arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.03359eess.IVcs.CVcs.LG
收藏

一种基于物理启发的MRI伪影生成器和对抗训练的高效半监督质量控制系统的训练方法

An efficient semi-supervised quality control system trained using physics-based MRI-artefact generators and adversarial training

University of Hertfordshire(赫特福德大学);University College London(伦敦大学学院);Queen Square Analytics(皇后广场分析公司);VU University Medical Center(阿姆斯特丹自由大学医学中心)

Daniele Ravi, Frederik Barkhof, Daniel C. Alexander, Lemuel Puglisi, Geoffrey JM Parker, Arman Eshaghi

AI总结:

本研究提出一种半监督质量控制框架,利用物理伪影生成器增强数据,结合特征选择与SVM分类器识别MRI伪影,在临床试验中显著提升性能并支持实时部署。

摘要:

大型医学影像数据集正变得越来越容易获取,但确保样本质量且不含有显著伪影仍具挑战性。现有的医学影像瑕疵识别方法依赖于数据密集型方法,而临床研究中用于训练机器学习模型的富含伪影的扫描图像稀缺,使问题更加复杂。为解决此问题,我们提出一个包含四个主要组件的框架:1)受磁共振物理启发的伪影生成器,用于破坏脑部MRI扫描图像并扩充训练数据集;2)抽象特征和工程特征,用于紧凑地表示图像;3)根据伪影类别进行特征选择的过程,以提高分类性能;4)用于识别伪影的SVM分类器。我们的贡献有三个方面:首先,基于物理的伪影生成器产生带有受控伪影的合成脑部MRI扫描图像,用于数据增强。这将避免对稀有伪影扫描图像进行劳动密集型的收集和标注过程。其次,我们提出一组抽象和工程图像特征,用于识别结构MRI中的9种不同伪影。最后,我们使用基于伪影的特征选择模块,该模块针对每一类伪影,找到提供最佳分类性能的特征集。我们在一个包含人工生成伪影的大型扫描图像数据集上进行了验证实验,并在一个多发性硬化症临床试验中进行了验证,其中真实伪影由专家识别,结果表明所提出的流程优于传统方法。特别是,我们的数据增强在准确率、精确率和召回率上提高了多达12.5个百分点。我们流程的计算效率使其能够实现潜在的实时部署,通过由质量控制系统驱动的自动化图像处理流程,有望实现高通量的临床应用。

英文摘要:

Large medical imaging data sets are becoming increasingly available, but ensuring sample quality without significant artefacts is challenging. Existing methods for identifying imperfections in medical imaging rely on data-intensive approaches, compounded by a scarcity of artefact-rich scans for training machine learning models in clinical research. To tackle this problem, we propose a framework with four main components: 1) artefact generators inspired by magnetic resonance physics to corrupt brain MRI scans and augment a training dataset, 2) abstract and engineered features to represent images compactly, 3) a feature selection process depending on the artefact class to improve classification, and 4) SVM classifiers to identify artefacts. Our contributions are threefold: first, physics-based artefact generators produce synthetic brain MRI scans with controlled artefacts for data augmentation. This will avoid the labour-intensive collection and labelling process of scans with rare artefacts. Second, we propose a pool of abstract and engineered image features to identify 9 different artefacts for structural MRI. Finally, we use an artefact-based feature selection block that, for each class of artefacts, finds the set of features providing the best classification performance. We performed validation experiments on a large data set of scans with artificially-generated artefacts, and in a multiple sclerosis clinical trial where real artefacts were identified by experts, showing that the proposed pipeline outperforms traditional methods. In particular, our data augmentation increases performance by up to 12.5 percentage points on accuracy, precision, and recall. The computational efficiency of our pipeline enables potential real-time deployment, promising high-throughput clinical applications through automated image-processing pipelines driven by quality control systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