Morphological and diagnostic evaluation of pediatric musculoskeletal system is crucial in clinical practice. However, most segmentation models do not perform well on scarce pediatric imaging data. We propose a regularized convolutional encoder-decoder network for the challenging task of segmenting pediatric magnetic resonance (MR) images. To overcome the scarcity and heterogeneity of pediatric imaging datasets, we adopt a regularization strategy to improve the generalization of segmentation models. To this end, we have conceived a novel optimization scheme for the segmentation network which comprises additional regularization terms to the loss function. In order to obtain globally consistent predictions, we incorporate a shape priors based regularization, derived from a non-linear shape representation learnt by an auto-encoder. Additionally, an adversarial regularization computed by a discriminator is integrated to encourage plausible delineations. Our method is evaluated for the task of multi-bone segmentation on two pediatric imaging datasets from different joints (ankle and shoulder), comprising pathological as well as healthy examinations. We illustrate that the proposed approach can be easily integrated into various multi-structure strategies and can improve the prediction accuracy of state-of-the-art models. The obtained results bring new perspectives for the management of pediatric musculoskeletal disorders.