Cardiac imaging protocols usually result in several types of acquisitions and descriptors extracted from the images. The statistical analysis of such data across a population may be challenging, and can be addressed by fusion techniques within a dimensionality reduction framework. However, directly combining different data types may lead to unfair comparisons (for heterogeneous descriptors) or over-exploitation of information (for strongly correlated modalities). In contrast, physicians progressively consider each type of data based on hierarchies derived from their experience or evidence-based recommendations, an inspiring approach for data fusion strategies. In this paper, we propose a novel methodology for hierarchical data fusion and unsupervised representation learning. It mimics the physicians’ approach by progressively integrating different high-dimensional data descriptors according to a known hierarchy. We model this hierarchy with a Hierarchical Gaussian Process Latent Variable Model (GP-LVM), which links the estimated low-dimensional latent representation and high-dimensional observations at each level in the hierarchy, with additional links between consecutive levels of the hierarchy. We demonstrate the relevance of this approach on a dataset of 1726 magnetic resonance image slices from 123 patients revascularized after acute myocardial infarction (MI) (first level in the hierarchy), some of them undergoing reperfusion injury (microvascular obstruction (MVO), second level in the hierarchy). Our experiments demonstrate that our hierarchical model provides consistent data organization across levels of the hierarchy and according to physiological characteristics of the lesions. This allows more relevant statistical analysis of myocardial lesion patterns, and in particular subtle lesions such as MVO.