Deformable shapes provide important and complex geometric features of objects presented in images. However, such information is oftentimes missing or underutilized as implicit knowledge in many image analysis tasks. This paper presents Geo-SIC, the first deep learning model to learn deformable shapes in a deformation space for an improved performance of image classification. We introduce a newly designed framework that (i) simultaneously derives features from both image and latent shape spaces with large intra-class variations; and (ii) gains increased model interpretability by allowing direct access to the underlying geometric features of image data. In particular, we develop a boosted classification network, equipped with an unsupervised learning of geometric shape representations characterized by diffeomorphic transformations within each class. In contrast to previous approaches using pre-extracted shapes, our model provides a more fundamental approach by naturally learning the most relevant shape features jointly with an image classifier. We demonstrate the effectiveness of our method on both simulated 2D images and real 3D brain magnetic resonance (MR) images. Experimental results show that our model substantially improves the image classification accuracy with an additional benefit of increased model interpretability. Our code is publicly available at https://github.com/jw4hv/Geo-SIC

翻译：可变形形状提供了图像中显示的物体的重要和复杂的几何特征。然而,这种信息往往在许多图像分析任务中作为隐含知识而缺失或未充分利用,作为隐含的知识。本文介绍了Geo-SIC,这是在变形空间中学习变形形状的第一个深层次学习模型,以便改进图像分类的性能。我们引入了一个新设计的框架,即(一) 同时从图像和潜在形状空间中产生特征,同时产生巨大的类内变;以及(二) 通过允许直接访问图像数据的基本几何特征而提高模型可解释性。特别是,我们开发了一个升级的分类网络,配备了以不同等级内地貌变形特征为特征的几何形状的不受监督的学习。与以前使用预变形形状来改进图像分类的方法相比,我们的模式提供了一种更根本的方法,即与图像分类仪一起自然地学习最相关的形状特征,我们展示了我们模拟的2D图像和真实的3D脑磁共振图像的方法的有效性。实验结果显示,我们的模型大大改进了图像分类的精确性,增加了模型的可解释性模型。