Automatic segmentation of brain glioma from multimodal MRI scans plays a key\nrole in clinical trials and practice. Unfortunately, manual segmentation is\nvery challenging, time-consuming, costly, and often inaccurate despite human\nexpertise due to the high variance and high uncertainty in the human\nannotations. In the present work, we develop an end-to-end deep-learning-based\nsegmentation method using a multi-decoder architecture by jointly learning\nthree separate sub-problems using a partly shared encoder. We also propose to\napply smoothing methods to the input images to generate denoised versions as\nadditional inputs to the network. The validation performance indicate an\nimprovement when using the proposed method. The proposed method was ranked 2nd\nin the task of Quantification of Uncertainty in Segmentation in the Brain\nTumors in Multimodal Magnetic Resonance Imaging Challenge 2020.\n