Cross-sequence semi-supervised learning for multi-parametric MRI-based visual pathway delineation

Objective.Accurately delineating the visual pathway (VP) is crucial for understanding the human visual system and diagnosing related disorders. Exploring multi-parametric MR imaging data has been identified as an important way to delineate VP. However, due to the complex cross-sequence relationships, existing methods cannot effectively model the complementary information from different MRI sequences. In addition, these existing methods heavily rely on large training data with labels, which is labor-intensive and time-consuming to obtain.Approach.We propose a novel semi-supervised multi-parametric feature decomposition framework for VP delineation. Specifically, a correlation-constrained feature decomposition is designed to handle the complex cross-sequence relationships by capturing the unique characteristics of each MRI sequence and easing the multi-parametric information fusion process. Furthermore, a consistency-based sample enhancement module is developed to address the limited labeled data issue, by generating and promoting meaningful edge information from unlabeled data.Main results.We validate our framework using two public datasets and one in-house multi-shell diffusion MRI dataset. Experimental results demonstrate the superiority of our approach in terms of delineation performance when compared to six state-of-the-art approaches.Significance.Our proposed framework effectively mitigates the challenges of modeling complex cross-sequence relationships and limited labeled data, offering a robust solution for accurate VP delineation. This approach not only enhances the understanding of the human visual system but also holds potential for improving the diagnosis of VP-related disorders.