论文标题
改进了胰腺癌患者的内腔内不相干运动建模和评估的无监督物理学深度学习
Improved unsupervised physics-informed deep learning for intravoxel incoherent motion modeling and evaluation in pancreatic cancer patients
论文作者
论文摘要
$ {\ bf perim} $：较早的工作表明，ivim-net $ _ {arew} $是一种无监督的物理知识的深神经网络，比其他最先进的内部玻璃体内含量 - 含量运动（IVIM）拟合DWI更准确。这项研究提出了改进的版本：IVIM-NET $ _ {OPTIOM} $，并表征了其在胰腺导管腺癌（PDAC）患者中的出色性能。 $ {\ bf方法} $：在模拟（SNR = 20）中，评估了IVIM-NET的准确性，独立性和一致性，以通过计算NRMSE，SPEARMAN的$ $ $ p $ cofficforceforce flication，nrmse，Spearman的$ p $ p $ p $ p $ p $ p $ p $ p $ p $ p $ p $ p $ pofforction（fit S0，fit S0，fit S0，约束，网络体系结构，＃隐藏层，掉落，批处理，学习率） （cv $ _ {net} $）。最佳性能网络Ivim-net $ _ {optim} $与最小二乘（LS）和不同SNR的贝叶斯方法进行了比较。在23名PDAC患者中评估了IVIM-NET $ _ {OPTIOM} $的性能。其中14名患者在扫描课程和9次治疗之间没有接受化学放疗。评估了受试者内标准偏差（WSD）和治疗引起的变化。 $ {\ bf结果} $：在模拟中，ivim-net $ _ {optim} $优于准确性的ivim-net $ _ {arrig} $（nrmse（d）= 0.18 vs 0.20 vs 0.20; nmrse; nmrse（f）= 0.22 （$ρ$（d*，f）= 0.22 vs 0.74）和一致性（cv $ _ {net} $（d）= 0.01 vs 0.10; cv $ _ {net} $（f）= 0.02 vs 0.05 vs 0.05; cv $ _ _ {net} $（net} $（d*）= 0.04 vs 0.11）。 Ivim-net $ _ {optim} $在SNRS <50时显示出优于LS和贝叶斯方法的性能。在体内，ivim-net $ _ {optim} $ sshow的噪声参数映射明显少于d和f的WSD较低的噪声映射，而不是替代方案。在经过处理的队列中，与日常变化相比，IVIM-NET $ _ {optim} $检测到了具有显着参数变化的最单独的患者。 $ {\ bf结论} $：ivim-net $ _ {optim} $建议用于IVIM拟合DWI数据。
${\bf Purpose}$: Earlier work showed that IVIM-NET$_{orig}$, an unsupervised physics-informed deep neural network, was more accurate than other state-of-the-art intravoxel-incoherent motion (IVIM) fitting approaches to DWI. This study presents an improved version: IVIM-NET$_{optim}$, and characterizes its superior performance in pancreatic ductal adenocarcinoma (PDAC) patients. ${\bf Method}$: In simulations (SNR=20), the accuracy, independence and consistency of IVIM-NET were evaluated for combinations of hyperparameters (fit S0, constraints, network architecture, # hidden layers, dropout, batch normalization, learning rate), by calculating the NRMSE, Spearman's $ρ$, and the coefficient of variation (CV$_{NET}$), respectively. The best performing network, IVIM-NET$_{optim}$ was compared to least squares (LS) and a Bayesian approach at different SNRs. IVIM-NET$_{optim}$'s performance was evaluated in 23 PDAC patients. 14 of the patients received no treatment between scan sessions and 9 received chemoradiotherapy between sessions. Intersession within-subject standard deviations (wSD) and treatment-induced changes were assessed. ${\bf Results}$: In simulations, IVIM-NET$_{optim}$ outperformed IVIM-NET$_{orig}$ in accuracy (NRMSE(D)=0.18 vs 0.20; NMRSE(f)=0.22 vs 0.27; NMRSE(D*)=0.39 vs 0.39), independence ($ρ$(D*,f)=0.22 vs 0.74) and consistency (CV$_{NET}$ (D)=0.01 vs 0.10; CV$_{NET}$ (f)=0.02 vs 0.05; CV$_{NET}$ (D*)=0.04 vs 0.11). IVIM-NET$_{optim}$ showed superior performance to the LS and Bayesian approaches at SNRs<50. In vivo, IVIM-NET$_{optim}$ sshowed significantly less noisy parameter maps with lower wSD for D and f than the alternatives. In the treated cohort, IVIM-NET$_{optim}$ detected the most individual patients with significant parameter changes compared to day-to-day variations. ${\bf Conclusion}$: IVIM-NET$_{optim}$ is recommended for IVIM fitting to DWI data.
