• 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

深度学习和水平集方法在 CT 扫描中的肝脏和肿瘤分割。

Deep learning and level set approach for liver and tumor segmentation from CT scans.

机构信息

College of Engineering and Technology, American University of the Middle East, Kuwait, Kuwait.

出版信息

J Appl Clin Med Phys. 2020 Oct;21(10):200-209. doi: 10.1002/acm2.13003. Epub 2020 Aug 10.

DOI:10.1002/acm2.13003
PMID:33113290
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7592966/
Abstract

PURPOSE

Segmentation of liver organ and tumors from computed tomography (CT) scans is an important task for hepatic surgical planning. Manual segmentation of liver and tumors is tedious, time-consuming, and biased to the clinician experience. Therefore, automatic segmentation of liver and tumors is highly desirable. It would improve the surgical planning treatments and follow-up assessment.

METHOD

This work presented the development of an automatic method for liver and tumor segmentation from CT scans. The proposed method was based on fully convolutional neural (FCN) network with region-based level set function. The framework starts to segment the liver organ from CT scan, which is followed by a step to segment tumors inside the liver envelope. The fully convolutional network is trained to predict the coarse liver/tumor segmentation, while the localized region-based level aims to refine the predicted segmentation to find the correct final segmentation.

RESULTS

The effectiveness of the proposed method is validated against two publically available datasets, LiTS and IRCAD datasets. Dice scores for liver and tumor segmentation in IRCAD datasets are 95.2% and 76.1%, respectively, while for LiTS dataset are 95.6% and 70%, respectively.

CONCLUSION

The proposed method succeeded to segment liver and tumors in heterogeneous CT scans from different scanners, as in IRCAD dataset, which proved its ability for generalization and be promising tool for automatic analysis of liver and its tumors in clinical routine.

摘要

目的

从计算机断层扫描 (CT) 扫描中分割肝脏器官和肿瘤是肝外科规划的重要任务。手动分割肝脏和肿瘤既繁琐又耗时，并且容易受到临床医生经验的影响。因此，自动分割肝脏和肿瘤是非常需要的。这将改善手术规划治疗和后续评估。

方法

本工作提出了一种从 CT 扫描中自动分割肝脏和肿瘤的方法。所提出的方法基于具有基于区域的水平集函数的全卷积神经网络 (FCN)。该框架首先从 CT 扫描中分割肝脏器官，然后进行分割肝包膜内的肿瘤。全卷积网络用于预测粗肝脏/肿瘤分割，而局部基于区域的水平集旨在细化预测的分割以找到正确的最终分割。

结果

该方法在两个公开可用的数据集 LiTS 和 IRCAD 上进行了有效性验证。IRCAD 数据集的肝脏和肿瘤分割的 Dice 分数分别为 95.2%和 76.1%，而 LiTS 数据集的分别为 95.6%和 70%。

结论

所提出的方法成功地分割了来自不同扫描仪的异质 CT 扫描中的肝脏和肿瘤，这证明了它的泛化能力，并有望成为临床常规中肝脏及其肿瘤自动分析的有用工具。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/17b2a555805e/ACM2-21-200-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/6a25561f5471/ACM2-21-200-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/4dff83b7c3bd/ACM2-21-200-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/b56811f07bc2/ACM2-21-200-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/05176eaa41f1/ACM2-21-200-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/dfd0263ddfc8/ACM2-21-200-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/277d08e52510/ACM2-21-200-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/7e127a83f48b/ACM2-21-200-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/17b2a555805e/ACM2-21-200-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/6a25561f5471/ACM2-21-200-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/4dff83b7c3bd/ACM2-21-200-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/b56811f07bc2/ACM2-21-200-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/05176eaa41f1/ACM2-21-200-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/dfd0263ddfc8/ACM2-21-200-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/277d08e52510/ACM2-21-200-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/7e127a83f48b/ACM2-21-200-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/86d2/7592966/17b2a555805e/ACM2-21-200-g008.jpg

