通过集成学习和主动轮廓模型对创伤性损伤患者进行自动肾脏分割
Automated Kidney Segmentation for Traumatic Injured Patients through Ensemble Learning and Active Contour Modeling.
作者信息
Farzaneh Negar, Reza Soroushmehr S M, Patel Hirenkumar, Wood Alexander, Gryak Jonathan, Fessell David, Najarian Kayvan
出版信息
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:3418-3421. doi: 10.1109/EMBC.2018.8512967.
Abstract
Traumatic abdominal injury can lead to multiple complications including laceration of major organs such as kidneys. Contrast-enhanced Computed Tomography (CT) is the primary imaging modality for evaluating kidney injury. However, the traditional visual examination of CT scans is time consuming, non-quantitative, prone to human error, and costly. In this work we propose a kidney segmentation method using machine learning and active contour modeling. We first detect an initialization mask inside the kidney and then evolve its boundary. This model is specifically developed and evaluated on trauma cases. Our experimental results show the average recall score of 92.6% and average Dice similarity value of 88.9%.
摘要
创伤性腹部损伤可导致多种并发症，包括肾脏等主要器官的撕裂伤。对比增强计算机断层扫描（CT）是评估肾脏损伤的主要成像方式。然而，传统的CT扫描视觉检查耗时、非定量、容易出现人为误差且成本高昂。在这项工作中，我们提出了一种使用机器学习和主动轮廓模型的肾脏分割方法。我们首先在肾脏内部检测一个初始化掩码，然后演化其边界。该模型是专门针对创伤病例开发和评估的。我们的实验结果显示平均召回率为92.6%，平均骰子相似性值为88.9%。
相似文献
1
Automated Kidney Segmentation for Traumatic Injured Patients through Ensemble Learning and Active Contour Modeling.通过集成学习和主动轮廓模型对创伤性损伤患者进行自动肾脏分割
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:3418-3421. doi: 10.1109/EMBC.2018.8512967.
2
Automated segmentation of the injured kidney due to abdominal trauma.腹部创伤致伤肾脏的自动分割。
J Med Syst. 2019 Nov 24;44(1):5. doi: 10.1007/s10916-019-1476-1.
3
Fully Automated Spleen Localization And Segmentation Using Machine Learning And 3D Active Contours.使用机器学习和3D活动轮廓的全自动脾脏定位与分割
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:53-56. doi: 10.1109/EMBC.2018.8512182.
4
Partitioned edge-function-scaled region-based active contour (p-ESRAC): automated liver segmentation in multiphase contrast-enhanced MRI.分区边缘函数缩放区域主动轮廓模型（p-ESRAC）：多期对比增强磁共振成像中的肝脏自动分割
Med Phys. 2014 Apr;41(4):041914. doi: 10.1118/1.4867865.
5
A robust statistics driven volume-scalable active contour for segmenting anatomical structures in volumetric medical images with complex conditions.一种基于稳健统计的体积可缩放活动轮廓，用于在具有复杂条件的体积医学图像中分割解剖结构。
Biomed Eng Online. 2016 Apr 14;15:39. doi: 10.1186/s12938-016-0153-6.
6
Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets.基于深度卷积神经网络和时间隐式水平集的自动腹部多器官分割。
Int J Comput Assist Radiol Surg. 2017 Mar;12(3):399-411. doi: 10.1007/s11548-016-1501-5. Epub 2016 Nov 24.
7
Detection of Lung Contour with Closed Principal Curve and Machine Learning.基于闭型主曲线和机器学习的肺轮廓检测
J Digit Imaging. 2018 Aug;31(4):520-533. doi: 10.1007/s10278-018-0058-y.
8
Spatial aggregation of holistically-nested convolutional neural networks for automated pancreas localization and segmentation.整体嵌套卷积神经网络的空间聚合用于自动胰腺定位和分割。
Med Image Anal. 2018 Apr;45:94-107. doi: 10.1016/j.media.2018.01.006. Epub 2018 Feb 1.
9
A generalized active shape model for segmentation of liver in low-contrast CT volumes.一种用于低对比度CT容积中肝脏分割的广义主动形状模型。
Comput Biol Med. 2017 Mar 1;82:59-70. doi: 10.1016/j.compbiomed.2017.01.009. Epub 2017 Jan 24.
