Wang Qi, Artières Thierry, Takerkart Sylvain
Institut de Neurosciences de la Timone UMR 7289 Aix-Marseille Université, CNRS Faculté de Médecine, 27 boulevard Jean Moulin, Marseille 13005, France; Laboratoire d'Informatique et Systèmes UMR 7020 Aix-Marseille Université, CNRS, Ecole Centrale de Marseille Faculté des Sciences, 163 avenue de Luminy, Case 901, Marseille 13009, France.
Laboratoire d'Informatique et Systèmes UMR 7020 Aix-Marseille Université, CNRS, Ecole Centrale de Marseille Faculté des Sciences, 163 avenue de Luminy, Case 901, Marseille 13009, France.
Comput Methods Programs Biomed. 2020 Dec;197:105730. doi: 10.1016/j.cmpb.2020.105730. Epub 2020 Sep 11.
In medical imaging, population studies have to overcome the differences that exist between individuals to identify invariant image features that can be used for diagnosis purposes. In functional neuroimaging, an appealing solution to identify neural coding principles that hold at the population level is inter-subject pattern analysis, i.e. to learn a predictive model on data from multiple subjects and evaluate its generalization performance on new subjects. Although it has gained popularity in recent years, its widespread adoption is still hampered by the blatant lack of a formal definition in the literature. In this paper, we precisely introduce the first principled formalization of inter-subject pattern analysis targeted at multivariate group analysis of functional neuroimaging.
We propose to frame inter-subject pattern analysis as a multi-source transductive transfer question, thus grounding it within several well defined machine learning settings and broadening the spectrum of usable algorithms. We describe two sets of inter-subject brain decoding experiments that use several open datasets: a magneto-encephalography study with 16 subjects and a functional magnetic resonance imaging paradigm with 100 subjects. We assess the relevance of our framework by performing model comparisons, where one brain decoding model exploits our formalization while others do not.
The first set of experiments demonstrates the superiority of a brain decoder that uses subject-by-subject standardization compared to state of the art models that use other standardization schemes, making the case for the interest of the transductive and the multi-source components of our formalization The second set of experiments quantitatively shows that, even after such transformation, it is more difficult for a brain decoder to generalize to new participants rather than to new data from participants available in the training phase, thus highlighting the transfer gap that needs to be overcome.
This paper describes the first formalization of inter-subject pattern analysis as a multi-source transductive transfer learning problem. We demonstrate the added value of this formalization using proof-of-concept experiments on several complementary functional neuroimaging datasets. This work should contribute to popularize inter-subject pattern analysis for functional neuroimaging population studies and pave the road for future methodological innovations.
在医学成像中，群体研究必须克服个体之间存在的差异，以识别可用于诊断目的的不变图像特征。在功能神经成像中，一种用于识别在群体水平上成立的神经编码原则的有吸引力的解决方案是主体间模式分析，即对来自多个主体的数据学习一个预测模型，并评估其在新主体上的泛化性能。尽管近年来它已受到广泛关注，但其广泛应用仍因文献中明显缺乏正式定义而受到阻碍。在本文中，我们精确地引入了针对功能神经成像的多变量组分析的主体间模式分析的首个有原则的形式化。
我们提议将主体间模式分析构建为一个多源转导转移问题，从而将其置于几个定义明确的机器学习设置中，并拓宽可用算法的范围。我们描述了两组主体间脑解码实验，这些实验使用了几个公开数据集：一项有16名受试者的脑磁图研究和一项有100名受试者的功能磁共振成像范式。我们通过进行模型比较来评估我们框架的相关性，其中一个脑解码模型采用我们的形式化，而其他模型则不采用。
第一组实验表明，与使用其他标准化方案的现有模型相比，使用逐个受试者标准化的脑解码器具有优越性，这证明了我们形式化中的转导和多源组件的重要性。第二组实验定量地表明，即使经过这样的转换，脑解码器推广到新参与者比推广到训练阶段可用参与者的新数据更困难，从而突出了需要克服的转移差距。
本文将主体间模式分析描述为一个多源转导转移学习问题的首个形式化。我们通过在几个互补的功能神经成像数据集上进行的概念验证实验证明了这种形式化的附加价值。这项工作应有助于推广用于功能神经成像群体研究的主体间模式分析，并为未来的方法创新铺平道路。
