A versatile end-to-end deep learning framework for improved full-automatic MRI hemodynamic parameter estimation

doi:10.1016/j.bspc.2025.107889

2025-05-29

PRE

DOI：10.1016/j.bspc.2025.107889

原文链接

原文求助

摘要

En 中文

磁共振成像（MRI）血流动力学参数是肿瘤侵袭性和生长的关键指标。然而，其估计常因可靠性低、偏差高、数据处理时间过长以及依赖操作者经验而受阻。为解决这些挑战，我们提出了一种通用的端到端框架（VEFAME），该框架整合了合成数据驱动的学习和空间信息，以实现MRI血流动力学参数的准确高效估计，无需显式选择动脉输入函数（AIF）。VEFAME中使用的合成数据具有精确的AIF、平滑的残差函数、精确的标签以及融合局部平滑性和复杂纹理先验的空间信息。VEFAME的有效性通过数值脑phantom和活体脑的动态对比度敏感度（DSC）和动态对比度增强（DCE）MRI参数估计进行评估。实验结果表明，VEFAME提高了估计的MRI血流动力学参数的准确性、精确度、诊断价值及可靠性。

Keyword:

MRI

Hemodynamic parameter estimation

Synthetic data-driven learning

Full-automatic estimation

End-to-end

期刊

Biomedical Signal Processing and Control

IF:

4.9

论文数:

1.0W

被引数:

2.4W

机构

暂无机构信息

引用论文

The 39 steps: evading error and deciphering the secrets for accurate dynamic susceptibility contrast MRI

NMR in Biomedicine

IF0

2012-07-11

PREAI

Lisa Willats; Fernando Calamante

Estimation of pharmacokinetic parameters from DCE-MRI by extracting long and short time-dependent features using an LSTM network

MEDICAL PHYSICS

IF3.2

2020-06-03

OAAI

Zou, Jiaren; Balter, James M.; Cao, Yue

Differentiation of High-Grade from Low-Grade Astrocytoma: Improvement in Diagnostic Accuracy and Reliability of Pharmacokinetic Parameters from DCE MR Imaging by Using Arterial Input Functions Obtained from DSC MR Imaging

RADIOLOGY

IF15.2

2018-03-01

PREAI

You, Sung-Hye; Choi, Seung Hong; Kim, Tae Min; Park, Chul-Kee; Park, Sung-Hye; Won, Jae-Kyung; Kim, Il Han; Lee, Soon Tae; Choi, Hye Jeong; Yoo, Roh-Eul; Kang, Koung Mi; Yun, Tae Jin; Kim, Ji-Hoon; Sohn, Chul-Ho

Comparison of contrast-enhanced modified T1-weighted 3D TSE black-blood and 3D MP-RAGE sequences for the detection of cerebral metastases and brain tumours

European Radiology

IF0

2015-09-03

PREAI

N. N. Kammer; E. Coppenrath; K. M. Treitl; H. Kooijman; O. Dietrich; T. Saam

Convolutional Neural Networks for Direct Inference of Pharmacokinetic Parameters: Application to Stroke Dynamic Contrast-Enhanced MRI

Frontiers in Neurology

IF0

2019-01-08

OAAI

Cagdas Ulas; Dhritiman Das; Michael J. Thrippleton; Maria del C. Valdés Hernández; Paul A. Armitage; Stephen D. Makin; Joanna M. Wardlaw; Bjoern H. Menze

Differentiation of high-grade and low-grade diffuse gliomas by intravoxel incoherent motion MR imaging

NEURO-ONCOLOGY

IF13.4

2015-08-04

134

OAAI

Togao, Osamu; Hiwatashi, Akio; Yamashita, Koji; Kikuchi, Kazufumi; Mizoguchi, Masahiro; Yoshimoto, Koji; Suzuki, Satoshi O.; Iwaki, Toru; Obara, Makoto; Van Cauteren, Marc; Honda, Hiroshi

High resolution measurement of cerebral blood flow using intravascular tracer bolus passages .1. Mathematical approach and statistical analysis

MAGNETIC RESONANCE IN MEDICINE

IF3

2005-12-12

1.4K

PREAI

Ostergaard, L; Weisskoff, RM; Chesler, DA; Gyldensted, C; Rosen, BR

Determination of arterial input function using fuzzy clustering for quantification of cerebral blood flow with dynamic susceptibility contrast-enhanced MR imaging

JOURNAL OF MAGNETIC RESONANCE IMAGING

IF3.5

2001-04-23

OAAI

Murase, K; Kikuchi, K; Miki, H; Shimizu, T; Ikezoe, J

Single-shot multi-parametric mapping based on multiple overlapping-echo detachment (MOLED) imaging

NeuroImage

IF0

2022-11-01

OAAI

Lingceng Ma; Jian Wu; Qinqin Yang; Zihan Zhou; Hongjian He; Jianfeng Bao; Lijun Bao; Xiaoyin Wang; Pujie Zhang; Jianhui Zhong; Congbo Cai; Shuhui Cai; Zhong Chen

Model-Based SyntheTic Data-Driven Learning (MOST-DL): Application in Single-Shot T2 Mapping With Severe Head Motion Using Overlapping-Echo Acquisition

IEEE TRANSACTIONS ON MEDICAL IMAGING

IF9.8

2022-11-01

PREAI

Yang, Qinqin; Lin, Yanhong; Wang, Jiechao; Bao, Jianfeng; Wang, Xiaoyin; Ma, Lingceng; Zhou, Zihan; Yang, Qizhi; Cai, Shuhui; He, Hongjian; Cai, Congbo; Dong, Jiyang; Cheng, Jingliang; Chen, Zhong; Zhong, Jianhui

查看更多内容