Improving Automatic Renal Segmentation in Clinically Normal and Abnormal Paediatric DCE-MRI via Contrast Maximisation and Convolutional Networks for Computing Markers of Kidney Function.

Improving Automatic Renal Segmentation in Clinically Normal and Abnormal Paediatric DCE-MRI via Contrast Maximisation and Convolutional Networks for Computing Markers of Kidney Function.
复制标题

通过对比度最大化和卷积网络计算肾功能标记物,改进临床正常和异常儿科 DCE-MRI 的自动肾脏分割。

DOI:
10.3390/s21237942
复制
发表时间:
2021-11-28
期刊:
Sensors (Basel, Switzerland)
影响因子:
--
通讯作者:
Kurugol S
Kurugol S
中科院分区:
其他
文献类型:
--
作者:
Asaturyan H;Villarini B;Sarao K;Chow JS;Afacan O;Kurugol S

文献摘要

参考文献

被引文献

相似文献

人们越来越需要快速、准确地计算临床标志物,以通过一项研究来改善肾功能和解剖学评估。然而,传统技术存在局限性,导致肾功能被高估或无法提供足够的空间分辨率来定位疾病位置。相比之下,动态对比增强(DCE)磁共振成像(MRI)的计算机辅助分析可以产生重要的标志物,包括肾小球滤过率(GFR)以及皮质和髓质的时间-强度曲线,用于确定尿路阻塞。本文提出了一种双级完全模块化框架,用于 4D DCE-MRI 体积中的自动肾室分割。 (1) 集成内存高效的 3D 深度学习,通过利用残差卷积神经网络来提高收敛性来定位每个肾脏;分割是通过有效学习时空信息以及保留边界的全卷积密集网络来执行的。 (2)通过非线性变换增强肾脏上下文信息以分割皮质和髓质。所提出的框架在包含 60 个 4D DCE-MRI 体积的儿科数据集上进行评估,这些数据表现出影响肾功能的不同条件。我们的技术在平均骰子相似度 (DSC) 方面优于基于 GrabCut 和支持向量机分类器的最先进方法 3.8%,并且在皮质和髓质分割方面表现出更高的统计稳定性和更低的标准偏差,分别降低了 12.4% 和 15.7%。
There is a growing demand for fast, accurate computation of clinical markers to improve renal function and anatomy assessment with a single study. However, conventional techniques have limitations leading to overestimations of kidney function or failure to provide sufficient spatial resolution to target the disease location. In contrast, the computer-aided analysis of dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) could generate significant markers, including the glomerular filtration rate (GFR) and time–intensity curves of the cortex and medulla for determining obstruction in the urinary tract. This paper presents a dual-stage fully modular framework for automatic renal compartment segmentation in 4D DCE-MRI volumes. (1) Memory-efficient 3D deep learning is integrated to localise each kidney by harnessing residual convolutional neural networks for improved convergence; segmentation is performed by efficiently learning spatial–temporal information coupled with boundary-preserving fully convolutional dense nets. (2) Renal contextual information is enhanced via non-linear transformation to segment the cortex and medulla. The proposed framework is evaluated on a paediatric dataset containing 60 4D DCE-MRI volumes exhibiting varying conditions affecting kidney function. Our technique outperforms a state-of-the-art approach based on a GrabCut and support vector machine classifier in mean dice similarity (DSC) by 3.8% and demonstrates higher statistical stability with lower standard deviation by 12.4% and 15.7% for cortex and medulla segmentation, respectively.
DOI: 10.1016/b978-0-12-815876-0.00078-4
发表时间: 2020-01-01
期刊: CHRONIC RENAL DISEASE, 2ND EDITION
影响因子: --
作者:
Cohen, Scott D.;Davison, Sara N.;Kimmel, Paul L.
通讯作者: Kimmel, Paul L.
DOI: 10.1002/mrm.24980
发表时间: 2014-09
影响因子: 3.3
作者:
Feng, Li;Grimm, Robert;Block, Kai Tobias;Chandarana, Hersh;Kim, Sungheon;Xu, Jian;Axel, Leon;Sodickson, Daniel K.;Otazo, Ricardo
通讯作者: Otazo, Ricardo
DOI: 10.1109/isbi.2018.8363865
发表时间: 2018-04
期刊: Proceedings. IEEE International Symposium on Biomedical Imaging
影响因子: --
作者:
Haghighi M;Warfield SK;Kurugol S
通讯作者: Kurugol S
DOI: 10.1002/wics.101
发表时间: 2010-07-01
影响因子: 3.2
作者:
Abdi, Herve;Williams, Lynne J.
通讯作者: Williams, Lynne J.
使用基于视图共享压缩感知的动态对比增强 MR 成像对动脉粥样硬化性肾病进行定量肾功能评估:一项体内研究
DOI: 10.1016/j.mri.2019.10.007
发表时间: 2020-01-01
影响因子: 2.5
作者:
Kong, Hanjing;Chen, Bin;Zhang, Jue
通讯作者: Zhang, Jue