Multi-Decoder Networks with Multi-Denoising Inputs for Tumor Segmentation

TL;DR

This paper introduces a multi-decoder deep learning approach with denoised inputs for improved brain tumor segmentation in MRI scans, addressing annotation uncertainty and achieving competitive results.

Contribution

It presents a novel multi-decoder architecture with multi-denoising inputs for more accurate tumor segmentation in multimodal MRI scans.

Findings

Improved segmentation accuracy with the proposed method.

Ranked 2nd in the Brain Tumors in Multimodal MRI Challenge 2020.

Enhanced robustness to annotation uncertainty.

Abstract

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