相似文献

1
Deep learning and level set approach for liver and tumor segmentation from CT scans.深度学习和水平集方法在 CT 扫描中的肝脏和肿瘤分割。
J Appl Clin Med Phys. 2020 Oct;21(10):200-209. doi: 10.1002/acm2.13003. Epub 2020 Aug 10.
2
HFRU-Net: High-Level Feature Fusion and Recalibration UNet for Automatic Liver and Tumor Segmentation in CT Images.HFRU-Net：用于 CT 图像中肝脏和肿瘤自动分割的高级特征融合和再校准 U 型网络。
Comput Methods Programs Biomed. 2022 Jan;213:106501. doi: 10.1016/j.cmpb.2021.106501. Epub 2021 Oct 28.
3
SADSNet: A robust 3D synchronous segmentation network for liver and liver tumors based on spatial attention mechanism and deep supervision.SADSNet：一种基于空间注意力机制和深度监督的稳健的肝脏和肝肿瘤三维同步分割网络。
J Xray Sci Technol. 2024;32(3):707-723. doi: 10.3233/XST-230312.
4
Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks.使用基于形状表示模型约束的全卷积神经网络进行头颈部癌症放疗的全自动多器官分割。
Med Phys. 2018 Oct;45(10):4558-4567. doi: 10.1002/mp.13147. Epub 2018 Sep 19.
5
Automatic liver segmentation by integrating fully convolutional networks into active contour models.基于全卷积网络的主动轮廓模型自动肝脏分割
Med Phys. 2019 Oct;46(10):4455-4469. doi: 10.1002/mp.13735. Epub 2019 Aug 16.
6
Patient-specific and global convolutional neural networks for robust automatic liver tumor delineation in follow-up CT studies.用于在随访 CT 研究中进行稳健自动肝肿瘤勾画的基于患者特定和全局卷积神经网络。
Med Biol Eng Comput. 2018 Sep;56(9):1699-1713. doi: 10.1007/s11517-018-1803-6. Epub 2018 Mar 10.
7
Efficient two-step liver and tumour segmentation on abdominal CT via deep learning and a conditional random field.通过深度学习和条件随机场在腹部CT上实现高效的两步肝脏和肿瘤分割
Comput Biol Med. 2022 Nov;150:106076. doi: 10.1016/j.compbiomed.2022.106076. Epub 2022 Sep 9.
8
Hepatic vessels segmentation using deep learning and preprocessing enhancement.使用深度学习和预处理增强进行肝脏血管分割。
J Appl Clin Med Phys. 2023 May;24(5):e13966. doi: 10.1002/acm2.13966. Epub 2023 Mar 18.
9
Tumor conspicuity enhancement-based segmentation model for liver tumor segmentation and RECIST diameter measurement in non-contrast CT images.基于肿瘤显著性增强的分割模型在非对比 CT 图像中进行肝脏肿瘤分割和 RECIST 直径测量。
Comput Biol Med. 2024 May;174:108420. doi: 10.1016/j.compbiomed.2024.108420. Epub 2024 Apr 6.
10
Segmentation of liver tumors with abdominal computed tomography using fully convolutional networks.使用全卷积网络对腹部计算机断层扫描中的肝脏肿瘤进行分割。
J Xray Sci Technol. 2022;30(5):953-966. doi: 10.3233/XST-221194.

引用本文的文献

1
When liver disease diagnosis encounters deep learning: Analysis, challenges, and prospects.当肝脏疾病诊断遇上深度学习：分析、挑战与展望。
ILIVER. 2023 Mar 4;2(1):73-87. doi: 10.1016/j.iliver.2023.02.002. eCollection 2023 Mar.
2
Ischemic Stroke Lesion Core Segmentation from CT Perfusion Scans Using Attention ResUnet Deep Learning.使用注意力ResUnet深度学习从CT灌注扫描中进行缺血性中风病灶核心分割
J Imaging Inform Med. 2025 Feb 14. doi: 10.1007/s10278-025-01407-8.
3
Efficient Extraction of Coronary Artery Vessels from Computed Tomography Angiography Images Using ResUnet and Vesselness.

