Vaziri Sana, Liu Huawei, Xie Emily, Ratiney Hélène, Sdika Michaël, Lupo Janine M, Xu Duan, Li Yan
Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States.
Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS UMR 5220, Lyon, France.
Front Neurosci. 2023 Aug 29;17:1219343. doi: 10.3389/fnins.2023.1219343. eCollection 2023.
While 3D MR spectroscopic imaging (MRSI) provides valuable spatial metabolic information, one of the hurdles for clinical translation is its interpretation, with voxel-wise quality control (QC) as an essential and the most time-consuming step. This work evaluates the accuracy of machine learning (ML) models for automated QC filtering of individual spectra from 3D healthy control and patient datasets.
A total of 53 3D MRSI datasets from prior studies (30 neurological diseases, 13 brain tumors, and 10 healthy controls) were included in the study. Three ML models were evaluated: a random forest classifier (RF), a convolutional neural network (CNN), and an inception CNN (ICNN) along with two hybrid models: CNN + RF, ICNN + RF. QC labels used for training were determined manually through consensus of two MRSI experts. Normalized and cropped real-valued spectra was used as input. A cross-validation approach was used to separate datasets into training/validation/testing sets of aggregated voxels.
All models achieved a minimum AUC of 0.964 and accuracy of 0.910. In datasets from neurological disease and controls, the CNN model produced the highest AUC (0.982), while the RF model achieved the highest AUC in patients with brain tumors (0.976). Within tumor lesions, which typically exhibit abnormal metabolism, the CNN AUC was 0.973 while that of the RF was 0.969. Data quality inference times were on the order of seconds for an entire 3D dataset, offering drastic time reduction compared to manual labeling.
ML methods accurately and rapidly performed automated QC. Results in tumors highlights the applicability to a variety of metabolic conditions.
虽然三维磁共振波谱成像（MRSI）可提供有价值的空间代谢信息，但临床转化的障碍之一是其解读，其中体素级质量控制（QC）是必不可少且最耗时的步骤。本研究评估了机器学习（ML）模型对来自三维健康对照和患者数据集的个体波谱进行自动QC滤波的准确性。
本研究纳入了先前研究中的53个三维MRSI数据集（30例神经系统疾病、13例脑肿瘤和10例健康对照）。评估了三种ML模型：随机森林分类器（RF）、卷积神经网络（CNN）和初始卷积神经网络（ICNN），以及两种混合模型：CNN + RF、ICNN + RF。用于训练的QC标签由两位MRSI专家通过共识手动确定。将归一化和裁剪后的实值波谱用作输入。采用交叉验证方法将数据集分离为聚集体素的训练/验证/测试集。
所有模型的最小曲线下面积（AUC）均达到0.964，准确率达到0.910。在神经系统疾病和对照的数据集中，CNN模型的AUC最高（0.982），而RF模型在脑肿瘤患者中AUC最高（0.976）。在通常表现出异常代谢的肿瘤病变内，CNN的AUC为0.973，而RF为0.969。对于整个三维数据集，数据质量推断时间约为几秒，与手动标注相比，时间大幅减少。
ML方法准确、快速地执行了自动QC。肿瘤方面的结果突出了其在各种代谢状况下的适用性。
