• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

创伤性骨盆CT图像中的骨折检测

Fracture Detection in Traumatic Pelvic CT Images.

作者信息

Wu Jie, Davuluri Pavani, Ward Kevin R, Cockrell Charles, Hobson Rosalyn, Najarian Kayvan

机构信息

Department of Computer Science, Virginia Commonwealth University, 401 West Main Street, Richmond, VA 23284, USA.

出版信息

Int J Biomed Imaging. 2012;2012:327198. doi: 10.1155/2012/327198. Epub 2012 Jan 4.

DOI:10.1155/2012/327198
PMID:22287952
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC3263603/
Abstract

Fracture detection in pelvic bones is vital for patient diagnostic decisions and treatment planning in traumatic pelvic injuries. Manual detection of bone fracture from computed tomography (CT) images is very challenging due to low resolution of the images and the complex pelvic structures. Automated fracture detection from segmented bones can significantly help physicians analyze pelvic CT images and detect the severity of injuries in a very short period. This paper presents an automated hierarchical algorithm for bone fracture detection in pelvic CT scans using adaptive windowing, boundary tracing, and wavelet transform while incorporating anatomical information. Fracture detection is performed on the basis of the results of prior pelvic bone segmentation via our registered active shape model (RASM). The results are promising and show that the method is capable of detecting fractures accurately.

摘要

骨盆骨折检测对于创伤性骨盆损伤患者的诊断决策和治疗规划至关重要。由于计算机断层扫描（CT）图像分辨率低以及骨盆结构复杂，通过手动从CT图像中检测骨折极具挑战性。从分割后的骨骼中自动检测骨折可以显著帮助医生在极短时间内分析骨盆CT图像并检测损伤的严重程度。本文提出了一种在骨盆CT扫描中使用自适应窗口、边界追踪和小波变换并结合解剖学信息的自动分层骨折检测算法。通过我们的注册主动形状模型（RASM），基于先前骨盆骨分割的结果进行骨折检测。结果很有前景，表明该方法能够准确检测骨折。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/83782a5515bd/IJBI2012-327198.010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/68dc41b4032d/IJBI2012-327198.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/77d4225df224/IJBI2012-327198.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/7b805d8045b7/IJBI2012-327198.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/4354cf722e87/IJBI2012-327198.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/25ea1f2db9fa/IJBI2012-327198.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/d43d1bc7ef9b/IJBI2012-327198.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/af181d0fd0c5/IJBI2012-327198.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/ec57d3cf1a70/IJBI2012-327198.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/5934bb29e2ca/IJBI2012-327198.009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/83782a5515bd/IJBI2012-327198.010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/68dc41b4032d/IJBI2012-327198.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/77d4225df224/IJBI2012-327198.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/7b805d8045b7/IJBI2012-327198.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/4354cf722e87/IJBI2012-327198.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/25ea1f2db9fa/IJBI2012-327198.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/d43d1bc7ef9b/IJBI2012-327198.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/af181d0fd0c5/IJBI2012-327198.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/ec57d3cf1a70/IJBI2012-327198.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/5934bb29e2ca/IJBI2012-327198.009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/84fb/3263603/83782a5515bd/IJBI2012-327198.010.jpg