10
Automatic localization of solid organs on 3D CT images by a collaborative majority voting decision based on ensemble learning.基于集成学习的协作多数投票决策自动定位 3D CT 图像中的实体器官。
Comput Med Imaging Graph. 2012 Jun;36(4):304-13. doi: 10.1016/j.compmedimag.2011.12.004. Epub 2012 Mar 14.
引用本文的文献
1
A Novel Method to Compute the Contact Surface Area Between an Organ and Cancer Tissue.一种计算器官与癌组织之间接触表面积的新方法。
J Imaging. 2025 Mar 6;11(3):78. doi: 10.3390/jimaging11030078.
2
The application of deep learning in abdominal trauma diagnosis by CT imaging.深度学习在 CT 影像诊断腹部创伤中的应用。
World J Emerg Surg. 2024 May 6;19(1):17. doi: 10.1186/s13017-024-00546-7.
3
Deep Learning for Automated Detection and Localization of Traumatic Abdominal Solid Organ Injuries on CT Scans.深度学习在 CT 扫描中自动检测和定位创伤性腹部实体器官损伤中的应用。
J Imaging Inform Med. 2024 Jun;37(3):1113-1123. doi: 10.1007/s10278-024-01038-5. Epub 2024 Feb 16.
4
A deep learning framework for automated detection and quantitative assessment of liver trauma.深度学习框架，用于自动检测和定量评估肝外伤。
BMC Med Imaging. 2022 Mar 8;22(1):39. doi: 10.1186/s12880-022-00759-9.
5
Improving segmentation accuracy of CT kidney cancer images using adaptive active contour model.使用自适应主动轮廓模型提高CT肾癌图像的分割精度
Medicine (Baltimore). 2020 Nov 20;99(47):e23083. doi: 10.1097/MD.0000000000023083.
6
Automated segmentation of the injured kidney due to abdominal trauma.腹部创伤致伤肾脏的自动分割。
J Med Syst. 2019 Nov 24;44(1):5. doi: 10.1007/s10916-019-1476-1.
本文引用的文献
1
3D Kidney Segmentation from Abdominal Images Using Spatial-Appearance Models.使用空间外观模型从腹部图像中进行3D肾脏分割
Comput Math Methods Med. 2017;2017:9818506. doi: 10.1155/2017/9818506. Epub 2017 Feb 9.
2
Computer-aided detection of exophytic renal lesions on non-contrast CT images.非增强CT图像上外生性肾病变的计算机辅助检测
Med Image Anal. 2015 Jan;19(1):15-29. doi: 10.1016/j.media.2014.07.005. Epub 2014 Aug 15.
3
Imaging in renal trauma.肾外伤的影像学检查
World J Radiol. 2013 Aug 28;5(8):275-84. doi: 10.4329/wjr.v5.i8.275.
4
Automated abdominal multi-organ segmentation with subject-specific atlas generation.基于特定个体图谱生成的自动腹部多器官分割。
IEEE Trans Med Imaging. 2013 Sep;32(9):1723-30. doi: 10.1109/TMI.2013.2265805. Epub 2013 Jun 3.
5
Multi-organ abdominal CT segmentation using hierarchically weighted subject-specific atlases.使用分层加权的个体特异性图谱进行腹部多器官CT分割
Med Image Comput Comput Assist Interv. 2012;15(Pt 1):10-7. doi: 10.1007/978-3-642-33415-3_2.
6
SLIC superpixels compared to state-of-the-art superpixel methods.SLIC 超像素与最先进的超像素方法比较。
IEEE Trans Pattern Anal Mach Intell. 2012 Nov;34(11):2274-82. doi: 10.1109/TPAMI.2012.120.
7
Automatic contrast phase estimation in CT volumes.CT容积中的自动对比剂相位估计
Med Image Comput Comput Assist Interv. 2011;14(Pt 3):166-74. doi: 10.1007/978-3-642-23626-6_21.
8
Active contours without edges.无边缘活动轮廓。
IEEE Trans Image Process. 2001;10(2):266-77. doi: 10.1109/83.902291.
9
Computer-aided kidney segmentation on abdominal CT images.腹部CT图像上的计算机辅助肾脏分割
IEEE Trans Inf Technol Biomed. 2006 Jan;10(1):59-65. doi: 10.1109/titb.2005.855561.
10
Fully automatic anatomical, pathological, and functional segmentation from CT scans for hepatic surgery.通过CT扫描实现肝脏手术的全自动解剖、病理和功能分割。
Comput Aided Surg. 2001;6(3):131-42. doi: 10.1002/igs.1016.
Zotero 插件