1038/s41598-020-80619-0.
10
Automatic Segmentation of Bone Selective MR Images for Visualization and Craniometry of the Cranial Vault.
Acad Radiol. 2022 Mar;29 Suppl 3(Suppl 3):S98-S106. doi: 10.1016/j.acra.2021.03.010. Epub 2021 Apr 24.

引用本文的文献

1
Exploration of Automated Measurement for Ossicular Chains Based on 3-Dimensional Geometric Information.
Cyborg Bionic Syst. 2025 Jul 2;6:0305. doi: 10.34133/cbsystems.0305. eCollection 2025.
2
ANTsX neuroimaging-derived structural phenotypes of UK Biobank.
Sci Rep. 2024 Apr 17;14(1):8848. doi: 10.1038/s41598-024-59440-6.
3
A Self-Configuring Deep Learning Network for Segmentation of Temporal Bone Anatomy in Cone-Beam CT Imaging.
Otolaryngol Head Neck Surg. 2023 Oct;169(4):988-998. doi: 10.1002/ohn.317. Epub 2023 Mar 8.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验