This paper explores the use of self-supervised deep learning in medical imaging cases where two scan modalities are available for same subject. Specifically, we a large publicly-available dataset over 20,000 subjects from UK Biobank with both whole body Dixon technique magnetic resonance (MR) scans and also dual-energy x-ray absorptiometry (DXA) scans. We make three contributions: (i) introduce...

Whole-body magnetic resonance imaging (WB-MRI) is an method without ionising radiation that can provide WB coverage with a core protocol of essential contrasts in less than 40 minutes, and it be complemented sequences to evaluate specific body regions as needed. In many cases, WB-MRI surpasses bone scintigraphy computed tomography detecting characterising lesions, evaluating their response ther...

Whole-body imaging with fluorescent proteins is a powerful technology with many applications in small animals. Brighter, red-shifted proteins can make whole-body imaging more sensitive owing to reduced absorption by tissues and less scatter. A new protein called Katushka has been isolated. It is the brightest known protein with emission at wavelengths longer than 620 nm. This new protein offers...