COVID-MTL: Multitask learning with Shift3D and random-weighted loss for COVID-19 diagnosis and severity assessment

•Automated and simultaneous detection and severity assessment of COVID-19 using CT.•Tackle under segmentation of ground-glass opacities in COVID-19 chest CT scans.•3D CNNs boosted by shifting low-level feature representations of volumetric inputs.•COVID-19 multitask learning performance improved by random-weighted loss function.•Identified features significantly related to positivity and severity of COVID-19.