相似文献

1
Fracture Detection in Traumatic Pelvic CT Images.创伤性骨盆CT图像中的骨折检测
Int J Biomed Imaging. 2012;2012:327198. doi: 10.1155/2012/327198. Epub 2012 Jan 4.
2
A hierarchical method based on active shape models and directed Hough transform for segmentation of noisy biomedical images; application in segmentation of pelvic X-ray images.基于主动形状模型和有向霍夫变换的分层方法用于分割噪声生物医学图像；在骨盆 X 射线图像分割中的应用。
BMC Med Inform Decis Mak. 2009 Nov 3;9 Suppl 1(Suppl 1):S2. doi: 10.1186/1472-6947-9-S1-S2.
3
Unified wavelet and Gaussian filtering for segmentation of CT images; application in segmentation of bone in pelvic CT images.统一的小波和高斯滤波在 CT 图像分割中的应用；在骨盆 CT 图像中骨分割的应用。
BMC Med Inform Decis Mak. 2009 Nov 3;9 Suppl 1(Suppl 1):S8. doi: 10.1186/1472-6947-9-S1-S8.
4
A new hierarchical method for multi-level segmentation of bone in pelvic CT scans.一种用于骨盆CT扫描中骨骼多级分割的新分层方法。
Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:3399-402. doi: 10.1109/IEMBS.2011.6090920.
5
Hemorrhage detection and segmentation in traumatic pelvic injuries.创伤性骨盆损伤中的出血检测和分割。
Comput Math Methods Med. 2012;2012:898430. doi: 10.1155/2012/898430. Epub 2012 Jul 19.
6
A computational pipeline for quantification of pulmonary infections in small animal models using serial PET-CT imaging.使用连续 PET-CT 成像对小动物模型中的肺部感染进行定量分析的计算流程。
EJNMMI Res. 2013 Jul 23;3(1):55. doi: 10.1186/2191-219X-3-55.
7
Interpretable Severity Scoring of Pelvic Trauma Through Automated Fracture Detection and Bayesian Inference.通过自动骨折检测和贝叶斯推理对骨盆创伤进行可解释的严重程度评分。
IEEE Trans Med Imaging. 2025 Jan;44(1):130-141. doi: 10.1109/TMI.2024.3428836. Epub 2025 Jan 2.
8
Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images.利用多方位断层图像的深度卷积神经网络检测 3D-CT 中的骨盆骨折。
Sci Rep. 2021 Jun 3;11(1):11716. doi: 10.1038/s41598-021-91144-z.
9
Fast and automatic bone segmentation and registration of 3D ultrasound to CT for the full pelvic anatomy: a comparative study.快速自动的 3D 超声与 CT 骨盆全解剖骨分割与配准：一项对比研究。
Int J Comput Assist Radiol Surg. 2018 Oct;13(10):1515-1524. doi: 10.1007/s11548-018-1788-5. Epub 2018 May 26.
10
Deep learning and SURF for automated classification and detection of calcaneus fractures in CT images.深度学习和 SURF 用于 CT 图像中跟骨骨折的自动分类和检测。
Comput Methods Programs Biomed. 2019 Apr;171:27-37. doi: 10.1016/j.cmpb.2019.02.006. Epub 2019 Feb 12.

引用本文的文献

1
Automated Association for Osteosynthesis Foundation and Orthopedic Trauma Association classification of pelvic fractures on pelvic radiographs using deep learning.基于深度学习的骨盆 X 射线片上自动进行骨科内固定协会和创伤骨科协会骨盆骨折分类。
Sci Rep. 2024 Sep 4;14(1):20548. doi: 10.1038/s41598-024-71654-2.
2
An Extra Set of Intelligent Eyes: Application of Artificial Intelligence in Imaging of Abdominopelvic Pathologies in Emergency Radiology.另一双智能之眼：人工智能在急诊放射学腹部盆腔病变成像中的应用
Diagnostics (Basel). 2022 May 30;12(6):1351. doi: 10.3390/diagnostics12061351.
3
Recognition and Segmentation of Individual Bone Fragments with a Deep Learning Approach in CT Scans of Complex Intertrochanteric Fractures: A Retrospective Study.