本文引用的文献

1
The Liver Tumor Segmentation Benchmark (LiTS).肝脏肿瘤分割基准（LiTS）。
Med Image Anal. 2023 Feb;84:102680. doi: 10.1016/j.media.2022.102680. Epub 2022 Nov 17.
2
Survey on Liver Tumour Resection Planning System: Steps, Techniques, and Parameters.肝脏肿瘤切除规划系统综述：步骤、技术与参数
J Digit Imaging. 2020 Apr;33(2):304-323. doi: 10.1007/s10278-019-00262-8.
3
Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges.深度学习技术在医学图像分割中的应用：成就与挑战。
使用ResUnet和血管造影术从计算机断层扫描血管造影图像中高效提取冠状动脉血管
Bioengineering (Basel). 2024 Jul 26;11(8):759. doi: 10.3390/bioengineering11080759.
4
Future Perspectives on Radiomics in Acute Liver Injury and Liver Trauma.急性肝损伤和肝创伤中放射组学的未来展望
J Pers Med. 2024 May 27;14(6):572. doi: 10.3390/jpm14060572.
5
MANet: a multi-attention network for automatic liver tumor segmentation in computed tomography (CT) imaging.MANet：一种用于 CT 成像中自动肝肿瘤分割的多注意力网络。
Sci Rep. 2023 Nov 16;13(1):20098. doi: 10.1038/s41598-023-46580-4.
6
Performance and clinical applicability of machine learning in liver computed tomography imaging: a systematic review.机器学习在肝脏计算机断层成像中的性能和临床适用性：系统评价。
Eur Radiol. 2023 Oct;33(10):6689-6717. doi: 10.1007/s00330-023-09609-w. Epub 2023 May 12.
7
Detection of Liver Tumour Using Deep Learning Based Segmentation with Coot Extreme Learning Model.基于Coot极限学习模型的深度学习分割技术在肝脏肿瘤检测中的应用
Biomedicines. 2023 Mar 6;11(3):800. doi: 10.3390/biomedicines11030800.
8
Hepatic vessels segmentation using deep learning and preprocessing enhancement.使用深度学习和预处理增强进行肝脏血管分割。
J Appl Clin Med Phys. 2023 May;24(5):e13966. doi: 10.1002/acm2.13966. Epub 2023 Mar 18.
9
Fully Automatic Liver and Tumor Segmentation from CT Image Using an AIM-Unet.使用AIM-Unet从CT图像中进行全自动肝脏和肿瘤分割。
Bioengineering (Basel). 2023 Feb 6;10(2):215. doi: 10.3390/bioengineering10020215.
10
Artificial Intelligence in Hepatology- Ready for the Primetime.肝病学中的人工智能——准备好迎接黄金时代。
J Clin Exp Hepatol. 2023 Jan-Feb;13(1):149-161. doi: 10.1016/j.jceh.2022.06.009. Epub 2022 Jun 29.
J Digit Imaging. 2019 Aug;32(4):582-596. doi: 10.1007/s10278-019-00227-x.
4
Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing.基于全卷积神经网络和基于对象的后处理的 CT 自动肝肿瘤分割。
Sci Rep. 2018 Oct 19;8(1):15497. doi: 10.1038/s41598-018-33860-7.
5
An automated liver tumour segmentation from abdominal CT scans for hepatic surgical planning.基于腹部 CT 扫描的肝脏肿瘤自动分割用于肝外科手术规划。
Int J Comput Assist Radiol Surg. 2018 Aug;13(8):1169-1176. doi: 10.1007/s11548-018-1801-z. Epub 2018 Jun 2.
6
Precision of manual two-dimensional segmentations of lung and liver metastases and its impact on tumour response assessment using RECIST 1.1.肺和肝转移瘤手动二维分割的精确性及其对使用RECIST 1.1进行肿瘤反应评估的影响。
Eur Radiol Exp. 2017;1(1):16. doi: 10.1186/s41747-017-0015-4. Epub 2017 Oct 30.
7
A low-interaction automatic 3D liver segmentation method using computed tomography for selective internal radiation therapy.一种用于选择性内放射治疗的基于计算机断层扫描的低交互自动三维肝脏分割方法。
Biomed Res Int. 2014;2014:198015. doi: 10.1155/2014/198015. Epub 2014 Jul 3.
8
Automated medical image segmentation techniques.自动化医学图像分割技术。
J Med Phys. 2010 Jan;35(1):3-14. doi: 10.4103/0971-6203.58777.
9
Noise reduction in computed tomography scans using 3-d anisotropic hybrid diffusion with continuous switch.使用三维各向异性混合扩散和连续切换进行 CT 扫描降噪。
IEEE Trans Med Imaging. 2009 Oct;28(10):1585-94. doi: 10.1109/TMI.2009.2022368.
10
Localizing region-based active contours.基于区域的主动轮廓定位
IEEE Trans Image Process. 2008 Nov;17(11):2029-39. doi: 10.1109/TIP.2008.2004611.