Segmentation, the problem of locating and outlining objects of interest in images, is a central problem in biomedical image analysis. It is the primary mechanism for quantifying the properties of anatomical structures and pathological formations using complex imaging data. With imaging used extensively across various fields of basic and clinical biomedical research, the value of accurate, reliable, and cost-effective segmentation cannot be understated. In brain research in particular, segmentation of MRI and other imaging modalities is crucial for studying the effects of behavior, disease, and treatment on brain anatomy and function. Despite years of research, automatic segmentation still generally underperforms manual segmentation in terms of reliability, and manual segmentation remains the gold standard in many problems. However, manual segmentation is often prohibitive, especially for large-scale studies or clinical trials. ‘The goal of our work is to develop, validate, and disseminate techniques that combine data from multiple sources in order to reduce the reliability gap between manual and automatic segmentation across a range of applications.