本文引用的文献

1
A new hierarchical method for multi-level segmentation of bone in pelvic CT scans.一种用于骨盆CT扫描中骨骼多级分割的新分层方法。
Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:3399-402. doi: 10.1109/IEMBS.2011.6090920.
2
Global registration of multiple bone fragments using statistical atlas models: feasibility experiments.使用统计图谱模型进行多个骨碎片的全局配准：可行性实验
Annu Int Conf IEEE Eng Med Biol Soc. 2008;2008:5374-7. doi: 10.1109/IEMBS.2008.4650429.
3
MRI bone segmentation using deformable models and shape priors.
深度学习方法在复杂转子间骨折 CT 扫描中对单个骨碎片的识别与分割：一项回顾性研究。
J Digit Imaging. 2022 Dec;35(6):1681-1689. doi: 10.1007/s10278-022-00669-w. Epub 2022 Jun 16.
4
Automatic multi-class intertrochanteric femur fracture detection from CT images based on AO/OTA classification using faster R-CNN-BO method.基于 AO/OTA 分类的更快 R-CNN-BO 方法从 CT 图像中自动检测多类股骨转子间骨折。
J Appl Biomed. 2020 Dec;18(4):97-105. doi: 10.32725/jab.2020.013. Epub 2020 Sep 22.
5
Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images.利用多方位断层图像的深度卷积神经网络检测 3D-CT 中的骨盆骨折。
Sci Rep. 2021 Jun 3;11(1):11716. doi: 10.1038/s41598-021-91144-z.
6
SEMI-AUTOMATED 3D SEGMENTATION OF PELVIC REGION BONES IN CT VOLUMES FOR THE ANNOTATION OF MACHINE LEARNING DATASETS.用于机器学习数据集标注的 CT 容积中骨盆区域骨骼的半自动 3D 分割。
Radiat Prot Dosimetry. 2021 Oct 12;195(3-4):172-176. doi: 10.1093/rpd/ncab073.
7
An Automated Deep Learning Method for Tile AO/OTA Pelvic Fracture Severity Grading from Trauma whole-Body CT.基于深度学习的创伤全身 CT 髋臼骨折Tile AO/OTA 分型严重程度自动分级方法
J Digit Imaging. 2021 Feb;34(1):53-65. doi: 10.1007/s10278-020-00399-x. Epub 2021 Jan 21.
8
Unsupervised cardiac image segmentation via multiswarm active contours with a shape prior.基于多群主动轮廓和形状先验的无监督心脏图像分割。
Comput Math Methods Med. 2013;2013:909625. doi: 10.1155/2013/909625. Epub 2013 Oct 2.
9
Biomedical informatics for computer-aided decision support systems: a survey.用于计算机辅助决策支持系统的生物医学信息学：一项综述。
ScientificWorldJournal. 2013;2013:769639. doi: 10.1155/2013/769639. Epub 2013 Feb 4.
10
Hemorrhage detection and segmentation in traumatic pelvic injuries.创伤性骨盆损伤中的出血检测和分割。
Comput Math Methods Med. 2012;2012:898430. doi: 10.1155/2012/898430. Epub 2012 Jul 19.
使用可变形模型和形状先验的MRI骨分割
Med Image Comput Comput Assist Interv. 2008;11(Pt 1):119-26. doi: 10.1007/978-3-540-85988-8_15.
4
Predictors of positive angiography in pelvic fractures: a prospective study.骨盆骨折血管造影阳性的预测因素：一项前瞻性研究。
J Am Coll Surg. 2008 Nov;207(5):656-62. doi: 10.1016/j.jamcollsurg.2008.05.025. Epub 2008 Jul 14.
5
Risk factors for pelvic fractures in lateral impact motor vehicle crashes.侧面撞击机动车碰撞中骨盆骨折的危险因素。
Accid Anal Prev. 2008 Jan;40(1):387-91. doi: 10.1016/j.aap.2007.07.005. Epub 2007 Jul 26.
6
Global registration of multiple point sets: feasibility and applications in multi-fragment fracture fixation.多点集的全球配准：在多片段骨折固定中的可行性及应用
Med Image Comput Comput Assist Interv. 2007;10(Pt 2):943-50. doi: 10.1007/978-3-540-75759-7_114.
7
The epidemiology of pelvic ring fractures: a population-based study.骨盆环骨折的流行病学：一项基于人群的研究。
J Trauma. 2007 Nov;63(5):1066-73; discussion 1072-3. doi: 10.1097/TA.0b013e3181589fa4.
8
Early detection of fractures with low-dose digital X-ray images in a pediatric trauma unit.在儿科创伤病房利用低剂量数字X线影像早期检测骨折
J Trauma. 2008 Jul;65(1):E4-7. doi: 10.1097/01.ta.0000198534.47134.bc.
9
Efficient shape matching using shape contexts.使用形状上下文进行高效形状匹配。
IEEE Trans Pattern Anal Mach Intell. 2005 Nov;27(11):1832-7. doi: 10.1109/TPAMI.2005.220.
10
4D deformable models with temporal constraints: application to 4D cardiac image segmentation.具有时间约束的4D可变形模型：应用于4D心脏图像分割
Med Image Anal. 2005 Feb;9(1):87-100. doi: 10.1016/j.media.2004.06.025.